Готові списки джерел за темами / EMOLIS Dataset

Зміст

Статті в журналах
Дисертації
Частини книг
Тези доповідей конференцій

Добірка наукової літератури з теми "EMOLIS Dataset"

Автор: Grafiati

Опубліковано: 29 березня 2025

Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями

Оберіть тип джерела:

Ознайомтеся зі списками актуальних статей, книг, дисертацій, тез та інших наукових джерел на тему "EMOLIS Dataset".

Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.

Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.

Статті в журналах з теми "EMOLIS Dataset"

Saadi, Wafa, Fatima Zohra Laallam, Messaoud Mezati, Dikra Louiza Youmbai, and Nour Elhouda Messaoudi. "Enhancing emotion detection on Twitter: an ensemble clustering approach utilizing emojis and keywords across multilingual datasets." STUDIES IN ENGINEERING AND EXACT SCIENCES 5, no. 2 (November 13, 2024): e10548. http://dx.doi.org/10.54021/seesv5n2-522.

Повний текст джерела

Анотація:

Social media has become a vital element of everyday life, shaping domains like business, politics, and personal interactions. Emotions play a critical role in these areas, necessitating accurate detection and interpretation, especially on platforms like Twitter (X), which feature short texts, various data formats (such as words, Emojis, and numbers), and multilingual content, including dialects. This study explores the importance of Emojis and keywords in positively interpreting emotions on Twitter (X). It uses ensemble-clustering techniques, combining different clustering algorithms like KMeans with various methods for a detailed analysis of emotional subtleties in social media discourse. By merging the semantic meanings of Emojis and keywords, a novel clustering ensemble algorithm is proposed to improve emotion detection accuracy. The approach is tested on two datasets: English and Arabic dataset, using the Ekman model, which classifies emotions into six basic categories (joy, sadness, anger, disgust, surprise, and fear). The findings from this integrated method show greater accuracy and precision compared to individual methods, providing valuable insights into public sentiments, enhancing customer satisfaction analysis, and improving social media monitoring tools.

Стилі APA, Harvard, Vancouver, ISO та ін.

Częstochowska, Justyna, Kristina Gligorić, Maxime Peyrard, Yann Mentha, Michał Bień, Andrea Grütter, Anita Auer, Aris Xanthos, and Robert West. "On the Context-Free Ambiguity of Emoji." Proceedings of the International AAAI Conference on Web and Social Media 16 (May 31, 2022): 1388–92. http://dx.doi.org/10.1609/icwsm.v16i1.19393.

Повний текст джерела

Анотація:

Due to their pictographic nature, emojis come with baked-in, grounded semantics. Although this makes emojis promising candidates for new forms of more accessible communication, it is still unknown to what degree humans agree on the inherent meaning of emojis when encountering them outside of concrete textual contexts. To bridge this gap, we collected a crowdsourced dataset (made publicly available) of one-word descriptions for 1,289 emojis presented to participants with no surrounding text. The emojis and their interpretations were then examined for ambiguity. We find that, with 30 annotations per emoji, 16 emojis (1.2%) are completely unambiguous, whereas 55 emojis (4.3%) are so ambiguous that the variation in their descriptions is as high as that in randomly chosen descriptions. Most emojis lie between these two extremes. Furthermore, investigating the ambiguity of different types of emojis, we find that emojis representing symbols from established, yet not cross-culturally familiar code books (e.g., zodiac signs, Chinese characters) are most ambiguous. We conclude by discussing design implications.

Стилі APA, Harvard, Vancouver, ISO та ін.

Arjun Kuruva and Dr. C. Nagaraju. "A Robust Hybrid Model for Text and Emoji Sentiment Analysis: Leveraging BERT and Pre-trained Emoji Embeddings." Bioscan 20, no. 1 (January 24, 2025): 186–91. https://doi.org/10.63001/tbs.2025.v20.i01.pp186-191.

Повний текст джерела

Анотація:

Sentiment analysis, a critical subfield of natural language processing, is widely employed to decipher the emotions andopinions expressed in textual data. With the growing prevalence of emojis in digital communication, understanding theircontribution alongside textual information has become paramount for comprehensive sentiment classification. This paperproposes a novel hybrid deep learning model for sentiment analysis that effectively integrates advanced feature fusion andattention mechanisms to address the challenges of analyzing multimodal data. By combining BERT-based textual embeddingsand pre-trained emoji embeddings, the model captures nuanced semantic and emotional information. A self-attentionmechanism further enhances the representation by identifying long-range dependencies and contextual relationships betweentext and emojis. The model was evaluated on the Sentiment140 dataset, achieving state-of-the-art performance with anaccuracy of 91.7%, an F1-score of 93.6%, and an AUC of 96.4%, outperforming existing models such as BERT-LSTM andRoBERTa-GRU. This superior performance demonstrates the effectiveness of multimodal fusion in sentiment classification,particularly for social media data where emojis play a significant role in emotional expression. The proposed architecture alsoshows strong generalizability, offering robust performance across diverse datasets. While computational complexity is a notedchallenge, future research could explore optimization techniques to improve efficiency without compromising accuracy. Thiswork highlights the potential of hybrid models to advance sentiment analysis by bridging the gap between textual and visual-emotional communication, setting a foundation for more comprehensive multimodal understanding in natural languageprocessing tasks.

Стилі APA, Harvard, Vancouver, ISO та ін.

Nakonechnyi, O. G., O. A. Kapustian, Iu M. Shevchuk, M. V. Loseva, and O. Yu Kosukha. "A intellectual system of analysis of reactions to news based on data from Telegram channels." Bulletin of Taras Shevchenko National University of Kyiv. Series: Physics and Mathematics, no. 3 (2022): 55–61. http://dx.doi.org/10.17721/1812-5409.2022/3.7.

Повний текст джерела

Анотація:

This paper describes the system of intellectual analysis and prediction of reactions to the news based on data from Telegram channels In particular, the features of collecting and pre-processing datasets for the intelligence systems, the methodology of thematic analysis of the received data, and the model used to obtain predictions of reactions to Telegram messages depending on their text are described We show the work of this system in the example of the Ukrainian news Telegram channel The results are estimations of probability of emojis for the news from the testing dataset Also, we give F-measures for our approaches to precise input data and models.

Стилі APA, Harvard, Vancouver, ISO та ін.

Peng, Jiao, Yue He, Yongjuan Chang, Yanyan Lu, Pengfei Zhang, Zhonghong Ou, and Qingzhi Yu. "A Social Media Dataset and H-GNN-Based Contrastive Learning Scheme for Multimodal Sentiment Analysis." Applied Sciences 15, no. 2 (January 10, 2025): 636. https://doi.org/10.3390/app15020636.

Повний текст джерела

Анотація:

Multimodal sentiment analysis faces a number of challenges, including modality missing, modality heterogeneity gap, incomplete datasets, etc. Previous studies usually adopt schemes like meta-learning or multi-layer structures. Nevertheless, these methods lack interpretability for the interaction between modalities. In this paper, we constructed a new dataset, SM-MSD, for sentiment analysis in social media (SAS) that differs significantly from conventional corpora, comprising 10K instances of diverse data from Twitter, encompassing text, emoticons, emojis, and text embedded in images. This dataset aims to reflect authentic social scenarios and various emotional expressions, and provides a meaningful and challenging evaluation benchmark for multimodal sentiment analysis in specific contexts. Furthermore, we propose a multi-task framework based on heterogeneous graph neural networks (H-GNNs) and contrastive learning. For the first time, heterogeneous graph neural networks are applied to multimodal sentiment analysis tasks. In the case of additional labeling data, it guides the emotion prediction of the missing mode. We conduct extensive experiments on multiple datasets to verify the effectiveness of the proposed scheme. Experimental results demonstrate that our proposed scheme surpasses state-of-the-art methods by 1.7% and 0 in accuracy and 1.54% and 4.9% in F1-score on the MOSI and MOSEI datasets, respectively, and exhibits robustness to modality missing scenarios.

Стилі APA, Harvard, Vancouver, ISO та ін.

Hauthal, Eva, Alexander Dunkel, and Dirk Burghardt. "Emojis as Contextual Indicants in Location-Based Social Media Posts." ISPRS International Journal of Geo-Information 10, no. 6 (June 12, 2021): 407. http://dx.doi.org/10.3390/ijgi10060407.

Повний текст джерела

Анотація:

The presented study aims to investigate the relationship between the use of emojis in location-based social media and the location of the corresponding post in terms of perceived objects and conducted activities connected to this place. The basis for this is not a purely frequency-based assessment, but a specifically introduced measure called typicality. To evaluate the typicality measure and examine the assumption that emojis are contextual indicants, a dataset of worldwide geotagged posts from Instagram relating to sunset and sunrise events is used, converted to a privacy-aware version based on a Hyperloglog approach. Results suggest that emojis can often provide more nuanced information about user activities and the surrounding environment than is possible with hashtags. Thus, emojis may be suitable for identifying less obvious characteristics and the sense of a place. Emojis are already explored in research, but mainly for sentiment analysis, for semantic studies or as part of emoji prediction. In contrast, this work provides novel insights into the user’s spatial or activity context by applying the typicality measure and therefore considers emojis contextual indicants.

Стилі APA, Harvard, Vancouver, ISO та ін.

Almalki, Jameel. "A machine learning-based approach for sentiment analysis on distance learning from Arabic Tweets." PeerJ Computer Science 8 (July 26, 2022): e1047. http://dx.doi.org/10.7717/peerj-cs.1047.

Повний текст джерела

Анотація:

Social media platforms such as Twitter, YouTube, Instagram and Facebook are leading sources of large datasets nowadays. Twitter’s data is one of the most reliable due to its privacy policy. Tweets have been used for sentiment analysis and to identify meaningful information within the dataset. Our study focused on the distance learning domain in Saudi Arabia by analyzing Arabic tweets about distance learning. This work proposes a model for analyzing people’s feedback using a Twitter dataset in the distance learning domain. The proposed model is based on the Apache Spark product to manage the large dataset. The proposed model uses the Twitter API to get the tweets as raw data. These tweets were stored in the Apache Spark server. A regex-based technique for preprocessing removed retweets, links, hashtags, English words and numbers, usernames, and emojis from the dataset. After that, a Logistic-based Regression model was trained on the pre-processed data. This Logistic Regression model, from the field of machine learning, was used to predict the sentiment inside the tweets. Finally, a Flask application was built for sentiment analysis of the Arabic tweets. The proposed model gives better results when compared to various applied techniques. The proposed model is evaluated on test data to calculate Accuracy, F1 Score, Precision, and Recall, obtaining scores of 91%, 90%, 90%, and 89%, respectively.

Стилі APA, Harvard, Vancouver, ISO та ін.

Madderi Sivalingam, Saravanan, Smitha Ponnaiyan Sarojam, Malathi Subramanian, and Kalachelvi Thulasingam. "A new mining and decoding framework to predict expression of opinion on social media emoji’s using machine learning models." IAES International Journal of Artificial Intelligence (IJ-AI) 13, no. 4 (December 1, 2024): 5005. http://dx.doi.org/10.11591/ijai.v13.i4.pp5005-5012.

Повний текст джерела

Анотація:

<span lang="EN-US">This research work proposes a new framework mining and decoding (MindE) to predict the expression of opinion on social media emojis using machine learning (ML) models. Expression of opinion can be predicted with short messages on social media. This study used two groups of ML algorithms, convolutional neural network (CNN) ImageNet and CNN AlexNet classifier, and finally, applied the decision tree classifier to predict the type of expression. A recent dataset was taken from Kaggle, an open-source dataset consisting of 7476 rows of emojis for expression of opinion prediction. Accuracy was computed with a G power of 80%, and the experiment was repeated 20 times using both models. After the introduction of the proposed MindE framework, the performance of an expression of opinion prediction will be analyzed with accuracy level. The CNN ImageNet achieved an impressive 97.32% accuracy, whereas the CNN AlexNet algorithm reached only 85.98%. The independent sample T Test indicated a p-value of 0.001, which is below the significance level of 0.05. This suggests that the performance difference between the two ML algorithms is statistically significant. Consequently, the results strongly support the proposed framework “MindE” to predict the expression of opinion on social media emojis.</span>

Стилі APA, Harvard, Vancouver, ISO та ін.

Anu Kiruthika M. and Angelin Gladston. "Implementation of Recurrent Network for Emotion Recognition of Twitter Data." International Journal of Social Media and Online Communities 12, no. 1 (January 2020): 1–13. http://dx.doi.org/10.4018/ijsmoc.2020010101.

Повний текст джерела

Анотація:

A new generation of emoticons, called emojis, is being largely used for both mobile and social media communications. Emojis are considered a graphic expression of emotions, and users have been widely used to express their emotions in social media. Emojis are graphic unicode symbols used to express perceptions, views, and ideas as a shorthand. Unlike the small number of well-known emoticons carrying clear emotional content, hundreds of emojis are being used in different social networks. The task of emoji emotion recognition is to predict the original emoji in a tweet. Recurrent neural network is used for building emoji emotion recognition system. Glove is a word-embedding method used for obtaining vector representation of words and are used for training the recurrent neural network. This is achieved by mapping words into a meaningful space where the distance between words is related to semantic similarity. Based on the word embedding in the Twitter dataset, recurrent neural network builds the model and finally predicts the emoji associated with the tweets with an accuracy of 83%.

Стилі APA, Harvard, Vancouver, ISO та ін.

Chen, Zhenpeng, Yanbin Cao, Huihan Yao, Xuan Lu, Xin Peng, Hong Mei, and Xuanzhe Liu. "Emoji-powered Sentiment and Emotion Detection from Software Developers’ Communication Data." ACM Transactions on Software Engineering and Methodology 30, no. 2 (March 2021): 1–48. http://dx.doi.org/10.1145/3424308.

Повний текст джерела

Анотація:

Sentiment and emotion detection from textual communication records of developers have various application scenarios in software engineering (SE). However, commonly used off-the-shelf sentiment/emotion detection tools cannot obtain reliable results in SE tasks and misunderstanding of technical knowledge is demonstrated to be the main reason. Then researchers start to create labeled SE-related datasets manually and customize SE-specific methods. However, the scarce labeled data can cover only very limited lexicon and expressions. In this article, we employ emojis as an instrument to address this problem. Different from manual labels that are provided by annotators, emojis are self-reported labels provided by the authors themselves to intentionally convey affective states and thus are suitable indications of sentiment and emotion in texts. Since emojis have been widely adopted in online communication, a large amount of emoji-labeled texts can be easily accessed to help tackle the scarcity of the manually labeled data. Specifically, we leverage Tweets and GitHub posts containing emojis to learn representations of SE-related texts through emoji prediction. By predicting emojis containing in each text, texts that tend to surround the same emoji are represented with similar vectors, which transfers the sentiment knowledge contained in emoji usage to the representations of texts. Then we leverage the sentiment-aware representations as well as manually labeled data to learn the final sentiment/emotion classifier via transfer learning. Compared to existing approaches, our approach can achieve significant improvement on representative benchmark datasets, with an average increase of 0.036 and 0.049 in macro-F1 in sentiment and emotion detection, respectively. Further investigations reveal that the large-scale Tweets make a key contribution to the power of our approach. This finding informs future research not to unilaterally pursue the domain-specific resource but try to transform knowledge from the open domain through ubiquitous signals such as emojis. Finally, we present the open challenges of sentiment and emotion detection in SE through a qualitative analysis of texts misclassified by our approach.

Стилі APA, Harvard, Vancouver, ISO та ін.

Більше джерел

Дисертації з теми "EMOLIS Dataset"

Lerch, Soëlie. "Suggestion de dessins animés par similarité émotionnelle : Approches neuronales multimodales combinant contenus et données physiologiques." Electronic Thesis or Diss., Toulon, 2024. http://www.theses.fr/2024TOUL0005.

Повний текст джерела

Анотація:

Le cadre général de cette thèse concerne l’étude des sentiments et des émotions afin de mieux comprendre leurs impacts, leurs interactions et ainsi améliorer la communication humain-machine. Un auteur peut véhiculer des sentiments et des émotions dans un message écrit ou au travers d’une vidéo et de ses personnages. Ces émotions et sentiments vont être interprétés par un lecteur ou un spectateur qui vont, eux-mêmes, ressentir des émotions. L’identification de ces émotions est subjective et n’est pas toujours facile. Par exemple, pour un spectateur, a-t-il été surpris ? a-t-il eu peur ? les deux ? Comment retrouver des vidéos qui lui permettront d’avoir les mêmes ressentis ? Pour répondre à ce type de questions, nos contributions exploitent, dans une analyse informatique, différentes modalités liées au contenu du support de communication mais aussi aux réactions physiologiques de ceux qui les reçoivent afin de détecter et d’identifier des émotions et de pouvoir leur suggérer des supports émotionnellement similaires. L’une de nos problématiques concerne la modélisation du sentiment et de l’émotion pour créer des modèles performants de détection de sentiments et d’émotions. Pour cela, nous étudions différentes représentations de données pour la prédiction d’émotions en exploitant la seule modalité texte. Différentes approches supervisées sont mises en œuvre ne nécessitant pas de lexiques. La seule modalité texte pouvant être ambiguë, nous étudions différentes représentations de données pour la prédiction d’émotions d’un point de vue multimodal. Pour cela, nous créons le corpus EMOLIS Dataset composé de dessins animés annotés en émotions et accompagnés de signaux physiologiques de spectateurs. Nous utilisons d’une part la modalité texte pour le contenu sémantique via la transcription des dialogues, la modalité image pour les expressions faciales des personnages, et la modalité audio pour les voix des personnages. D’autre part, nous exploitons des signaux physiologiques tels que électrocardiogramme, respiration et mouvements oculaires du spectateur. Ces différentes modalités permettent de prendre en compte à la fois l’émotion véhiculée par le contenu de la vidéo et les émotions ressenties par les spectateurs. Nous utilisons ensuite ce jeu de données pour évaluer différents modèles d’identification d’émotions contenues dans EMOLIS Dataset. Deux approches sont expérimentées selon une fusion tardive ou précoce des représentations des modalités avant la classification. Enfin, nous analysons l’impact de la prise en compte des émotions et des sentiments pour la suggestion de dessins animés. Nous décrivons le logiciel EMOLIS App qui permet la suggestion de dessins animés issus d’EMOLIS Dataset. Cette suggestion est basée sur le calcul de similarités entre matrices émotionnelles et multimodales et les signaux physiologiques. En perspective, EMOLIS App pourrait être exploitée dans le cadre de thérapies cognitives et comportementales pour les personnes présentant des troubles du spectre autistique et ayant des difficultés à identifier et verbaliser leurs émotions
The general framework of this thesis related to the study of feelings and emotions to better understand their impacts and interactions, thereby improving human-machine communication. An author can convey feelings and emotions in a written message or through a video and its characters. These emotions and feelings are then interpreted by a reader or a viewer, who, in turn, experiences emotions. Identifying these emotions is subjective and not always easy. For example, was a viewer surprised? Were they scared? Or both? How can we find videos that would allow them to feel the same emotions again? To address such questions, our contributions leverage various modalities in a computational analysis—considering both the communication medium's content and the physiological reactions of recipients—to detect and identify emotions and to suggest emotionally similar content.Our first research question concerns the modeling of feelings and emotions to create efficient models for sentiment and emotion detection. To this end, we study different data representations for emotion prediction by utilizing only the textual modality. Various supervised approaches are implemented, which do not require lexicons.Since the textual modality alone can be ambiguous, we examine different data representations for emotion prediction from a multimodal perspective. For this purpose, we create the EMOLIS Dataset, consisting of cartoons annotated with emotions and accompanied by viewers' physiological signals. On one hand, we use the text modality to capture semantic content via dialogue transcription, the image modality for characters' facial expressions, and the audio modality for characters' voices. On the other hand, we utilize physiological signals such as electrocardiograms, respiration, and eye movements of viewers. These different modalities allow us to consider both the emotion conveyed by the video content and the emotions experienced by viewers.Then, we use this dataset to evaluate different models for identifying emotions contained within the EMOLIS Dataset. Two approaches are experimented with, depending on whether representations of modalities are merged late or early in the classification process.Finally, we analyze the impact of incorporating emotions and feelings into cartoon recommendations. We describe the EMOLIS App software, which suggests cartoons from the EMOLIS Dataset. This suggestion is based on calculating similarities between emotional and multimodal matrices as well as physiological signals.In the future, EMOLIS App could potentially be used in cognitive-behavioral therapies for individuals on the autism spectrum who may have difficulty identifying and verbalizing their emotions

Стилі APA, Harvard, Vancouver, ISO та ін.

Частини книг з теми "EMOLIS Dataset"

Gupta, Shelley, Archana Singh, and Jayanthi Ranjan. "An Online Document Emoji-Based Classification Using Twitter Dataset." In Proceedings of Data Analytics and Management, 409–17. Singapore: Springer Singapore, 2021. http://dx.doi.org/10.1007/978-981-16-6285-0_33.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Martín Gascón, Beatriz. "Chapter 11. Irony in American-English tweets." In Current Issues in Linguistic Theory, 197–217. Amsterdam: John Benjamins Publishing Company, 2024. http://dx.doi.org/10.1075/cilt.366.11mar.

Повний текст джерела

Анотація:

The present study examines verbal irony from a cognitive linguistics perspective, based on Ruiz de Mendoza’s (2017) development of the echoic account and on big data. Built on previous research on the detection of Spanish ironic utterances in Twitter (Martín-Gascón, 2019), this investigation aims to analyze how American-English speakers conceptualize and express irony and compares findings to the Spanish ones. The dataset, initially consisting of 1,157,773,379 tweets from 248 countries and 66 languages, was first reduced to 27,517 tweets from English-speaking users in the United States using the words “irony”, “ironies”, and “ironic”, then to 605 containing the words as hashtag and finally to 495 tweets evincing implicit and explicit-echoic irony. An in-depth cognitive and qualitative analysis of the sample revealed the complexities of perceiving irony in written discourse and, therefore, the relevance of adding contextual ironic markers, such as hashtags, emojis, interjections, laughter typing and ironic phraseology, among others. In line with Martín-Gascón’s (2019) study, findings showed a higher use of positive and explicit-echoic irony as compared to implicit and negative irony. By drawing attention to the similarities and differences in the expression of irony, we expect to offer preliminary informed options for the design of pedagogical proposals that enhance not only the learners’ linguistic and ironic competencies, but also their intercultural awareness.

Стилі APA, Harvard, Vancouver, ISO та ін.

Das, Ankit, and Saubhik Bandyopadhyay. "Analysis of Oversampling and Its Impact on an Imbalanced Dataset for Emoji Prediction from Tweets Using Machine Learning Techniques." In Lecture Notes in Networks and Systems, 297–308. Singapore: Springer Nature Singapore, 2025. https://doi.org/10.1007/978-981-97-8476-9_21.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Hartman, Ryan, S. M. Mahdi Seyednezhad, Diego Pinheiro, Josemar Faustino, and Ronaldo Menezes. "Entropy in Network Community as an Indicator of Language Structure in Emoji Usage: A Twitter Study Across Various Thematic Datasets." In Studies in Computational Intelligence, 328–37. Cham: Springer International Publishing, 2018. http://dx.doi.org/10.1007/978-3-030-05411-3_27.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Anu Kiruthika M. and Angelin Gladston. "Implementation of Recurrent Network for Emotion Recognition of Twitter Data." In Research Anthology on Implementing Sentiment Analysis Across Multiple Disciplines, 398–411. IGI Global, 2022. http://dx.doi.org/10.4018/978-1-6684-6303-1.ch022.

Повний текст джерела

Анотація:

Стилі APA, Harvard, Vancouver, ISO та ін.

Doan, Minh Tri, Minh Phuong Dam, Tram T. Doan, Hung Nguyen, and Binh T. Nguyen. "Sentiment Classification in Mobile Gaming Reviews: Customized Transformer Models with Emojis Retained." In Frontiers in Artificial Intelligence and Applications. IOS Press, 2024. http://dx.doi.org/10.3233/faia240384.

Повний текст джерела

Анотація:

This research introduces a novel dataset of user reviews in the mobile gaming domain, comprising over 251,000 reviews spanning 72 game types gathered from the Google Play Store. Leveraging advanced natural language processing (NLP) techniques, the dataset undergoes processing to serve as a valuable resource for developing sentiment analysis models. Additionally, this paper presents a new approach utilizing Transformer models for the sentiment analysis problem on this dataset, explicitly focusing on overall sentiment classification into Positive, Negative, or Neutral categories. In this paper, we incorporate emoji data into sentiment classification. The experimental results demonstrate that the inclusion of emojis leads to improved performance. Specifically, the RoBERTa model achieves the highest performance on the emojis dataset, with an Accuracy of 0.942, Loss of 0.146, and F1 Scores for Positive, Neutral, and Negative sentiments at 0.970, 0.800, and 0.930, respectively.

Стилі APA, Harvard, Vancouver, ISO та ін.

Whitney, Jessica, Marisa Hultgren, Murray Eugene Jennex, Aaron Elkins, and Eric Frost. "Using Knowledge Management and Machine Learning to Identify Victims of Human Sex Trafficking." In Knowledge Management, Innovation, and Entrepreneurship in a Changing World, 360–89. IGI Global, 2020. http://dx.doi.org/10.4018/978-1-7998-2355-1.ch014.

Повний текст джерела

Анотація:

Social media and the interactive Web have enabled human traffickers to lure victims and then sell them faster and in greater safety than ever before. However, these same tools have also enabled investigators in their search for victims and criminals. Authors used system development action research methodology to create and apply a prototype designed to identify victims of human sex trafficking by analyzing online ads. The prototype used a knowledge management approach of generating actionable intelligence by applying a set of strong filters based on an ontology to identify potential victims. Authors used the prototype to analyze a dataset generated from online ads from southern California and used the results of this process to generate a revised prototype that included the use of machine learning and text mining enhancements. An unexpected outcome of the second dataset was the discovery of the use of emojis in an expanded ontology.

Стилі APA, Harvard, Vancouver, ISO та ін.

Geethanjali, R., and Dr A. Valarmathi. "SENTIMENT FUSION: LEVERAGING BIG DATA AND DEEP LEARNING FOR MULTIMODAL SENTIMENT ANALYSIS IN SOCIAL NETWORKS." In Futuristic Trends in Computing Technologies and Data Sciences Volume 3 Book 3, 193–206. Iterative International Publisher, Selfypage Developers Pvt Ltd, 2024. http://dx.doi.org/10.58532/v3bfct3p5ch1.

Повний текст джерела

Анотація:

Social networks have become prolific platforms for individuals to express their thoughts, emotions, and opinions, generating an unprecedented volume of user-generated content. However, traditional sentiment analysis methods mainly focus on textual data, disregarding valuable emotional cues conveyed through other modalities such as images, videos, and emojis. In response, this paper introduces "Sentiment Fusion," a novel approach harnessing the power of big data and deep learning for multimodal sentiment analysis in social networks. By aggregating diverse data sources and integrating deep learning techniques, the Sentiment Fusion model effectively extracts features from text, visuals, and emoticons to capture nuanced emotional nuances. Extensively evaluated on a large-scale dataset from popular social networks, the model outperforms single-modal approaches, providing more accurate sentiment analysis while offering interpretability insights. With scalability demonstrated, Sentiment Fusion paves the way for a deeper understanding of collective emotions on a global scale and finds applications in marketing, public opinion analysis, and social media monitoring. As part of future research, exploring additional performance metrics like precision, recall, F1-score, and cross-modal correlation will enable further refinement of the Sentiment Fusion model, enhancing its applicability and robustness in diverse real-world scenarios.

Стилі APA, Harvard, Vancouver, ISO та ін.

Тези доповідей конференцій з теми "EMOLIS Dataset"

Ghafourian, Sarvenaz, Ramin Sharifi, and Amirali Baniasadi. "Facial Emotion Recognition in Imbalanced Datasets." In 9th International Conference on Artificial Intelligence and Applications (AIAPP 2022). Academy and Industry Research Collaboration Center (AIRCC), 2022. http://dx.doi.org/10.5121/csit.2022.120920.

Повний текст джерела

Анотація:

The wide usage of computer vision has become popular in the recent years. One of the areas of computer vision that has been studied is facial emotion recognition, which plays a crucial role in the interpersonal communication. This paper tackles the problem of intraclass variances in the face images of emotion recognition datasets. We test the system on augmented datasets including CK+, EMOTIC, and KDEF dataset samples. After modifying our dataset, using SMOTETomek approach, we observe improvement over the default method.

Стилі APA, Harvard, Vancouver, ISO та ін.

Kosti, Ronak, Jose M. Alvarez, Adria Recasens, and Agata Lapedriza. "EMOTIC: Emotions in Context Dataset." In 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, 2017. http://dx.doi.org/10.1109/cvprw.2017.285.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Hayati, Shirley Anugrah, Aditi Chaudhary, Naoki Otani, and Alan W. Black. "Dataset Analysis and Augmentation for Emoji-Sensitive Irony Detection." In Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019). Stroudsburg, PA, USA: Association for Computational Linguistics, 2019. http://dx.doi.org/10.18653/v1/d19-5527.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Hakami, Shatha Ali A., Robert Hendley, and Phillip Smith. "ArSarcasMoji Dataset: The Emoji Sentiment Roles in Arabic Ironic Contexts." In Proceedings of ArabicNLP 2023. Stroudsburg, PA, USA: Association for Computational Linguistics, 2023. http://dx.doi.org/10.18653/v1/2023.arabicnlp-1.18.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Zhang, Tianlin, Kailai Yang, Shaoxiong Ji, Boyang Liu, Qianqian Xie, and Sophia Ananiadou. "SuicidEmoji: Derived Emoji Dataset and Tasks for Suicide-Related Social Content." In SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, NY, USA: ACM, 2024. http://dx.doi.org/10.1145/3626772.3657852.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Cui, Chenye, Yi Ren, Jinglin Liu, Feiyang Chen, Rongjie Huang, Ming Lei, and Zhou Zhao. "EMOVIE: A Mandarin Emotion Speech Dataset with a Simple Emotional Text-to-Speech Model." In Interspeech 2021. ISCA: ISCA, 2021. http://dx.doi.org/10.21437/interspeech.2021-1148.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Jandre, Frederico, Gabriel Motta Ribeiro, and João Vitor Silva. "Could large language models estimate valence of words? A small ablation study." In Congresso Brasileiro de Inteligência Computacional. SBIC, 2023. http://dx.doi.org/10.21528/cbic2023-148.

Повний текст джерела

Анотація:

Large language models (LLMs) saw substantial development in recent years. Although trained with broad-range corpora, LLMs have been shown to display capabilities such as quantitative sentiment analysis without the need for further fine tuning. In this study, we performed a small ablation study to evaluate the performance of 3 off-the-shelf LLMs in the task of assigning ratings of hedonic valence to words: GPT-3.5 in chat mode, and GPT-3 and Bloom in completion mode. The models were operated via their public APIs, using prompts engineered to request emojis and ratings of valence in a 9-point scale to represent each of 140 words drawn from a large dataset rated by humans. Prompts were designed to demand the ratings from an adult, with modifiers average or overly positive employed to assess their effects on the results. All linear regressions between the LLM outputs and the human ratings had p-value. The 95% confidence intervals of the slopes include 1.0 for “adult” and “average adult”, except for the model Bloom. These simulacra responded, albeit with limitations, tovalenceofwords andtomodifiersintheprompt.

Стилі APA, Harvard, Vancouver, ISO та ін.

Kirk, Hannah, Bertie Vidgen, Paul Rottger, Tristan Thrush, and Scott Hale. "Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-Based Hate." In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, PA, USA: Association for Computational Linguistics, 2022. http://dx.doi.org/10.18653/v1/2022.naacl-main.97.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Keinan, Ron, Dan Bouhnik, and Efraim A Margalit. "Emotional Analysis in Hebrew Texts: Enhancing Machine Learning with Psychological Feature Lexicons [Abstract]." In InSITE 2024: Informing Science + IT Education Conferences. Informing Science Institute, 2024. http://dx.doi.org/10.28945/5279.

Повний текст джерела

Анотація:

Aim/Purpose. This paper addresses the challenge of emotional analysis in Hebrew texts, specifically focusing on enhancing machine learning techniques with psychological feature lexicons to improve classification accuracy in identifying depression. Background. Emotional analysis in Hebrew texts presents unique challenges due to the language's intricate morphology and rich derivation system. This paper seeks to leverage advanced machine learning methods augmented with carefully crafted psychological feature lexicons to address these challenges and improve the identification of depression from online discourse. Methodology. The study involves scraping and analyzing a dataset consisting of over 350K posts from 25K users on the "Camoni" health-related social network spanning 2010-2021. Various machine learning models, including SVM, Random Forest, Logistic Regression, and Multi-Layer Perceptron, were employed alongside ensemble methods such as Bagging, Boosting, and Stacking. Features were selected using TF-IDF, incorporating both word and character n-grams (Aisopos et al., 2016; HaCohen-Kerner et al., 2018). Pre-processing steps, including punctuation removal, stop word elimination, and lemmatization, were applied, to handle the challenges in Hebrew as a reach morphological language (Amram et al., 2018; Tsarfaty et al., 2019). Then hyperparameter tuning was conducted to optimize model performance across different languages. Following this, the models were enriched with features extracted from sentiment lexicons conducted by professional psychologists. (Shapira et al., 2021). Contribution. This paper contributes to the field by demonstrating the efficacy of integrating psychological feature lexicons into machine-learning models for emotional analysis in Hebrew texts. Addressing the unique linguistic challenges, it advances the understanding of depression detection in online communities and informs the development of more effective preventive measures and treatments. Findings. Through experimentation, it was discovered that enriching the models with features from sentiment lexicons significantly improved classification accuracy. Among the sentiment lexicons tested, six were identified as particularly enchanting: Negative emojis, positive emojis, neutral emojis, Hostile words, Anxiety words, and No-Trust words. The coverage and the quality of a feature lexicon are and may contribute to the success of various tasks like opinion mining and sentiment analysis (Feldman, 2013; Liu, 2012; Yang et al., 2020). Recommendations for Practitioners. Practitioners in mental health and social work should prioritize enriching machine learning models with sentiment lexicons to enhance the accuracy and effectiveness of depression detection in online discourse. By incorporating lexicons capturing emotional nuances, practitioners can improve the sensitivity of their screening processes. Recommendations for Researchers. Future research endeavors should focus on further refining machine learning models by enriching them with sentiment lexicons. Additionally, exploring the integration of sentiment lexicons into deep learning models could provide further insights into the classification of emotional content in textual data. Impact on Society. The findings have significant implications for the development of more accurate and efficient methods for detecting depression in online Hebrew discourse. By leveraging advanced machine learning techniques augmented with psychological feature lexicons, this research contributes to enhancing mental health interventions and promoting well-being in online communities. Future Research. Future research should not only continue exploring the integration of sentiment lexicons into machine learning models but also extend this investigation to deep learning architectures. Investigating the effectiveness of sentiment lexicons in enhancing the performance of deep learning models could advance our understanding of emotional analysis in textual data and improve depression detection algorithms.

Стилі APA, Harvard, Vancouver, ISO та ін.

Ми пропонуємо знижки на всі преміум-плани для авторів, чиї праці увійшли до тематичних добірок літератури. Зв'яжіться з нами, щоб отримати унікальний промокод!