Journal articles on the topic 'Explicit content detection'
To see the other types of publications on this topic, follow the link: Explicit content detection.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Explicit content detection.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Marcial Basilio, Jorge Alberto, Gualberto Aguilar Torres, Gabriel Sanchez Perez, Linda Karina Toscano Medina, Hector Manuel Perez Meana, and Enrique Escamilla Hernadez. "Explicit Content Image Detection." Signal & Image Processing : An International Journal 1, no. 2 (December 29, 2010): 47–58. http://dx.doi.org/10.5121/sipij.2010.1205.
2
Qamar Bhatti, Ali, Muhammad Umer, Syed Hasan Adil, Mansoor Ebrahim, Daniyal Nawaz, and Faizan Ahmed. "Explicit Content Detection System: An Approach towards a Safe and Ethical Environment." Applied Computational Intelligence and Soft Computing 2018 (July 4, 2018): 1–13. http://dx.doi.org/10.1155/2018/1463546.
Abstract:
An explicit content detection (ECD) system to detect Not Suitable For Work (NSFW) media (i.e., image/ video) content is proposed. The proposed ECD system is based on residual network (i.e., deep learning model) which returns a probability to indicate the explicitness in media content. The value is further compared with a defined threshold to decide whether the content is explicit or nonexplicit. The proposed system not only differentiates between explicit/nonexplicit contents but also indicates the degree of explicitness in any media content, i.e., high, medium, or low. In addition, the system also identifies the media files with tampered extension and label them as suspicious. The experimental result shows that the proposed model provides an accuracy of ~ 95% when tested on our image and video datasets.
3
Appati, Justice Kwame, Kennedy Yaw Lodonu, and Richmond Chris-Koka. "A Review of Image Analysis Techniques for Adult Content Detection." International Journal of Software Innovation 9, no. 2 (April 2021): 102–21. http://dx.doi.org/10.4018/ijsi.2021040106.
Abstract:
The fast growth of internet access globally without boundary has led to some negative impacts among children who are exposed to pornographic contents daily. Many parental control strategies have been put in place to protect these children; however, these strategies are usually inspired by political and social interventions. With the availability of computational tools, many automated explicit content detection methods though having their flaws have been proposed to support these social interventions. In this study, a review of the current automated adult content detectors is presented with open issues for future research work.
4
Chen, Xiaoyuan, Turki Aljrees, Muhammad Umer, Hanen Karamti, Saba Tahir, Nihal Abuzinadah, Khaled Alnowaiser, Ala’ Abdulmajid Eshmawi, Abdullah Mohamed, and Imran Ashraf. "A novel approach for explicit song lyrics detection using machine and deep ensemble learning models." PeerJ Computer Science 9 (August 30, 2023): e1469. http://dx.doi.org/10.7717/peerj-cs.1469.
Abstract:
The content of music is not always suitable for all ages. Industries that manage music content are looking for ways to help adults determine what is appropriate for children. Lyrics of songs have become increasingly inappropriate for kids and can negatively impact their mental development. However, it is difficult to filter explicit musical content because it is mostly done manually, which is time-consuming and prone to errors. Existing approaches lack the desired accuracy and are complex. This study suggests using a combination of machine learning and deep learning models to automatically screen song lyrics in this regard. The proposed model, called ELSTM-VC, combines extra tree classifier and long short-term memory and its performance is compared to other models. The ELSTM-VC can detect explicit content in English lyrics and can be useful for the music industry. The study used a dataset of 100 songs from Spotify for training, and the results show that the proposed approach effectively detects explicit lyrics. It can censor offensive content for children with a 96% accuracy. The performance of the proposed approach is better than existing approaches including machine learning models and encoding-decoding models.
5
Muhammad Fadzli, Muhammad Arif Haikal, Mohd Fadzil Abu Hassan, and Norazlin Ibrahim. "Explicit kissing scene detection in cartoon using convolutional long short-term memory." Bulletin of Electrical Engineering and Informatics 11, no. 1 (February 1, 2022): 213–20. http://dx.doi.org/10.11591/eei.v11i1.3542.
Abstract:
The main concern of this study is due to certain cartoon content consisting of explicit scenes such as kissing, sex, violence. That are somehow not suitable for kids and may contradict to some religions and cultures. There are some reasons the film industry does not expel the kissing scene in a cartoon movie. It is categorized as a romance sequence and love scene. These could be a double-edged weapon that will ruin an individual’s childhood through excessive exposure to explicit content. This paper proposes a deep learning-based classifier to detect the kissing scene in the cartoon by using Darknet-19 for frame-level feature extraction, while the feature aggregation in the temporal domain is using convolutional long short-term memory (conv-LSTM). This paper also has discussed a few steps related to evaluation and analysis regarding the performance of the models. Extensive experiments prove that the proposed system provides excellent results of 96.43% accuracy to detect the kissing scene in the cartoon. Due to high accuracy performance, the model is suitable to be a kissing scene filter feature in a digital video player that may able to decrease the excessive exposure to explicit content for kids.
6
Marcial Basilio, Jorge A., Gualberto Aguilar Torres, Gabriel Sánchez Pérez, Karina Toscano Medina, and Héctor M. Pérez Meana. "Novel method for pornographic image detection using HSV and YCbCr color models." Revista Facultad de Ingeniería Universidad de Antioquia, no. 64 (October 3, 2012): 79–90. http://dx.doi.org/10.17533/udea.redin.13117.
Abstract:
In this paper a novel method to explicit content or pornographic images detection is proposed, using the transformation from RGB to HSV or YCbCr color model, which is the most usual format to images that exists on Internet, moreover the using of a threshold to skin detection applying the color models HSV and YCbCr is proposed. Using the proposed threshold the image is segmented, once the image segmented, the skin quantity localized in that image is calculated. The obtained results using the proposed system are compared with two programs which carry out with the same goal, the Forensic Toolkit 3.1 Explicit Image Detection (FTK 3.1 EID) and the Parabenís Porn Detection Stick that are two the most commercials solutions to pornographic images detection. The reported results in this paper were obtained using three sets of images, each one of them consist of 800 images choosing randomly which 400 are natural images and the rest are explicit content images, this sets were used to probe the proposed system and the two tools commercials. The proposed system achieved a 78,75% of recognizing, 28% of false positives and 14,50% of false negatives, the software FTK 3.1 Explicit Image Detection obtained 72,12% of recognizing, 38,50% of false positives and 17,25% of false negatives. Parabenís Porn Detection Stick achieved 74,25% of recognizing with 16% of false positives and 35,50% of false negatives. Finally can be prove that the proposed system be able to detect the images under study better than two of the software solutions more using for forensic researchers, for this reason the proposed method can be applied to computer forensics or in detection of pornographic images stored on mass storage devices.
7
Zhang, Linhao, Li Jin, Xian Sun, Guangluan Xu, Zequn Zhang, Xiaoyu Li, Nayu Liu, Qing Liu, and Shiyao Yan. "TOT：Topology-Aware Optimal Transport for Multimodal Hate Detection." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 4 (June 26, 2023): 4884–92. http://dx.doi.org/10.1609/aaai.v37i4.25614.
Abstract:
Multimodal hate detection, which aims to identify the harmful content online such as memes, is crucial for building a wholesome internet environment. Previous work has made enlightening exploration in detecting explicit hate remarks. However, most of their approaches neglect the analysis of implicit harm, which is particularly challenging as explicit text markers and demographic visual cues are often twisted or missing. The leveraged cross-modal attention mechanisms also suffer from the distributional modality gap and lack logical interpretability. To address these semantic gap issues, we propose TOT: a topology-aware optimal transport framework to decipher the implicit harm in memes scenario, which formulates the cross-modal aligning problem as solutions for optimal transportation plans. Specifically, we leverage an optimal transport kernel method to capture complementary information from multiple modalities. The kernel embedding provides a non-linear transformation ability to reproduce a kernel Hilbert space (RKHS), which reflects significance for eliminating the distributional modality gap. Moreover, we perceive the topology information based on aligned representations to conduct bipartite graph path reasoning. The newly achieved state-of-the-art performance on two publicly available benchmark datasets, together with further visual analysis, demonstrate the superiority of TOT in capturing implicit cross-modal alignment.
8
Bekaryan, Lilit. "Lost in “Transl-Hation”: Exploring the Impact of Machine Translation as an Intermediary Tool in Detecting Armenian Hate Speech." Translation Studies: Theory and Practice 3, no. 2 (6) (December 25, 2023): 40–47. http://dx.doi.org/10.46991/tstp/2023.3.2.040.
Abstract:
As the pervasive spread of hate speech continues to pose significant challenges to online communities, detecting, and countering hateful content on social media has become a priority. Social media platforms typically use machine translation to identify the hateful content of the posts made in languages other than English. If this approach works effectively in identifying explicit hateful content in languages that are predominantly used on social media, its effect is almost insignificant when it comes to Armenian. The present research investigates the effectiveness of machine translation as an intermediary tool in accurately identifying and addressing instances of Armenian hate speech posts retrieved from social networking websites. The study of hate speech posts and comments made by Armenian users in Armenian helps identify that it is often the absence of intricate cultural and linguistic nuances, as well as insufficient contextualized understanding, that impede with hate speech detection in Armenian.
9
FOUCAMBERT, DENIS, and JACQUES BAILLÉ. "Evolution of the missing-letter effect among young readers between ages 5 and 8." Applied Psycholinguistics 32, no. 1 (October 7, 2010): 1–17. http://dx.doi.org/10.1017/s0142716410000263.
Abstract:
ABSTRACTIn light of the numerous studies on the detection of target letters among adults, it is generally accepted that the missing-letter effect depends both on a given word's frequency in its language and on its role (function vs. content) in a sentence. Following a presentation of several models explaining these observations we analyze the results of a letter-detection task given to 886 French students from kindergarten to second grade. The purpose of the present study is to determine the moment when the sensitivity to content/function word distinction emerges. The results of this study reveal that even if word frequency plays a role in letter detection, the emergence of an ability to extract sentence structure, along the lines of the structural model of reading, is significantly linked to the initial stages of explicit reading instruction.
10
Cela-Conde, Camilo J., Gisèle Marty, Enric Munar, Marcos Nadal, and Lucrecia Burges. "The “Style Scheme” Grounds Perception of Paintings." Perceptual and Motor Skills 95, no. 1 (August 2002): 91–100. http://dx.doi.org/10.2466/pms.2002.95.1.91.
Abstract:
We studied the formation of style scheme (identification of the style that characterizes an artist) presenting 100 participants aesthetic visual stimuli. Participants were Spanish university students who volunteered: 72 women, 28 men of mean age 22.8 yr. Among those 50 were enrolled in History of Art and 50 students in Psychology. Stimuli belonged to different categories—High Art (pictures of well-known artists, like Van Gogh)/Popular Art (decorative pictures like Christmas postcards) and Representational (pictures with explicit meaning content, like a landscape)/Abstract (pictures without explicit meaning content, like Pollock's colored stains). Analysis using Signal Detection Theory techniques focused on how participants discriminate representational and abstract pictures. With High An stimuli, participants can better discriminate representational paintings than abstract ones. However, the difference in discrimination between representational and abstract pictures diminishes among participants studying History of Art. It seems that prior education in art favors forming style schemes and to some extent enables the participant to detect the “meaning” in High Art abstract paintings.
11
Seyler, Dominic, Shulong Tan, Dingcheng Li, Jingyuan Zhang, and Ping Li. "Textual Analysis and Timely Detection of Suspended Social Media Accounts." Proceedings of the International AAAI Conference on Web and Social Media 15 (May 22, 2021): 644–55. http://dx.doi.org/10.1609/icwsm.v15i1.18091.
Abstract:
Suspended accounts are high-risk accounts that violate the rules of a social network. These accounts contain spam, offensive and explicit language, among others, and are incredibly variable in terms of textual content. In this work, we perform a detailed linguistic and statistical analysis into the textual information of suspended accounts and show how insights from our study significantly improve a deep-learning-based detection framework. Moreover, we investigate the utility of advanced topic modeling for the automatic creation of word lists that can discriminate suspended from regular accounts. Since early detection of these high-risk accounts is crucial, we evaluate multiple state-of-the-art classification models along the temporal dimension by measuring the minimum amount of textual signal needed to perform reliable predictions. Further, we show that the best performing models are able to detect suspended accounts earlier than the social media platform.
12
Malkawi, Rami, Mohammad Daradkeh, Ammar El-Hassan, and Pavel Petrov. "A Semantic Similarity-Based Identification Method for Implicit Citation Functions and Sentiments Information." Information 13, no. 11 (November 17, 2022): 546. http://dx.doi.org/10.3390/info13110546.
Abstract:
Automated citation analysis is becoming increasingly important in assessing the scientific quality of publications and identifying patterns of collaboration among researchers. However, little attention has been paid to analyzing the scientific content of the citation context. This study presents an unsupervised citation detection method that uses semantic similarities between citations and candidate sentences to identify implicit citations, determine their functions, and analyze their sentiments. We propose different document vector models based on TF-IDF weights and word vectors and compare them empirically to calculate their semantic similarity. To validate this model for identifying implicit citations, we used deep neural networks and LDA topic modeling on two citation datasets. The experimental results show that the F1 values for the implicit citation classification are 88.60% and 86.60% when the articles are presented in abstract and full-text form, respectively. Based on the citation function, the results show that implicit citations provide background information and a technical basis, while explicit citations emphasize research motivation and comparative results. Based on the citation sentiment, the results showed that implicit citations tended to describe the content objectively and were generally neutral, while explicit citations tended to describe the content positively. This study highlights the importance of identifying implicit citations for research evaluation and illustrates the difficulties researchers face when analyzing the citation context.
13
Despot, Kristina Š., Ana Ostroški Anić, and Tony Veale. "“Somewhere along your pedigree, a bitch got over the wall!” A proposal of implicitly offensive language typology." Lodz Papers in Pragmatics 19, no. 2 (December 1, 2023): 385–414. http://dx.doi.org/10.1515/lpp-2023-0019.
Abstract:
Abstract The automatic detection of implicitly offensive language is a challenge for NLP, as such language is subtle, contextual, and plausibly deniable, but it is becoming increasingly important with the wider use of large language models to generate human-quality texts. This study argues that current difficulties in detecting implicit offence are exacerbated by multiple factors: (a) inadequate definitions of implicit and explicit offense; (b) an insufficient typology of implicit offence; and (c) a dearth of detailed analysis of implicitly offensive linguistic data. In this study, based on a qualitative analysis of an implicitly offensive dataset, a new typology of implicitly offensive language is proposed along with a detailed, example-led account of the new typology, an operational definition of implicitly offensive language, and a thorough analysis of the role of figurative language and humour in each type. Our analyses identify three main issues with previous datasets and typologies used in NLP approaches: (a) conflating content and form in the annotation; (b) treating figurativeness, particularly metaphor, as the main device of implicitness, while ignoring its equally important role in the explicit offence; and (c) an over-focus on form-specific datasets (e.g. focusing only on offensive comparisons), which fails to reflect the full complexity of offensive language use.
14
Lavie, Nilli, Diane M. Beck, and Nikos Konstantinou. "Blinded by the load: attention, awareness and the role of perceptual load." Philosophical Transactions of the Royal Society B: Biological Sciences 369, no. 1641 (May 5, 2014): 20130205. http://dx.doi.org/10.1098/rstb.2013.0205.
Abstract:
What is the relationship between attention and conscious awareness? Awareness sometimes appears to be restricted to the contents of focused attention, yet at other times irrelevant distractors will dominate awareness. This contradictory relationship has also been reflected in an abundance of discrepant research findings leading to an enduring controversy in cognitive psychology. Lavie's load theory of attention suggests that the puzzle can be solved by considering the role of perceptual load. Although distractors will intrude upon awareness in conditions of low load, awareness will be restricted to the content of focused attention when the attended information involves high perceptual load. Here, we review recent evidence for this proposal with an emphasis on the various subjective blindness phenomena, and their neural correlates, induced by conditions of high perceptual load. We also present novel findings that clarify the role of attention in the response to stimulus contrast. Overall, this article demonstrates a critical role for perceptual load across the spectrum of perceptual processes leading to awareness, from the very early sensory responses related to contrast detection to explicit recognition of semantic content.
15
Jakku, Sai Sreekar, Sudheer Narla, Abhinav Reddy Emmadi, and V. Kakulapati. "A Novel Approach to Detection of Fake News in Online Communities." Advances in Research 24, no. 4 (April 8, 2023): 79–84. http://dx.doi.org/10.9734/air/2023/v24i4950.
Abstract:
Fake news serving various political and commercial agendas has emerged on the web and spread rapidly in recent years, thanks in large part to the proliferation of online social networks. People who use informal online groups are especially vulnerable to the sneaky effects of deceptive language used in fake news on the internet, which has far-reaching effects on real society. To make information in informal online communities more reliable, it is important to be able to spot fake news as soon as possible. The goal of this study is to look at the criteria, methods, and calculations that are used to find and evaluate fake news, content, and topics in unstructured online communities. This research is mostly about how vague fake news is and how many connections there are between articles, writers, and topics. In this piece, we introduce FAKEDETECTOR, a novel controlled graph neural network. FAKEDETECTOR creates a deep diffusive organization model based on a wide range of explicit and specific attributes extracted from the textual content, allowing it to simultaneously learn the models of reports, authors, and topics. The complete version of this paper provides exploratory results from extensive experiments on a real fake news dataset designed to distinguish FAKEDETECTOR from two state-of-the-art algorithms.
16
Buchner, Jens S., Ute Wollschläger, and Kurt Roth. "Inverting surface GPR data using FDTD simulation and automatic detection of reflections to estimate subsurface water content and geometry." GEOPHYSICS 77, no. 4 (July 1, 2012): H45—H55. http://dx.doi.org/10.1190/geo2011-0467.1.
Abstract:
A new inversion scheme for common-offset ground-penetrating radar measurements at multiple antenna separations was proposed, which is intermediate between inverting of picked reflectors using ray-tracing and full-waveform inversion. The measurements are modeled similarly to the real data using 2D finite-difference time-domain simulations. These simulations are obtained with a parameterized model of the subsurface that consists of several layers with constant dielectric permittivity and an explicit representation of the layers’ interfaces. Then, reflections in the modeled and in the real data are detected automatically, and the reflections of interest of the real data are selected manually. The sum of squared residuals of the reflections’ traveltime and amplitude is iteratively minimized to estimate subsurface water content and geometry, i.e., the position and shape of the layer interfaces. The method was first tested with a synthetic data set and then applied to a real data set. The comparison of the method’s result with ground-truth data showed an agreement with the subsurface geometry within [Formula: see text] and with the water content, a difference less than [Formula: see text] volume.
17
Peng, Jin, Chengming Liu, Haibo Pang, Xiaomeng Gao, Guozhen Cheng, and Bing Hao. "GP-Net: Image Manipulation Detection and Localization via Long-Range Modeling and Transformers." Applied Sciences 13, no. 21 (November 5, 2023): 12053. http://dx.doi.org/10.3390/app132112053.
Abstract:
With the rise of image manipulation techniques, an increasing number of individuals find it easy to manipulate image content. Undoubtedly, this presents a significant challenge to the integrity of multimedia data, thereby fueling the advancement of image forgery detection research. A majority of current methods employ convolutional neural networks (CNNs) for image manipulation localization, yielding promising outcomes. Nevertheless, CNN-based approaches possess limitations in establishing explicit long-range relationships. Consequently, addressing the image manipulation localization task necessitates a solution that adeptly builds global context while preserving a robust grasp of low-level details. In this paper, we propose GPNet to address this challenge. GPNet combines Transformer and CNN in parallel which can build global dependency and capture low-level details efficiently. Additionally, we devise an effective fusion module referred to as TcFusion, which proficiently amalgamates feature maps generated by both branches. Thorough extensive experiments conducted on diverse datasets showcase that our network outperforms prevailing state-of-the-art manipulation detection and localization approaches.
18
Sui Lyn, Hor, Sarina Mansor, Nouar AlDahoul, and Hezerul Abdul Karim. "Convolutional Neural Network-based Transfer Learning and Classification of Visual Contents for Film Censorship." Journal of Engineering Technology and Applied Physics 2, no. 2 (December 15, 2020): 28–35. http://dx.doi.org/10.33093/jetap.2020.2.2.5.
Abstract:
Content filtering is gaining popularity due to easy exposure of explicit visual contents to the public. Excessive exposure of inappropriate visual contents can cause devastating effects such as the growth of improper mindset and rise of societal issues such as free sex, child abandonment and rape cases. At present, most of the broadcasting media sites are hiring censorship editors to label graphic contents manually. Nevertheless, the efficiency is limited by factors such as the attention span of humans and the training required for the editors. This paper proposes to study the effect of usage of Convolutional Neural Network (CNN) as feature extractor coupled with Support Vector Machine (SVM) as classifier in an automated pornographic detection system. Three CNN architectures: Mobile Net, Visual Geometry Group-19 (VGG-19) and Residual Network-50 Version 2 (ResNet50_V2), and two classifiers: CNN and SVM were utilized to explore the combination that produce the best result. Frames of films fed as input into the CNN were classified into two groups: porn or non-porn. The best accuracy was 92.80% obtained using fine-tuned ResNet50_V2 as feature extractor and SVM as classifier. Transfer learning and SVM have improved the CNN model by approximately 10%.
19
Wen, Hamilton, Janos L. Mathe, Stuart T. Weinberg, Asli Ozdas Weitkamp, and Scott D. Nelson. "Creating an immunization content database for knowledge management across clinical systems." American Journal of Health-System Pharmacy 76, Supplement_3 (July 28, 2019): S79—S84. http://dx.doi.org/10.1093/ajhp/zxz134.
Abstract:
Abstract Purpose A initiative at an academic medical center to create a single database of immunization-related content to inform the build and configuration of immunization-related knowledge assets across multiple clinical systems is described. Methods Semistructured expert interviews were conducted to ascertain the immunization information needs of the institution’s clinical systems. Based on those needs, an immunization domain model constructed with data available from the Centers for Disease Control and Prevention (CDC) website was developed and used to analyze and compare current immunization-related content from CDC data sources with the content of the institution’s clinical systems. Results Five identified clinical systems that used immunization-related content collectively required 22 unique information concepts, 11 of which were obtainable from CDC vaccine code sets. The proportion of vaccines designated by CDC as active products (i.e., currently available administrable vaccines) that were included in the 5 clinical systems ranged from 59% to 95%; in addition, some non–active-status vaccines were listed as active-status products in the various clinical systems. Upon further review, updates to immunization-related content in the 5 clinical systems were implemented. Conclusion Creating a single database for immunization-related content based on CDC data facilitated an explicit and tractable knowledge management process and helped ensure that clinical systems had correct and current content. The immunization domain model created has the potential to assist in the automated detection of updates and relaying those updates to the applicable clinical systems.
20
Kumar, Shubham. "Smart System to Detect Adult Content and Child Pornography on Web." International Journal for Research in Applied Science and Engineering Technology 9, no. 9 (September 30, 2021): 1704–6. http://dx.doi.org/10.22214/ijraset.2021.38256.
Abstract:
Abstract: Adult contents on the internet is very common today but it has become a serious concern now because of many reasons such as the proliferation of free to view adult websites has made it easier for individuals of any age to gain access to explicit content. Children increasingly use mobile devices such as smartphones to access the internet and these adult content can have bad impact on their mind. Excessive exposure to these contents can lead to addiction which can have very adverse effect on their mind and their heath.so i came up with an idea to reduce this activity on internet saving people and childrens in particular. In this paper we will discuss a pipeline of a system developed which consists of three modules. The first one is scanning the heading and subheading of the web page to identify if the page is toxic or not. For this task we have used the SOTA model. The second module finds if the page contains a video and identifies it as adult video or not through video caption. we have used LSTM[1] network for this classification task and the last module is CV module which is the most important part of the project. It is an age detection module which detects the age of the people inside the video. The objective was to block the video if the age of any people doing activity exceeds 18. These modules when passed to the pipeline will forbid internet users to watch any kind of adult content specifically which involves a child. It's important to stop this because this has a very negative impact on our society and it is ruining our culture. Index Terms: Deep Learning, Natural Language Processing, Computer vision, Transformers, LSTM
21
Ziems, Caleb, Ymir Vigfusson, and Fred Morstatter. "Aggressive, Repetitive, Intentional, Visible, and Imbalanced: Refining Representations for Cyberbullying Classification." Proceedings of the International AAAI Conference on Web and Social Media 14 (May 26, 2020): 808–19. http://dx.doi.org/10.1609/icwsm.v14i1.7345.
Abstract:
Cyberbullying is a pervasive problem in online communities. To identify cyberbullying cases in large-scale social networks, content moderators depend on machine learning classifiers for automatic cyberbullying detection. However, existing models remain unfit for real-world applications, largely due to a shortage of publicly available training data and a lack of standard criteria for assigning ground truth labels. In this study, we address the need for reliable data using an original annotation framework. Inspired by social sciences research into bullying behavior, we characterize the nuanced problem of cyberbullying using five explicit factors to represent its social and linguistic aspects. We model this behavior using social network and language-based features, which improve classifier performance. These results demonstrate the importance of representing and modeling cyberbullying as a social phenomenon.
22
Formenton, M., G. Panegrossi, D. Casella, S. Dietrich, A. Mugnai, P. Sanò, F. Di Paola, H. D. Betz, C. Price, and Y. Yair. "Using a cloud electrification model to study relationships between lightning activity and cloud microphysical structure." Natural Hazards and Earth System Sciences 13, no. 4 (April 24, 2013): 1085–104. http://dx.doi.org/10.5194/nhess-13-1085-2013.
Abstract:
Abstract. In this study a one-dimensional numerical cloud electrification model, called the Explicit Microphysics Thunderstorm Model (EMTM), is used to find quantitative relationships between the simulated electrical activity and microphysical properties in convective clouds. The model, based on an explicit microphysics scheme coupled to an ice–ice noninductive electrification scheme, allows us to interpret the connection of cloud microphysical structure with charge density distribution within the cloud, and to study the full evolution of the lightning activity (intracloud and cloud-to-ground) in relation to different environmental conditions. Thus, we apply the model to a series of different case studies over continental Europe and the Mediterranean region. We first compare, for selected case studies, the simulated lightning activity with the data provided by the ground-based Lightning Detection Network (LINET) in order to verify the reliability of the model and its limitations, and to assess its ability to reproduce electrical activity consistent with the observations. Then, using all simulations, we find a correlation between some key microphysical properties and cloud electrification, and derive quantitative relationships relating simulated flash rates to minimum thresholds of graupel mass content and updrafts. Finally, we provide outlooks on the use of such relationships and comments on the future development of this study.
23
Mudler, Jan, Andreas Hördt, Dennis Kreith, Madhuri Sugand, Kirill Bazhin, Lyudmila Lebedeva, and Tino Radić. "Broadband spectral induced polarization for the detection of Permafrost and an approach to ice content estimation – a case study from Yakutia, Russia." Cryosphere 16, no. 11 (November 14, 2022): 4727–44. http://dx.doi.org/10.5194/tc-16-4727-2022.
Abstract:
Abstract. The reliable detection of subsurface ice using non-destructive geophysical methods is an important objective in permafrost research. The ice content of the frozen ground is an essential parameter for further interpretation, for example in terms of risk analysis and for the description of permafrost carbon feedback by thawing processes. The high-frequency induced polarization method (HFIP) enables the measurement of the frequency-dependent electrical conductivity and permittivity of the subsurface, in a frequency range between 100 Hz and 100 kHz. As the electrical permittivity of ice exhibits a strong characteristic behaviour in this frequency range, HFIP in principle is suitable to estimate ice content. Here, we present methodological advancements of the HFIP method and suggest an explicit procedure for ice content estimation. A new measuring device, the Chameleon-II (Radic Research), was used for the first time. Compared to a previous generation, the new system is equipped with longer cables and higher power, such that we can now achieve larger penetration depths up to 10 m. Moreover, it is equipped with technology to reduce electromagnetic coupling effects which can distort the desired subsurface signal. The second development is a method to estimate ice content quantitatively from five Cole–Cole parameters obtained from spectral two-dimensional inversion results. The method is based on a description of the subsurface as a mixture of two components (matrix and ice) and uses a previously suggested relationship between frequency-dependent electrical permittivity and ice content. In this model, the ice relaxation is considered the dominant process in the frequency range around 10 kHz. Measurements on a permafrost site near Yakutsk, Russia, were carried out to test the entire procedure under real conditions at the field scale. We demonstrate that the spectral signal of ice can clearly be identified even in the raw data and show that the spectral 2-D inversion algorithm is suitable to obtain the multidimensional distribution of electrical parameters. The parameter distribution and the estimated ice content agree reasonably well with previous knowledge of the field site from borehole and geophysical investigations. We conclude that the method is able to provide quantitative ice content estimates and that relationships that have been tested in the laboratory may be applied at the field scale.
24
John-Africa, Elijah, and Victor T. Emmah. "Performance Evaluation of LSTM and RNN Models in the Detection of Email Spam Messages." European Journal of Information Technologies and Computer Science 2, no. 6 (November 26, 2022): 24–30. http://dx.doi.org/10.24018/compute.2022.2.6.80.
Abstract:
Email spam is an unwanted bulk message that is sent to a recipient’s email address without explicit consent from the recipient. This is usually considered a means of advertising and maximizing profit, especially with the increase in the usage of the internet for social networking, but can also be very frustrating and annoying to the recipients of these messages. Recent research has shown that about 14.7 billion spam messages are sent out every single day of which more than 45% of these messages are promotional sales content that the recipient did not specifically opt-in. This has gotten the attention of many researchers in the area of natural language processing. In this paper, we used the Long Short-Time Memory (LSTM) for classification tasks between spam and Ham messages. The performance of LSTM is compared with that of a Recurrent Neural Network( RNN) which can also be used for a classification task of this nature but suffers from short-time memory and tends to leave out important information from earlier time steps to later ones in terms of prediction. The evaluation of the result shows that LSTM achieved 97% accuracy with both Adams and RMSprop optimizers compared to RNN with an accuracy of 94% with RMSprop and 87% accuracy with Adams optimizer.
25
Laio, F., P. Allamano, and P. Claps. "Exploiting the information content of hydrological ''outliers'' for goodness-of-fit testing." Hydrology and Earth System Sciences 14, no. 10 (October 12, 2010): 1909–17. http://dx.doi.org/10.5194/hess-14-1909-2010.
Abstract:
Abstract. Validation of probabilistic models based on goodness-of-fit tests is an essential step for the frequency analysis of extreme events. The outcome of standard testing techniques, however, is mainly determined by the behavior of the hypothetical model, FX(x), in the central part of the distribution, while the behavior in the tails of the distribution, which is indeed very relevant in hydrological applications, is relatively unimportant for the results of the tests. The maximum-value test, originally proposed as a technique for outlier detection, is a suitable, but seldom applied, technique that addresses this problem. The test is specifically targeted to verify if the maximum (or minimum) values in the sample are consistent with the hypothesis that the distribution FX(x) is the real parent distribution. The application of this test is hindered by the fact that the critical values for the test should be numerically obtained when the parameters of FX(x) are estimated on the same sample used for verification, which is the standard situation in hydrological applications. We propose here a simple, analytically explicit, technique to suitably account for this effect, based on the application of censored L-moments estimators of the parameters. We demonstrate, with an application that uses artificially generated samples, the superiority of this modified maximum-value test with respect to the standard version of the test. We also show that the test has comparable or larger power with respect to other goodness-of-fit tests (e.g., chi-squared test, Anderson-Darling test, Fung and Paul test), in particular when dealing with small samples (sample size lower than 20–25) and when the parent distribution is similar to the distribution being tested.
26
Laio, F., P. Allamano, and P. Claps. "Exploiting the information content of hydrological "outliers" for goodness-of-fit testing." Hydrology and Earth System Sciences Discussions 7, no. 4 (July 22, 2010): 4851–74. http://dx.doi.org/10.5194/hessd-7-4851-2010.
Abstract:
Abstract. Validation of probabilistic models based on goodness-of-fit tests is an essential step for the frequency analysis of extreme events. The outcome of standard testing techniques, however, is mainly determined by the the behavior of the hypothetical model, FX(x), in the central part of the distribution, while the behavior in the tails of the distribution, which is indeed very relevant in hydrological applications, is relatively unimportant for the results of the tests. The maximum-value test, originally proposed as a technique for outlier detection, is a suitable, but seldom applied, technique that addresses this problem. The test is specifically targeted to verify if the maximum (or minimum) values in the sample are consistent with the hypothesis that the distribution FX(x) is the real parent distribution. The application of this test is hindered by the fact that the critical values for the test should be numerically obtained when the parameters of FX(x) are estimated on the same sample used for verification, which is the standard situation in hydrological applications. We propose here a simple, analytically explicit, technique to suitably account for this effect, based on the application of censored L-moments estimators of the parameters. We demonstrate, with an application that uses artificially generated samples, the superiority of this modified maximum-value test with respect to the standard version of the test. We also show that the test has comparable or larger power with respect to other goodness-of-fit tests (e.g., chi-squared test, Anderson-Darling test, Fung and Paul test), in particular when dealing with small samples (sample size lower than 20–25) and when the parent distribution is similar to the distribution being tested.
27
Jeevan Nagendra Kumar, Y., Rohith Reddy Vanapatla, Vamshi Krishna Pinamoni, Jaswanth Kandukuri, Muntather Almusawi, Aravinda K, Lavish Kansal, and Ravi Kalra. "Detecting cyberbullying in social media using text analysis and ensemble techniques." E3S Web of Conferences 507 (2024): 01069. http://dx.doi.org/10.1051/e3sconf/202450701069.
Abstract:
In the dynamic landscape of our hyper-connected digital world, social media platforms play a dual role as facilitators of global interaction and breeding grounds for harmful behaviors. Cyberbullying, an insidious online menace, inflicts emotional distress and psychological trauma on numerous individuals, underscoring the urgent need for advanced tools to detect and prevent such malevolent actions. This innovative project harnesses the power of artificial intelligence and text analysis to illuminate the dark corners of social media where cyberbullying thrives, offering hope to countless victims. At its core, this endeavor utilizes cutting-edge ensemble techniques, a fusion of diverse machine learning algorithms, to analyze textual content across social media platforms. This approach ensures unparalleled accuracy in identifying and flagging cyberbullying instances, enhancing the efficiency of the detection process while minimizing false positives. The project adopts a multifaceted approach to text analysis, examining explicit language, sentiments, context, and behavioral patterns in online interactions. By delving into the intricacies of human communication, the system distinguishes between genuine expressions and malicious intent, providing a nuanced and accurate assessment.
28
JUPP, JULIE, and JOHN S. GERO. "Visual style: Qualitative and context-dependent categorization." Artificial Intelligence for Engineering Design, Analysis and Manufacturing 20, no. 3 (June 27, 2006): 247–66. http://dx.doi.org/10.1017/s0890060406060197.
Abstract:
Style is an ordering principle by which to structure artifacts in a design domain. The application of a visual order entails some explicit grouping property that is both cognitively plausible and contextually dependent. Central to cognitive–contextual notions are the type of representation used in analysis and the flexibility to allow semantic interpretation. We present a model of visual style based on the concept of similarity as a qualitative context-dependent categorization. The two core components of the model are semantic feature extraction and self-organizing maps (SOMs). The model proposes a method of categorizing two-dimensional unannotated design diagrams using both low-level geometric and high-level semantic features that are automatically derived from the pictorial content of the design. The operation of the initial model, called Q-SOM, is then extended to include relevance feedback (Q-SOM:RF). The extended model can be seen as a series of sequential processing stages, in which qualitative encoding and feature extraction are followed by iterative recategorization. Categorization is achieved using an unsupervised SOM, and contextual dependencies are integrated via cluster relevance determined by the observer's feedback. The following stages are presented: initial per feature detection and extraction, selection of feature sets corresponding to different spatial ontologies, unsupervised categorization of design diagrams based on appropriate feature subsets, and integration of design context via relevance feedback. From our experiments we compare different outcomes from consecutive stages of the model. The results show that the model provides a cognitively plausible and context-dependent method for characterizing visual style in design.
29
Panagiotaropoulos, Theofanis I., Vishal Kapoor, and Nikos K. Logothetis. "Subjective visual perception: from local processing to emergent phenomena of brain activity." Philosophical Transactions of the Royal Society B: Biological Sciences 369, no. 1641 (May 5, 2014): 20130534. http://dx.doi.org/10.1098/rstb.2013.0534.
Abstract:
The combination of electrophysiological recordings with ambiguous visual stimulation made possible the detection of neurons that represent the content of subjective visual perception and perceptual suppression in multiple cortical and subcortical brain regions. These neuronal populations, commonly referred to as the neural correlates of consciousness , are more likely to be found in the temporal and prefrontal cortices as well as the pulvinar, indicating that the content of perceptual awareness is represented with higher fidelity in higher-order association areas of the cortical and thalamic hierarchy, reflecting the outcome of competitive interactions between conflicting sensory information resolved in earlier stages. However, despite the significant insights into conscious perception gained through monitoring the activities of single neurons and small, local populations, the immense functional complexity of the brain arising from correlations in the activity of its constituent parts suggests that local, microscopic activity could only partially reveal the mechanisms involved in perceptual awareness. Rather, the dynamics of functional connectivity patterns on a mesoscopic and macroscopic level could be critical for conscious perception. Understanding these emergent spatio-temporal patterns could be informative not only for the stability of subjective perception but also for spontaneous perceptual transitions suggested to depend either on the dynamics of antagonistic ensembles or on global intrinsic activity fluctuations that may act upon explicit neural representations of sensory stimuli and induce perceptual reorganization. Here, we review the most recent results from local activity recordings and discuss the potential role of effective, correlated interactions during perceptual awareness.
30
Monroe, J. Grey, John K. McKay, Detlef Weigel, and Pádraic J. Flood. "The population genomics of adaptive loss of function." Heredity 126, no. 3 (February 11, 2021): 383–95. http://dx.doi.org/10.1038/s41437-021-00403-2.
Abstract:
AbstractDiscoveries of adaptive gene knockouts and widespread losses of complete genes have in recent years led to a major rethink of the early view that loss-of-function alleles are almost always deleterious. Today, surveys of population genomic diversity are revealing extensive loss-of-function and gene content variation, yet the adaptive significance of much of this variation remains unknown. Here we examine the evolutionary dynamics of adaptive loss of function through the lens of population genomics and consider the challenges and opportunities of studying adaptive loss-of-function alleles using population genetics models. We discuss how the theoretically expected existence of allelic heterogeneity, defined as multiple functionally analogous mutations at the same locus, has proven consistent with empirical evidence and why this impedes both the detection of selection and causal relationships with phenotypes. We then review technical progress towards new functionally explicit population genomic tools and genotype-phenotype methods to overcome these limitations. More broadly, we discuss how the challenges of studying adaptive loss of function highlight the value of classifying genomic variation in a way consistent with the functional concept of an allele from classical population genetics.
31
Thakur, Nirmalya, Shuqi Cui, Karam Khanna, Victoria Knieling, Yuvraj Nihal Duggal, and Mingchen Shao. "Investigation of the Gender-Specific Discourse about Online Learning during COVID-19 on Twitter Using Sentiment Analysis, Subjectivity Analysis, and Toxicity Analysis." Computers 12, no. 11 (October 31, 2023): 221. http://dx.doi.org/10.3390/computers12110221.
Abstract:
This paper presents several novel findings from a comprehensive analysis of about 50,000 Tweets about online learning during COVID-19, posted on Twitter between 9 November 2021 and 13 July 2022. First, the results of sentiment analysis from VADER, Afinn, and TextBlob show that a higher percentage of these Tweets were positive. The results of gender-specific sentiment analysis indicate that for positive Tweets, negative Tweets, and neutral Tweets, between males and females, males posted a higher percentage of the Tweets. Second, the results from subjectivity analysis show that the percentage of least opinionated, neutral opinionated, and highly opinionated Tweets were 56.568%, 30.898%, and 12.534%, respectively. The gender-specific results for subjectivity analysis indicate that females posted a higher percentage of highly opinionated Tweets as compared to males. However, males posted a higher percentage of least opinionated and neutral opinionated Tweets as compared to females. Third, toxicity detection was performed on the Tweets to detect different categories of toxic content—toxicity, obscene, identity attack, insult, threat, and sexually explicit. The gender-specific analysis of the percentage of Tweets posted by each gender for each of these categories of toxic content revealed several novel insights related to the degree, type, variations, and trends of toxic content posted by males and females related to online learning. Fourth, the average activity of males and females per month in this context was calculated. The findings indicate that the average activity of females was higher in all months as compared to males other than March 2022. Finally, country-specific tweeting patterns of males and females were also performed which presented multiple novel insights, for instance, in India, a higher percentage of the Tweets about online learning during COVID-19 were posted by males as compared to females.
32
Ahne, Adrian, Vivek Khetan, Xavier Tannier, Md Imbesat Hassan Rizvi, Thomas Czernichow, Francisco Orchard, Charline Bour, Andrew Fano, and Guy Fagherazzi. "Extraction of Explicit and Implicit Cause-Effect Relationships in Patient-Reported Diabetes-Related Tweets From 2017 to 2021: Deep Learning Approach." JMIR Medical Informatics 10, no. 7 (July 19, 2022): e37201. http://dx.doi.org/10.2196/37201.
Abstract:
Background Intervening in and preventing diabetes distress requires an understanding of its causes and, in particular, from a patient’s perspective. Social media data provide direct access to how patients see and understand their disease and consequently show the causes of diabetes distress. Objective Leveraging machine learning methods, we aim to extract both explicit and implicit cause-effect relationships in patient-reported diabetes-related tweets and provide a methodology to better understand the opinions, feelings, and observations shared within the diabetes online community from a causality perspective. Methods More than 30 million diabetes-related tweets in English were collected between April 2017 and January 2021. Deep learning and natural language processing methods were applied to focus on tweets with personal and emotional content. A cause-effect tweet data set was manually labeled and used to train (1) a fine-tuned BERTweet model to detect causal sentences containing a causal relation and (2) a conditional random field model with Bidirectional Encoder Representations from Transformers (BERT)-based features to extract possible cause-effect associations. Causes and effects were clustered in a semisupervised approach and visualized in an interactive cause-effect network. Results Causal sentences were detected with a recall of 68% in an imbalanced data set. A conditional random field model with BERT-based features outperformed a fine-tuned BERT model for cause-effect detection with a macro recall of 68%. This led to 96,676 sentences with cause-effect relationships. “Diabetes” was identified as the central cluster followed by “death” and “insulin.” Insulin pricing–related causes were frequently associated with death. Conclusions A novel methodology was developed to detect causal sentences and identify both explicit and implicit, single and multiword cause, and the corresponding effect, as expressed in diabetes-related tweets leveraging BERT-based architectures and visualized as cause-effect network. Extracting causal associations in real life, patient-reported outcomes in social media data provide a useful complementary source of information in diabetes research.
33
Jo, Mijoung, Soondool Chung, and Hajin Lee. "Comparative analysis of Ordinances on the Prevention of Lonely Deaths in Metropolitan and Local Governments : Focused on the「Act on the Prevention and Management of Lonely Deaths」." Academy of Social Welfare and Law 14, no. 2 (August 31, 2023): 3–26. http://dx.doi.org/10.35589/swlj.2023.14.2.3.
Abstract:
This study focuses on the need for coordination between the government's Act on the Prevention and Management of Lonely Deaths and the ordinances of local governments. It distinguishes between metropolitan and local governments to examine their current status and characteristics. The study also proposes improvement suggestions for the amendment and enhancement of relevant ordinances. A total of 232 ordinances obtained from the Local Autonomous Regulations Information System of the National Law Information Center were analyzed using content analysis. The analysis framework categorized the ordinances into basic information, normative framework, and effectiveness system for comparative analysis.
The analysis findings reveal several key insights. Firstly, in terms of basic information, the ordinance titles commonly combined terminologies related to lonely deaths, household types, and age criteria. Furthermore, the definitions of key terms related to lonely deaths in most local governments primarily focused on the end-of-life and post-end-of-life stages. Secondly, within the normative framework, the ordinances were structured to align with the provisions of the Act on the Prevention and Management of Lonely Deaths. However, many ordinances imposed limitations on the scope and requirements of policy targets, and some lacked explicit mention of residents' responsibilities or included arbitrary provisions for surveys.
Thirdly, in the effectiveness system, support contents varied between metropolitan and local governments. While metropolitan governments emphasized preventive aspects such as early detection, local governments focused on counseling, well-being checks, technology utilization, and funeral support. Additionally, most support systems contained passive provisions, with the exception of clauses allowing financial support within budgetary limits. Notably, metropolitan governments explicitly mentioned the utilization of private resources, unlike local governments.
Based on these analysis findings, the study proposes the following improvement suggestions for ordinances. Firstly, based on the Act on the Prevention and Management of Lonely Deaths, modifications and supplements are needed in the titles and definitions of ordinances. A comprehensive approach is required, expanding the scope of vulnerable groups susceptible to lonely deaths, considering various situational characteristics. Secondly, it is crucial to specify the support contents, delivery systems, and efforts to secure financial resources in the existing ordinances related to the prevention of lonely deaths. This will enable the integrated delivery of lonely death prevention services. To achieve this, the deployment, training, and expansion of specialized personnel, as well as the establishment of relevant centers, need to be expanded.
34
Markovsky, Aleksandr V. "ADDITIVE EFFECT OF GENES POLYMORPHISM OF FOLATE CYCLE PROTEINS AND HOMOCYSTEIN LEVEL IN PATIENTS WITH PROLIFERATIVE DISEASES OF THE BREAST AS A POTENTIAL FACTOR OF THE RISK OF THROMBOSSES." Atherothrombosis Journal, no. 2 (December 27, 2018): 46–53. http://dx.doi.org/10.21518/2307-1109-2018-2-46-53.
Abstract:
Aim.The aim of study was to examine the relationship between serum and mammary gland homocysteine levels with the carrier of separate SNP (single nucleotide polymorphism) genes of the folate metabolism system in patients with proliferative diseases and breast cancer.Methods and results.The study included 182 patients with proliferative diseases of the mammary gland in transbaikalia. The control group included 144 women who did not have oncological diseases. The serum homocysteine level and the supernatant of the mammary tissue homogenate were evaluated by high performance liquid chromatography. Genotyping for the detection of polymorphism MTHFRС677T, MTHFRА1298C, MTRA2756G, MTRRA66G was carried out by polymerase chain reaction with the detection of the amplification product in real time. In the course of molecular genetic testing in patients with proliferative diseases of the mammary gland, there was found: 1) the absence of an explicit association of the carriage of genetic polymorphism MTHFRС677T, MTHFRА1298C, MTRA2756G and MTRRA66G with serum homocysteine concentration, however, comparative hyperhomocysteinemia and, to a lesser extent, in women with the benign breast diseases; 2) the highest homocysteine content in the blood in patients with breast cancer whose genotype was characterized by combinations of polymorphic alleles MTR2756G x MTRR66G; 3) that the MTR2756A allele and genotype MTHFR1298AC, especially their combination of MTHFR1298AC x MTR2756A, increase the risk of developing benign breast formations; 4) the effect of the risk alleles MTR2756G and MTRR66GON the concentration of homocystein in the tumor tissue of the mammary gland.Conclusion. These patterns indicate a certain contribution of the polymorphisms studied, especially their additive effect, both in the development of proliferative diseases of the mammary gland and in the possible potentiation of prothrombotic effects in these patients against the background of tumor progression and homocysteine metabolism disorders.
35
Dewani, Amirita, Mohsin Ali Memon, Sania Bhatti, Adel Sulaiman, Mohammed Hamdi, Hani Alshahrani, Abdullah Alghamdi, and Asadullah Shaikh. "Detection of Cyberbullying Patterns in Low Resource Colloquial Roman Urdu Microtext using Natural Language Processing, Machine Learning, and Ensemble Techniques." Applied Sciences 13, no. 4 (February 5, 2023): 2062. http://dx.doi.org/10.3390/app13042062.
Abstract:
Social media platforms have become a substratum for people to enunciate their opinions and ideas across the globe. Due to anonymity preservation and freedom of expression, it is possible to humiliate individuals and groups, disregarding social etiquette online, inevitably proliferating and diversifying the incidents of cyberbullying and cyber hate speech. This intimidating problem has recently sought the attention of researchers and scholars worldwide. Still, the current practices to sift the online content and offset the hatred spread do not go far enough. One factor contributing to this is the recent prevalence of regional languages in social media, the dearth of language resources, and flexible detection approaches, specifically for low-resource languages. In this context, most existing studies are oriented towards traditional resource-rich languages and highlight a huge gap in recently embraced resource-poor languages. One such language currently adopted worldwide and more typically by South Asian users for textual communication on social networks is Roman Urdu. It is derived from Urdu and written using a Left-to-Right pattern and Roman scripting. This language elicits numerous computational challenges while performing natural language preprocessing tasks due to its inflections, derivations, lexical variations, and morphological richness. To alleviate this problem, this research proposes a cyberbullying detection approach for analyzing textual data in the Roman Urdu language based on advanced preprocessing methods, voting-based ensemble techniques, and machine learning algorithms. The study has extracted a vast number of features, including statistical features, word N-Grams, combined n-grams, and BOW model with TFIDF weighting in different experimental settings using GridSearchCV and cross-validation techniques. The detection approach has been designed to tackle users’ textual input by considering user-specific writing styles on social media in a colloquial and non-standard form. The experimental results show that SVM with embedded hybrid N-gram features produced the highest average accuracy of around 83%. Among the ensemble voting-based techniques, XGboost achieved the optimal accuracy of 79%. Both implicit and explicit Roman Urdu instances were evaluated, and the categorization of severity based on prediction probabilities was performed. Time complexity is also analyzed in terms of execution time, indicating that LR, using different parameters and feature combinations, is the fastest algorithm. The results are promising with respect to standard assessment metrics and indicate the feasibility of the proposed approach in cyberbullying detection for the Roman Urdu language.
36
Gobel, Sry Ade Muhtya, Elnovani Lusiana, and Susanne Dida. "Mental Health Promotion: Stop Self-Diagnosing Through Social Media." Jurnal Promkes 11, no. 1 (March 10, 2023): 71–81. http://dx.doi.org/10.20473/jpk.v11.i1.2023.71-81.
Abstract:
Background: Mental health is increasingly being recognized as a severe problem. While there has been an increasing awareness of mental health and psychological well-being for economic and social development over the past two decades, there has not been a corresponding increase in mental health investment. Social media platforms allow healthcare practitioners to take full advantage of the potential of social media. However, this good thing is followed by a bad thing, where more and more information is accessible; people use that information to benchmark that they also have a "mental disorder" while not consulting a professional (psychologist/psychiatrist). Incidents like this are commonly referred to as self-diagnosis. Method: Therefore, this study will discuss the existence of information and promotion through accurate and explicit content related to self-diagnosis, using qualitative research with a case study approach. Results: The results obtained are that this accessibility allows the public to seek information about the symptoms they are experiencing, thereby facilitating early detection of mental health disorders. The power of social media to engage audiences to improve communication and expand the capacity to promote programs, products, and services should be valued in health promotion. Conclusion: Social media platforms, regardless of time or location, allow practically infinite opportunities to interact and communicate with others. This ease of use of on-demand communication may be critical in increasing social connection among people suffering from mental illnesses who have difficulty interacting in person.
37
Lin, Qinan, Huaguo Huang, Linfeng Yu, and Jingxu Wang. "Detection of Shoot Beetle Stress on Yunnan Pine Forest Using a Coupled LIBERTY2-INFORM Simulation." Remote Sensing 10, no. 7 (July 18, 2018): 1133. http://dx.doi.org/10.3390/rs10071133.
Abstract:
Yunnan pine shoot beetles (PSB), Tomicus yunnanensis and Tomicus minor have spread through southwestern China in the last five years, leading to millions of hectares of forest being damaged. Thus, there is an urgent need to develop an effective approach for accurate early warning and damage assessment of PSB outbreaks. Remote sensing is one of the most efficient methods for this purpose. Despite many studies existing on the mountain pine beetle (MPB), very little work has been undertaken on assessing PSB stress using remote sensing. The objective of this paper was to develop a spectral linear mixing model aided by radiative transfer (RT) and a new Yellow Index (YI) to simulate the reflectance of heterogeneous canopies containing damaged needles and quantitatively inverse their PSB stress. The YI, the fraction of dead needles, is a physically-explicit stress indicator that represents the plot shoots damage ratio (plot SDR). The major steps of this methods include: (1) LIBERTY2 was developed to simulate the reflectance of damaged needles using YI to linearly mix the green needle spectra with the dead needle spectra; (2) LIBERTY2 was coupled with the INFORM model to scale the needle spectra to the canopy scale; and (3) a look-up table (LUT) was created against Sentinel 2 (S2) imagery and inversed leaf chlorophyll content (LCC), green leaf area index (LAI) and plot SDR. The results show that (1) LIBERTY2 effectively simulated the reflectance spectral values on infested needles (mean relative error (MRE) = 1.4–18%), and the YI can indicate the degrees of needles damage; (2) the coupled LIBERTY2-INFORM model is suitable to estimate LAI (R2 = 0.73, RMSE = 0.17 m m−2, NRMSE = 11.41% and the index of agreement (IOA) = 0.92) and LCC (R2 = 0.49, RMSE = 56.24 mg m−2, NRMSE = 25.22% and IOA = 0.72), and is better than the original LIBERTY model (LAI: R2 = 0.38, RMSE = 0.43 m m−2, NRMSE = 28.85% and IOA = 0.68; LCC: R2 = 0.34, RMSE = 76.44 mg m−2, NRMSE = 34.23% and IOA = 0.57); and (3) the inversed YI is positively correlated with the measured plot SDR (R2 = 0.40, RMSE = 0.15). We conclude that the LIBERTY2 model improved the reflectance simulation accuracy of both the needles and canopies, making it suitable for assessing PSB stress. The YI has the potential to assess PSB damage.
38
McCauley, Robert N., George Graham, and A. C. Reid. "Theory of Mind, Religiosity, and Autistic Spectrum Disorder: a Review of Empirical Evidence Bearing on Three Hypotheses." Journal of Cognition and Culture 19, no. 5 (November 8, 2019): 411–31. http://dx.doi.org/10.1163/15685373-12340067.
Abstract:
AbstractThe cognitive science of religions’ By-Product Theory contends that much religious thought and behavior can be explained in terms of the cultural activation of maturationally natural cognitive systems. Those systems address fundamental problems of human survival, encompassing such capacities as hazard precautions, agency detection, language processing, and theory of mind. Across cultures they typically arise effortlessly and unconsciously during early childhood. They are not taught and appear independent of general intelligence. Theory of mind (mentalizing) undergirds an instantaneous and automatic intuitive understanding of minds, mental representations, and their implications for agents’ actions. By-Product theorists hypothesize about a social cognition content bias, holding that mentalizing capacities inform participants’ implicit understanding of religious representations of agents with counter-intuitive properties. That hypothesis, in combination with Baron-Cohen’s account of Autistic Spectrum Disorder (ASD) in terms of diminished theory of mind capacities (what he calls “mind-blindness”), suggests an impaired religious understanding hypothesis. It proposes that people with ASD have substantial limitations in intuitive understanding of and creative inferences from such representations. Norenzayan argues for a mind-blind atheism hypothesis, which asserts that the truth of these first two hypotheses suggests that people with ASD have an increased probability, compared to the general population, of being atheists. Numerous empirical studies have explored these three hypotheses’ merits. After carefully pondering distinctions between intuitive versus reflective mentalizing and between explicit versus implicit measures and affective versus cognitive measures of mentalizing, the available empirical evidence provides substantial support for the first two hypotheses and non-trivial support for the third.
39
Sahbeni, Ghada, Balázs Székely, Peter K. Musyimi, Gábor Timár, and Ritvik Sahajpal. "Crop Yield Estimation Using Sentinel-3 SLSTR, Soil Data, and Topographic Features Combined with Machine Learning Modeling: A Case Study of Nepal." AgriEngineering 5, no. 4 (October 9, 2023): 1766–88. http://dx.doi.org/10.3390/agriengineering5040109.
Abstract:
Effective crop monitoring and accurate yield estimation are fundamental for informed decision-making in agricultural management. In this context, the present research focuses on estimating wheat yield in Nepal at the district level by combining Sentinel-3 SLSTR imagery with soil data and topographic features. Due to Nepal’s high-relief terrain, its districts exhibit diverse geographic and soil properties, leading to a wide range of yields, which poses challenges for modeling efforts. In light of this, we evaluated the performance of two machine learning algorithms, namely, the gradient boosting machine (GBM) and the extreme gradient boosting (XGBoost). The results demonstrated the superiority of the XGBoost-based model, achieving a determination coefficient (R2) of 0.89 and an RMSE of 0.3 t/ha for training, with an R2 of 0.61 and an RMSE of 0.42 t/ha for testing. The calibrated model improved the overall accuracy of yield estimates by up to 10% compared to GBM. Notably, total nitrogen content, slope, total column water vapor (TCWV), organic matter, and fractional vegetation cover (FVC) significantly influenced the predicted values. This study highlights the effectiveness of combining multi-source data and Sentinel-3 SLSTR, particularly proposing XGBoost as an alternative tool for accurately estimating yield at lower costs. Consequently, the findings suggest comprehensive and robust estimation models for spatially explicit yield forecasting and near-future yield projection using satellite data acquired two months before harvest. Future work can focus on assessing the suitability of agronomic practices in the region, thereby contributing to the early detection of yield anomalies and ensuring food security at the national level.
40
Rospocher, Marco, and Samaneh Eksir. "Assessing Fine-Grained Explicitness of Song Lyrics." Information 14, no. 3 (March 2, 2023): 159. http://dx.doi.org/10.3390/info14030159.
Abstract:
Music plays a crucial role in our lives, with growing consumption and engagement through streaming services and social media platforms. However, caution is needed for children, who may be exposed to explicit content through songs. Initiatives such as the Parental Advisory Label (PAL) and similar labelling from streaming content providers aim to protect children from harmful content. However, so far, the labelling has been limited to tagging the song as explicit (if so), without providing any additional information on the reasons for the explicitness (e.g., strong language, sexual reference). This paper addresses this issue by developing a system capable of detecting explicit song lyrics and assessing the kind of explicit content detected. The novel contributions of the work include (i) a new dataset of 4000 song lyrics annotated with five possible reasons for content explicitness and (ii) experiments with machine learning classifiers to predict explicitness and the reasons for it. The results demonstrated the feasibility of automatically detecting explicit content and the reasons for explicitness in song lyrics. This work is the first to address explicitness at this level of detail and provides a valuable contribution to the music industry, helping to protect children from exposure to inappropriate content.
41
Zhao, Jian, Ming Xiao, Juntao Chen, and Dongdong Li. "Explicit Dynamic DDA Method considering Dynamic Contact Force." Shock and Vibration 2016 (2016): 1–12. http://dx.doi.org/10.1155/2016/7431245.
Abstract:
This paper proposes an explicit dynamic DDA method considering dynamic contact force, which aims at solving the problems of low efficiency of dynamic contact detection and the simulation of dynamic contact force in the conventional DDA method. The mutual contact between blocks can be regarded as the application of point loading on a single block, and the corresponding contact submatrix can be calculated and the simultaneous equations of the block system can be integrated. The central difference method is adopted to deduce the explicit expression of block displacement containing dynamic contact force. With the relationship between displacement and dynamic contact force, contact constraint equations of a block system are obtained to calculate the dynamic contact force and the corresponding block displacement. The accuracy of the explicit dynamic DDA method is verified using two numerical cases. The calculation results show that the new DDA method can be applied in large-scale geotechnical engineering.
42
Mendoza, Juan Pablo, Reid Simmons, and Manuela Veloso. "Detection and correction of subtle context-dependent robot model inaccuracies using parametric regions." International Journal of Robotics Research 38, no. 8 (May 20, 2019): 887–909. http://dx.doi.org/10.1177/0278364919845047.
Abstract:
Autonomous robots frequently rely on models of their sensing and actions for intelligent decision making. Unfortunately, in complex environments, robots are bound to encounter situations in which their models do not accurately represent the world. Furthermore, these context-dependent model inaccuracies may be subtle, such that multiple observations may be necessary to distinguish them from noise. This paper formalizes the problem of detection and correction of such subtle contextual model inaccuracies in autonomous robots, and presents an algorithm to address this problem. The solution relies on reasoning about these contextual inaccuracies as parametric regions of inaccurate modeling (RIMs) in the robot’s planning space. Empirical results from various real robot domains demonstrate that, by explicitly searching for RIMs, robots are capable of efficiently detecting subtle contextual model inaccuracies, which in turn can lead to task performance improvement.
43
Mastouri, Mahmoud, Zied Bouyahia, Hedi Haddad, Leila Horchani, and Nafaa Jabeur. "A Context-Aware, Computer-Vision-Based Approach for the Detection of Taxi Street-Hailing Scenes from Video Streams." Sensors 23, no. 10 (May 16, 2023): 4796. http://dx.doi.org/10.3390/s23104796.
Abstract:
With the increasing deployment of autonomous taxis in different cities around the world, recent studies have stressed the importance of developing new methods, models and tools for intuitive human–autonomous taxis interactions (HATIs). Street hailing is one example, where passengers would hail an autonomous taxi by simply waving a hand, exactly like they do for manned taxis. However, automated taxi street-hailing recognition has been explored to a very limited extent. In order to address this gap, in this paper, we propose a new method for the detection of taxi street hailing based on computer vision techniques. Our method is inspired by a quantitative study that we conducted with 50 experienced taxi drivers in the city of Tunis (Tunisia) in order to understand how they recognize street-hailing cases. Based on the interviews with taxi drivers, we distinguish between explicit and implicit street-hailing cases. Given a traffic scene, explicit street hailing is detected using three elements of visual information: the hailing gesture, the person’s relative position to the road and the person’s head orientation. Any person who is standing close to the road, looking towards the taxi and making a hailing gesture is automatically recognized as a taxi-hailing passenger. If some elements of the visual information are not detected, we use contextual information (such as space, time and weather) in order to evaluate the existence of implicit street-hailing cases. For example, a person who is standing on the roadside in the heat, looking towards the taxi but not waving his hand is still considered a potential passenger. Hence, the new method that we propose integrates both visual and contextual information in a computer-vision pipeline that we designed to detect taxi street-hailing cases from video streams collected by capturing devices mounted on moving taxis. We tested our pipeline using a dataset that we collected with a taxi on the roads of Tunis. Considering both explicit and implicit hailing scenarios, our method yields satisfactory results in relatively realistic settings, with an accuracy of 80%, a precision of 84% and a recall of 84%.
44
Ruan, Dongsheng, Jun Wen, Nenggan Zheng, and Min Zheng. "Linear Context Transform Block." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 5553–60. http://dx.doi.org/10.1609/aaai.v34i04.6007.
Abstract:
Squeeze-and-Excitation (SE) block presents a channel attention mechanism for modeling global context via explicitly capturing dependencies across channels. However, we are still far from understanding how the SE block works. In this work, we first revisit the SE block, and then present a detailed empirical study of the relationship between global context and attention distribution, based on which we propose a simple yet effective module, called Linear Context Transform (LCT) block. We divide all channels into different groups and normalize the globally aggregated context features within each channel group, reducing the disturbance from irrelevant channels. Through linear transform of the normalized context features, we model global context for each channel independently. The LCT block is extremely lightweight and easy to be plugged into different backbone models while with negligible parameters and computational burden increase. Extensive experiments show that the LCT block outperforms the SE block in image classification task on the ImageNet and object detection/segmentation on the COCO dataset with different backbone models. Moreover, LCT yields consistent performance gains over existing state-of-the-art detection architectures, e.g., 1.5∼1.7% APbbox and 1.0%∼1.2% APmask improvements on the COCO benchmark, irrespective of different baseline models of varied capacities. We hope our simple yet effective approach will shed some light on future research of attention-based models.
45
Ji, Wenting, Hanfen Shi, Tianyi Feng, Shuang Zhang, Haixia Liu, Wenxiu Xu, Xueqian Wang, and Qingguo Wang. "Majie Cataplasm Promotes Th1 Response to Fight against Asthmatic Th2 Inflammation through NKs." Evidence-Based Complementary and Alternative Medicine 2022 (May 12, 2022): 1–12. http://dx.doi.org/10.1155/2022/6745420.
Abstract:
Background. Immune cells are tightly bound up with the pathogenesis of asthma. Besides T cells, B cells, macrophages, and mast cells, the mechanism of innate lymphoid cells (ILCs) in asthma is gradually explicit. As a kind of traditional Chinese medicine, Majie cataplasm realizes its potential in the clinical setting as an adjuvant for asthma. In our previous experiments, Majie cataplasm inhibits the increasing Th1 and Th2 in allergic asthma inflammation and reshapes a balance between Th1 and Th2. As ILCs are the reflection of Th cells in lung tissues, we will figure out whether Majie cataplasm could have similar effects on ILCs or not. Methods. A total of 40 female C57/BL6 mice were randomly divided into the control group (n = 10), the asthma model group (n = 10), the dexamethasone group (n = 10), and the Majie cataplasm group (n = 10). Except for the control group, mice were sensitized with ovalbumin (OVA) and excited to establish mice models of asthma. Lung tissue and splenic tissue were collected at 24 h after the last challenge with OVA, and the cell suspension of the lungs and spleen was prepared. The number of ILC1s, ILC2s, ILC3s, and NKs cells in the lungs and Tregs and B10s in the spleen were detected by flow cytometry (FCM). This was followed by simultaneous quantitative detection of 40 inflammatory cytokines and chemokines in the lung by a protein microarray. Results. The dexamethasone and Majie cataplasm could restore the number of ILC1s, ILC2s, and ILC3s in lung tissue. Compared with the control group, these cells remained unchanged in the asthma model group, while ILC1s ( P < 0.001 , P < 0.01 ), ILC2s ( P < 0.001 , P < 0.01 ), and ILC3s ( P < 0.01 , P < 0.05 ) were restored after the intervention of dexamethasone and Majie cataplasm. The number of NKs was low among the control group, the asthma model group, and the dexamethasone group, while the number of NKs rocketed in the Majie cataplasm group ( P < 0.0001 ). For splenic Tregs and B10s, Majie cataplasm could curb the increasing numbers of them in the asthma model group ( P < 0.0001 , P < 0.01 ), while only Tregs were suppressed by the dexamethasone ( P < 0.0001 ). For the inflammatory cytokines in the lung, the contents of TNF-α, TNFR2, CXCL-9, CCL-12, CCL-9, CCL-2, and CCL-5 in the asthma model group were higher than those in the control group, while the contents of GM-CSF and IL-1α were decreased. Comparing the asthma model group to the dexamethasone group, the levels of G-CSF, CCL-9, CCL-5, and TNFR2 in the former group were higher. The levels of TNF-α, TNFR2, and CCL-9 in the asthma model group increase, while the levels of IFN-γ, IL-1α, ICAM-1, and IL-4 increased in the Majie cataplasm group, especially IFN-γ and IL-1α. Conclusion. Both the dexamethasone and Majie cataplasm could control the asthmatic inflammation by reducing the inflammatory factors, inhibiting the adaptive inflammation reaction in the latter stage of inflammation and furtherly reversing the inhibition of ILC2s, ILC2s, and ILC3s. In addition, Majie cataplasm can promote the quantity of NKs and the content of IL-1α and IFN-γ, induce IFN-γ+NKs to shut down the Th2 response, and tend to elicit the Th1 response.
46
Maeda, Tatsuro, Kazuaki Oishi, Hiroto Ishii, Hiroyuki Ishii, Wen Hsin Chang, Tetsuji Shimizu, Akira Endoh, Hiroki Fujishiro, and Takashi Koida. "Schottky barrier contact on In0.53Ga0.47As with short-wave infrared transparent conductive oxide." Applied Physics Letters 121, no. 23 (December 5, 2022): 232102. http://dx.doi.org/10.1063/5.0129445.
Abstract:
In this study, we fabricate and investigate Schottky barrier contact on n- and p-type In0.53Ga0.47As with transparent conductive oxide (TCO) that transmits light from the visible to short-wave infrared (SWIR) region. The TCO/p-In0.53Ga0.47As contact exhibits explicit rectifying behavior in current–voltage measurement, with an effective Schottky barrier height of 0.587 eV ( I– V) and 0.567 eV ( C– V). Conversely, the TCO/n-In0.53Ga0.47As exhibits the Ohmic behavior. From high-resolution transmission electron microscopy observations, we identified two types of interfacial layers between TCO and InGaAs: an In/Ga-rich InGaAs oxide layer and an In/Ga-deficient InGaAs layer. These interfacial layers may have a significant impact on the performance of the Schottky barrier contact. An ultra-thin Ni-layer insertion at the TCO/n+-InGaAs interface reduces the contact resistivity by more than an order of magnitude while maintaining high transparency. The TCO/p-InGaAs Schottky barrier contact also performs broadband light detection from the visible to SWIR region in a front-side illumination manner, which is highly promising for detecting wavelengths covering the optical communication band.
47
Dunshea, Glenn, Nélio B. Barros, Elizabeth J. Berens McCabe, Nicholas J. Gales, Mark A. Hindell, Simon N. Jarman, and Randall S. Wells. "Stranded dolphin stomach contents represent the free-ranging population's diet." Biology Letters 9, no. 3 (June 23, 2013): 20121036. http://dx.doi.org/10.1098/rsbl.2012.1036.
Abstract:
Diet is a fundamental aspect of animal ecology. Cetacean prey species are generally identified by examining stomach contents of stranded individuals. Critical uncertainty in these studies is whether samples from stranded animals are representative of the diet of free-ranging animals. Over two summers, we collected faecal and gastric samples from healthy free-ranging individuals of an extensively studied bottlenose dolphin population. These samples were analysed by molecular prey detection and these data compared with stomach contents data derived from stranded dolphins from the same population collected over 22 years. There was a remarkable consistency in the prey species composition and relative amounts between the two datasets. The conclusions of past stomach contents studies regarding dolphin habitat associations, prey selection and proposed foraging mechanisms are supported by molecular data from live animals and the combined dataset. This is the first explicit test of the validity of stomach contents analysis for accurate population-scale diet determination of an inshore cetacean.
48
Calvo, Manuel G., P. Avero, M. Dolores Castillo, and Juan J. Miguel-Tobal. "Multidimensional Anxiety and Content-specificity Effects in Preferential Processing of Threat." European Psychologist 8, no. 4 (January 2003): 252–65. http://dx.doi.org/10.1027//1016-9040.8.4.252.
Abstract:
We examined the relative contribution of specific components of multidimensional anxiety to cognitive biases in the processing of threat-related information in three experiments. Attentional bias was assessed by the emotional Stroop word color-naming task, interpretative bias by an on-line inference processing task, and explicit memory bias by sensitivity (d') and response criterion (β) from word-recognition scores. Multiple regression analyses revealed, first, that phobic anxiety and evaluative anxiety predicted selective attention to physical- and ego-threat information, respectively; cognitive anxiety predicted selective attention to both types of threat. Second, phobic anxiety predicted inhibition of inferences related to physically threatening outcomes of ambiguous situations. And, third, evaluative anxiety predicted a response bias, rather than a genuine memory bias, in the reporting of presented and nonpresented ego-threat information. Other anxiety components, such as motor and physiological anxiety, or interpersonal and daily-routines anxiety made no specific contribution to any cognitive bias. Multidimensional anxiety measures are useful for detecting content-specificity effects in cognitive biases.
49
Römer, Ulrich J., Alexander Fidlin, and Wolfgang Seemann. "Explicit analytical solutions for two-dimensional contact detection problems between almost arbitrary geometries and straight or circular counterparts." Mechanism and Machine Theory 128 (October 2018): 205–24. http://dx.doi.org/10.1016/j.mechmachtheory.2018.05.018.
50
Berdnikova, T. V. "The Problem of Detecting Incitement in Extremist Content (Using Examples from the Internet)." Theory and Practice of Forensic Science 14, no. 3 (October 23, 2019): 34–39. http://dx.doi.org/10.30764/1819-2785-2019-14-3-34-39.
Abstract:
The article considers the characteristics of targeting when identifying the signs of incitement in extremist materials: in texts, commentaries to articles, videos, audios etc. on the Internet. The methods of linguistic analysis (lexical-semantic, stylistic analysis, semantic analysis, communicative-pragmatic analysis) were used in the study. As a result, the following forms of targeting expression in the aspect of linguistic signs of incitement were identified: 1) an appeal to a specific interlocutor (to a specific person, group of persons); 2) through the components of the communicative situation in general (focus on the mass, public addressee and even on the self which is transformed into a focus on the own group). Complicated cases of the implementation of the targeting category in texts with a pronounced or hidden language game are noted. The definition of the targeting category is shown to be an important component when identifying the linguistic signs of the “incitement” meaning, the speech (text) purpose depends on it. Targeting is closely related to the types of incitement: direct/indirect, explicit/implicit. To identify the linguistic features of the “incitement” meaning it is necessary to conduct a multidimensional analysis considering the general communicative situation, the category of targeting and its implementation in the statement.