Dissertations / Theses on the topic 'News classification'
To see the other types of publications on this topic, follow the link: News classification.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'News classification.'
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 dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Kroha, Petr, and Ricardo Baeza-Yates. "Classification of Stock Exchange News." Universitätsbibliothek Chemnitz, 2004. http://nbn-resolving.de/urn:nbn:de:swb:ch1-200401576.
Full textAbstract:
In this report we investigate how much similarity good news and bad news may have in context of long-terms market trends. We discuss the relation between text mining, classification, and information retrieval. We present examples that use identical set of words but have a quite different meaning, we present examples that can be interpreted in both positive or negative sense so that the decision is difficult as before reading them. Our examples prove that methods of information retrieval are not strong enough to solve problems as specified above. For searching of common properties in groups of news we had used classifiers (e.g. naive Bayes classifier) after we found that the use of diagnostic methods did not deliver reasonable results. For our experiments we have used historical data concerning the German market index DAX 30In diesem Bericht untersuchen wir, wieviel Ähnlichkeit gute und schlechte Nachrichten im Kontext von Langzeitmarkttrends besitzen. Wir diskutieren die Verbindungen zwischen Text Mining, Klassifikation und Information Retrieval. Wir präsentieren Beispiele, die identische Wortmengen verwenden, aber trotzdem recht unterschiedliche Bedeutungen besitzen; Beispiele, die sowohl positiv als auch negativ interpretiert werden können. Sie zeigen Probleme auf, die mit Methoden des Information Retrieval nicht gelöst werden können. Um nach Gemeinsamkeiten in Nachrichtengruppen zu suchen, verwendeten wir Klassifikatoren (z.B. Naive Bayes), nachdem wir herausgefunden hatten, dass der Einsatz von diagnostizierenden Methoden keine vernünftigen Resultate erzielte. Für unsere Experimente nutzten wir historische Daten des Deutschen Aktienindex DAX 30
2
Sandsmark, Håkon. "Spoken Document Classification of Broadcast News." Thesis, Norges teknisk-naturvitenskapelige universitet, Institutt for elektronikk og telekommunikasjon, 2012. http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-19226.
Full textAbstract:
Two systems for spoken document classification are implemented by combining an automatic speech recognizer with the two classification algorithms naive Bayes and logistic regression. The focus is on how to handle the inherent uncertainty in the output of the speech recognizer. Feature extraction is performed by computing expected word counts from speech recognition lattices, and subsequently removing words that are found to carry little or noisy information about the topic label, as determined by the information gain metric. The systems are evaluated by performing cross-validation on broadcast news stories, and the classification accuracy is measured with different configurations and on recognition output with different word error rates. The results show that a relatively high classification accuracy can be obtained with word error rates around 50%, and that the benefit of extracting features from lattices instead of 1-best transcripts increases with increasing word error rates.
3
Blein, Florent. "Automatic Document Classification Applied to Swedish News." Thesis, Linköping University, Department of Computer and Information Science, 2005. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-3065.
Full textAbstract:
The first part of this paper presents briefly the ELIN[1] system, an electronic newspaper project. ELIN is a framework that stores news and displays them to the end-user. Such news are formatted using the xml[2] format. The project partner Corren[3] provided ELIN with xml articles, however the format used was not the same. My first task has been to develop a software that converts the news from one xml format (Corren) to another (ELIN).
The second and main part addresses the problem of automatic document classification and tries to find a solution for a specific issue. The goal is to automatically classify news articles from a Swedish newspaper company (Corren) into the IPTC[4] news categories.
This work has been carried out by implementing several classification algorithms, testing them and comparing their accuracy with existing software. The training and test documents were 3 weeks of the Corren newspaper that had to be classified into 2 categories.
The last tests were run with only one algorithm (Naïve Bayes) over a larger amount of data (7, then 10 weeks) and categories (12) to simulate a more real environment.
The results show that the Naïve Bayes algorithm, although the oldest, was the most accurate in this particular case. An issue raised by the results is that feature selection improves speed but can seldom reduce accuracy by removing too many features.
4
Kolluru, BalaKrishna. "Broadcast news processing: Structural Classification, Summarisation and Evaluation." Thesis, University of Sheffield, 2006. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.485892.
Full textAbstract:
This thesis describes the automation and evaluation of structural classification and summarisation of audio documents, specifically broadcast news programmes. News broadcasts are typically 30-minute episodes consisting of several stories describing various events, incidents and current affairs. Some of these news stories are annotated to train the statistical models. Structural classification techniques use speaker-role (eg. anchor, reporter etc) information to categorise these stories into different broad classes such as reader and interview. A few carefully drafted set of rules assign a specific speaker-role to each utterance, which are subsequently used to classify the news stories. It is argued in this thesis that selecting the most relevant subsentence linguistic components is ari efficient information gathering mechanism for summarisation. Short to intermediate sized (15 to 50 word) summaries are automatically generated by employing an iterative decremental refining process that first decomposes a story into sentences and then further divides them into chunks or phrases. The most relevant parts are retained at each iteration until the desired number of words is reached. These chunks are then joined using a set of junction words which are decided by a combination of language model and probabilistic parser scores to generate a fluent summary. The performance of this approach is measured using a novel bipartite evaluation mechanism. It is shown that the summaries need to be measured for informativeness and therefore an approach based on a comprehension test is employed to calculate such scores. The evaluation mechanism uses afiuency scale which is based on comprehensibility and coherence to quantify the fluency of summaries. In experiments, human-authored summaries were analysed to quantify the subjectivity using the comprehension test. Experimental results indicate that the iterative refining approach is a lot more informative than a baseline constructed from first sentence or the 50 words of a news story. The results indicate that the use ofjunction words improved fluency in the summaries.
5
Rozman, Darija. "UDC in 2008 - Brief news from Slovenia." UDC Consortium, 2008. http://hdl.handle.net/10150/106214.
Full textAbstract:
The Slovenian translation of the UDC version of MRF 2001 - in the online edition available at http://www.nuk.uni-lj.si/udk/ - was presented at the UDC Seminar in The Hague, in June 2007. In the autumn of 2008 it was updated according to the UDC MRF 2006, including changes approved from 2002 to 2006.
6
Kurasinski, Lukas. "Machine Learning explainability in text classification for Fake News detection." Thesis, Malmö universitet, Fakulteten för teknik och samhälle (TS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-20058.
Full textAbstract:
Fake news detection gained an interest in recent years. This made researchers try to findmodels that can classify text in the direction of fake news detection. While new modelsare developed, researchers mostly focus on the accuracy of a model. There is little researchdone in the subject of explainability of Neural Network (NN) models constructed for textclassification and fake news detection. When trying to add a level of explainability to aNeural Network model, allot of different aspects have to be taken under consideration.Text length, pre-processing, and complexity play an important role in achieving successfully classification. Model’s architecture has to be taken under consideration as well. Allthese aspects are analyzed in this thesis. In this work, an analysis of attention weightsis performed to give an insight into NN reasoning about texts. Visualizations are usedto show how 2 models, Bidirectional Long-Short term memory Convolution Neural Network (BIDir-LSTM-CNN), and Bidirectional Encoder Representations from Transformers(BERT), distribute their attentions while training and classifying texts. In addition, statistical data is gathered to deepen the analysis. After the analysis, it is concluded thatexplainability can positively influence the decisions made while constructing a NN modelfor text classification and fake news detection. Although explainability is useful, it is nota definitive answer to the problem. Architects should test, and experiment with differentsolutions, to be successful in effective model construction.
7
Svärd, Mikael, and Philip Rumman. "COMBATING DISINFORMATION : Detecting fake news with linguistic models and classification algorithms." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-209755.
Full textAbstract:
The purpose of this study is to examine the possibility of accurately distinguishing fabricated news from authentic news stories using Naive Bayes classification algorithms. This involves a comparative study of two different machine learning classification algorithms. The work also contains an overview of how linguistic text analytics can be utilized in detection purposes and an attempt to extract interesting information was made using Word Frequencies. A discussion of how different actors and parties in businesses and governments are affected by and how they handle deception caused by fake news articles was also made. This study further tries to ascertain what collective steps could be made towards introducing a functioning solution to combat fake news. The result swere inconclusive and the simple Naive Bayes algorithms used did not yieldfully satisfactory results. Word frequencies alone did not give enough information for detection. They were however found to be potentially useful as part of a larger set of algorithms and strategies as part of a solution to handling of misinformation.Syftet med denna studie är att undersöka möjligheten att på ett pålitligt sättskilja mellan fabricerade och autentiska nyheter med hjälp av Naive bayesalgoritmer,detta involverar en komparativ studie mellan två olika typer avalgoritmer. Arbetet innehåller även en översikt över hur lingvistisk textanalyskan användas för detektion och ett försök gjordes att extrahera information medhjälp av ordfrekvenser. Det förs även en diskussion kring hur de olika aktörernaoch parterna inom näringsliv och regeringar påverkas av och hur de hanterarbedrägeri kopplat till falska nyheter. Studien försöker vidare undersöka vilkasteg som kan tas mot en fungerande lösning för att motarbeta falska nyheter. Algoritmernagav i slutändan otillfredställande resultat och ordfrekvenserna kundeinte ensamma ge nog med information. De tycktes dock potentiellt användbarasom en del i ett större maskineri av algoritmer och strategier ämnade att hanteradesinformation.
8
Gravenhorst, Claus. "News media processing and interactive presentation." Sächsische Landesbibliothek - Staats- und Universitätsbibliothek Dresden, 2017. https://slub.qucosa.de/id/qucosa%3A16574.
Full text
9
Arevian, Garen Zohrab. "Recurrent neural networks for text classification of news articles from the Reuters Corpus." Thesis, University of Sunderland, 2007. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.439972.
Full text
10
Lagerkrants, Eleonor, and Jesper Holmström. "Using machine learning to classify news articles." Thesis, Linnéuniversitetet, Institutionen för datavetenskap (DV), 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-59449.
Full textAbstract:
In today’s society a large portion of the worlds population get their news on electronicdevices. This opens up the possibility to enhance their reading experience bypersonalizing news for the readers based on their previous preferences. We have conductedan experiment to find out how accurately a Naïve Bayes classifier can selectarticles that a user might find interesting. Our experiments was done on two userswho read and classified 200 articles as interesting or not interesting. Those articleswere divided into four datasets with the sizes 50, 100, 150 and 200. We used a NaïveBayes classifier with 16 different settings configurations to classify the articles intotwo categories. From these experiments we could find several settings configurationsthat showed good results. One settings configuration was chosen as a good generalsetting for this kind of problem. We found that for datasets with a size larger than 50there were no significant increase in classification confidence.
11
Li, Chaoyang, and Ke Liu. "Smart Search Engine : A Design and Test of Intelligent Search of News with Classification." Thesis, Högskolan Dalarna, Institutionen för information och teknik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:du-37601.
Full textAbstract:
Background Google, Bing, and Baidu are the most commonly used search engines in the world. They also have some problems. For example, when searching for Jaguar, most of the search results are cars, not animals. This is the problem of polysemy. Search engines always provide the most popular but not the most correct results. Aim We want to design and implement a search function and explore whether the method of classified news can improve the precision of users searching for news. Method In this research, we collect data by using a web crawler. We use a web crawler to crawl the data of news in BBC news. Then we use NLTK, inverted index to do data pre-processing, and use BM25 to do data processing. Results Compare to the normal search function, our function has a lower recall rate and a higher precision. Conclusions This search function can improve the precision when people search for news. Implications This search function can be used not only to search news but to search everything. It has a great future in search engines. It can be combined with machine learning to analyze users' search habits to search and classify more accurately.
12
Kan'an, Tarek Ghaze. "Arabic News Text Classification and Summarization: A Case of the Electronic Library Institute SeerQ (ELISQ)." Diss., Virginia Tech, 2015. http://hdl.handle.net/10919/74272.
Full textAbstract:
Arabic news articles in heterogeneous electronic collections are difficult for users to work with. Two problems are: that they are not categorized in a way that would aid browsing, and that there are no summaries or detailed metadata records that could be easier to work with than full articles. To address the first problem, schema mapping techniques were adapted to construct a simple taxonomy for Arabic news stories that is compatible with the subject codes of the International Press Telecommunications Council. So that each article would be labeled with the proper taxonomy category, automatic classification methods were researched, to identify the most appropriate. Experiments showed that the best features to use in classification resulted from a new tailored stemming approach (i.e., a new Arabic light stemmer called P-Stemmer). When coupled with binary classification using SVM, the newly developed approach proved to be superior to state-of-the-art techniques. To address the second problem, i.e., summarization, preliminary work was done with English corpora. This was in the context of a new Problem Based Learning (PBL) course wherein students produced template summaries of big text collections. The techniques used in the course were extended to work with Arabic news. Due to the lack of high quality tools for Named Entity Recognition (NER) and topic identification for Arabic, two new tools were constructed: RenA for Arabic NER, and ALDA for Arabic topic extraction tool (using the Latent Dirichlet Algorithm). Controlled experiments with each of RenA and ALDA, involving Arabic speakers and a randomly selected corpus of 1000 Qatari news articles, showed the tools produced very good results (i.e., names, organizations, locations, and topics). Then the categorization, NER, topic identification, and additional information extraction techniques were combined to produce approximately 120,000 summaries for Qatari news articles, which are searchable, along with the articles, using LucidWorks Fusion, which builds upon Solr software. Evaluation of the summaries showed high ratings based on the 1000-article test corpus. Contributions of this research with Arabic news articles thus include a new: test corpus, taxonomy, light stemmer, classification approach, NER tool, topic identification tool, and template-based summarizer – all shown through experimentation to be highly effective.Ph. D.
13
Borggren, Lukas. "Automatic Categorization of News Articles With Contextualized Language Models." Thesis, Linköpings universitet, Artificiell intelligens och integrerade datorsystem, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-177004.
Full textAbstract:
This thesis investigates how pre-trained contextualized language models can be adapted for multi-label text classification of Swedish news articles. Various classifiers are built on pre-trained BERT and ELECTRA models, exploring global and local classifier approaches. Furthermore, the effects of domain specialization, using additional metadata features and model compression are investigated. Several hundred thousand news articles are gathered to create unlabeled and labeled datasets for pre-training and fine-tuning, respectively. The findings show that a local classifier approach is superior to a global classifier approach and that BERT outperforms ELECTRA significantly. Notably, a baseline classifier built on SVMs yields competitive performance. The effect of further in-domain pre-training varies; ELECTRA’s performance improves while BERT’s is largely unaffected. It is found that utilizing metadata features in combination with text representations improves performance. Both BERT and ELECTRA exhibit robustness to quantization and pruning, allowing model sizes to be cut in half without any performance loss.
14
Rekathati, Faton. "Curating news sections in a historical Swedish news corpus." Thesis, Linköpings universitet, Statistik och maskininlärning, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-166313.
Full textAbstract:
The National Library of Sweden uses optical character recognition software to digitize their collections of historical newspapers. The purpose of such software is first to automatically segment text and images from scanned newspaper pages, and second to read the contents of the identified text regions. While the raw text is often digitized successfully, important contextual information regarding whether the text constitutes for example a header, a section title or the body text of an article is not captured. These characteristics are easy for a human to distinguish, yet they remain difficult for a machine to recognize. The main purpose of this thesis is to investigate how well section titles in the newspaper Svenska Dagbladet can be classified by using so called image embeddings as features. A secondary aim is to examine whether section titles become harder to classify in older newspaper data. Lastly, we explore if manual annotation work can be reduced using the predictions of a semi-supervised classifier to help in the labeling process. Results indicate the use of image embeddings help quite substantially in classifying section titles. Datasets from three different time periods: 1990-1997, 2004-2013, and 2017 and onwards were sampled and annotated. The best performing model (Xgboost) achieved macro F1 scores of 0.886, 0.936 and 0.980 for the respective time periods. The results also showed classification became more difficult on older newspapers. Furthermore, a semi-supervised classifier managed an average precision of 83% with only single section title examples, showing promise as way to speed up manual annotation of data.
15
Simmler, Urs. "Simulation-News in Creo 1.0." Universitätsbibliothek Chemnitz, 2011. http://nbn-resolving.de/urn:nbn:de:bsz:ch1-qucosa-68394.
Full text
16
Luo, Ying. "A Credibility-based Classification of Journalistic Blogs:A Literature Study on Credibility Indicators and Examination of Illustrative Cases." Ohio University / OhioLINK, 2009. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1237233585.
Full text
17
Rohleder, Rebekka. "Im/Possible Prisons: News from the Future of Work." Universität Leipzig, 2021. https://ul.qucosa.de/id/qucosa%3A73701.
Full text
18
Deaville, James. "Selling War: Television News Music and the Shaping of American Public Opinion." Bärenreiter Verlag, 2012. https://slub.qucosa.de/id/qucosa%3A72045.
Full text
19
Wan, Zhibin, and Huatai Xu. "Performance comparison of different machine learningmodels in detecting fake news." Thesis, Högskolan Dalarna, Institutionen för information och teknik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:du-37576.
Full textAbstract:
The phenomenon of fake news has a significant impact on our social life, especially in the political world. Fake news detection is an emerging area of research. The sharing of infor-mation on the Web, primarily through Web-based online media, is increasing. The ability to identify, evaluate, and process this information is of great importance. Deliberately created disinformation is being generated on the Internet, either intentionally or unintentionally. This is affecting a more significant segment of society that is being blinded by technology. This paper illustrates models and methods for detecting fake news from news articles with the help of machine learning and natural language processing. We study and compare three different feature extraction techniques and seven different machine classification techniques. Different feature engineering methods such as TF, TF-IDF, and Word2Vec are used to gener-ate feature vectors in this proposed work. Even different machine learning classification al-gorithms were trained to classify news as false or true. The best algorithm was selected to build a model to classify news as false or true, considering accuracy, F1 score, etc., for com-parison. We perform two different sets of experiments and finally obtain the combination of fake news detection models that perform best in different situations.
20
Bürger, Thomas. "Welcome to the SLUB - IFLA 2017 News Media Satellite Conferences." Sächsische Landesbibliothek - Staats- und Universitätsbibliothek Dresden, 2017. https://slub.qucosa.de/id/qucosa%3A16342.
Full text
21
Dogan, Ebru. "Content-based Audio Management And Retrieval System For News Broadcasts." Master's thesis, METU, 2009. http://etd.lib.metu.edu.tr/upload/12611018/index.pdf.
Full textAbstract:
The audio signals can provide rich semantic cues for analyzing multimedia content, so audio information has been recently used for content-based multimedia indexing and retrieval. Due to growing amount of audio data, demand for efficient retrieval techniques is increasing. In this thesis work, we propose a complete, scalable and extensible audio based content management and retrieval system for news broadcasts. The proposed system considers classification, segmentation, analysis and retrieval of an audio stream. In the sound classification and segmentation stage, a sound stream is segmented by classifying each sub segment into silence, pure speech, music, environmental sound, speech over music, and speech over environmental sound in multiple steps. Support Vector Machines and Hidden Markov Models are employed for classification and these models are trained by using different sets of MPEG-7 features. In the analysis and retrieval stage, two alternatives exist for users to query audio data. The first of these isolates user from main acoustic classes by providing semantic domain based fuzzy classes. The latter offers users to query audio by giving an audio sample in order to find out the similar segments or by requesting expressive summary of the content directly. Additionally, a series of tests was conducted on audio tracks of TRECVID news broadcasts to evaluate the performance of the proposed solution.
22
Boss, Katherine, and Meredith Broussard. "Describing dynamic data journalism: developing a survey of news applications." Sächsische Landesbibliothek - Staats- und Universitätsbibliothek Dresden, 2017. https://slub.qucosa.de/id/qucosa%3A16654.
Full textAbstract:
Preserving dynamic, born-digital data journalism requires more than web scraping, as news stories today are built from much more than just text and images. Data journalism projects like news applications, or “news apps,” are composed of a database, the data in the database, the graphical interface that appears in the browser, accompanying text, and often images, videos, audio, and other multimedia components. Existing Internet archiving methods are not sufficient to save these data journalism projects for the future.
This paper summarizes the context and history of news apps archiving, and describes the development of a survey of news applications. This survey will be used to create a working list of news organizations that are producing data journalism in the United States and a better sense of how and where these projects are currently being stored. The results of the survey will inform recommendations and processes for archiving dynamic data journalism.
23
Vollbrecht, Ralf, and Verena Odrig. "Medienwelten - Zeitschrift für Medienpädagogik." Technische Universität Dresden, 2020. https://tud.qucosa.de/id/qucosa%3A70797.
Full textAbstract:
Unter den Anglizismen des Jahres 2016 schaffte es „Fake News“ noch vor den zweit- und drittplatzierten Wörtern „Dark Net“ und „Hate Speech“ zum Publikumsliebling und wurde auch von der Jury der „Aktion Anglizismen des Jahres“ 2016 auf den ersten Platz gewählt (http://www.anglizismusdesjahres.de). In seiner Laudatio weist Anatol Stefanowitsch darauf hin, dass das Wort Fake News schon im 19. Jahrhundert in ähnlicher Bedeutung wie heute verwendet wurde im Sinne einer frei erfundenen Nachricht, die politische Gegner ungünstig darstellt und von den Lesern – ist hier noch nicht die Rede – positiv aufgenommen wird, weil sie deren Weltbild bestätigt. Die früheste Verwendung datiert er auf 1894 in der Zeitschrift American Historical Register [... aus dem Editorial]
24
Klinger, Jessica, and Antje Müller. "Eignen sich Kindernachrichten für Kinder?" Saechsische Landesbibliothek- Staats- und Universitaetsbibliothek Dresden, 2016. http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-196024.
Full textAbstract:
Nachrichtensendungen für Kinder sind im Rahmen der politischen Sozialisation bedeutsam und sehen sich mit verschiedenen Anforderungen konfrontiert. In der vorliegenden Studie unterziehen die Autorinnen die deutsche Kindernachrichtensendung Logo! und die britische Kindernachrichtensendung Newsround einem inhaltsanalytischen Qualitätsvergleich. Dazu leiten sie Qualitätskriterien aus normativen, inhaltlichen sowie formalen Beurteilungskriterien aus Rezipienten-, Produzenten- sowie aus wissenschaftlicher Sicht ab, die sie für Aussagen über die Aufbereitung und Eignung dieser Kindernachrichtenprogramme heranziehen. Die Ergebnisse dieser tiefgründigen Analyse bieten detaillierten Aufschluss über Gemeinsamkeiten und Unterschiede der untersuchten Sendungen und ermöglichen so eine differenzierte Betrachtung der Frage danach, was die Qualität von Kindernachrichtensendungen – auch unter interkulturellen Gesichtspunkten – ausmachtTV News programs for children, within the context of political socialization, are not only hugely important but are also being faced with constant challenges. The following study focuses on Germany’s Logo! and Britain’s Newsround, two of the larger scale television news programs on offer for children. The study offers ananalytical, quality comparison of the two shows. It looks both at the quality criteria of normative, context-related and formal assessment criteria, whilst exploring the perspective of the recipient, the producer and more scientific approaches. The study concludes with an analysis of the format preparation of the two shows and analyses their respective suitability for children. The study offers a profound insight into the similarities and differences between these two broadcasts and considers how we can attempt to measure the quality of children’s news programs
25
Hoffmann, Martin. "Informationskompetenz: Auszubildende werden „Fit for News“ - Pilotprojekt entwickelt Unterrichtsmodule für Sachsens Berufsschüler." Landkreis Nordsachsen, 2019. https://slub.qucosa.de/id/qucosa%3A34422.
Full textAbstract:
Berufsschüler standen bisher nicht im Fokus von Medienkompetenz-Schulungen. Es gibt auch keine Unterrichtseinheiten, die auf diese Schulungsbedarfe zugeschnitten sind. Während Digitalisierung und Medienwandel von den Bildungssystemen anderer Staaten aufgenommen wurden, attestieren Studien deutschen Schülern ein „eher mäßiges
Kompetenzniveau“ und „großen Aufholbedarf“ (Härtel, 2018). Der überwiegende Teil der Schulabsolventen ist einer Untersuchung der TU Dresden zufolge noch nicht einmal in der Lage, den Wahrheitsgehalt von Sachaussagen zu erkennen. (Hagen/Renatus/Obermüller, 2017). Dabei suchen knapp 70 Prozent der jungen Erwachsenen hauptsächlich im Netz nach News (Hölig/Hasebrink, 2019). Insbesondere die Ausbildenden benötigen fundiertes Wissen und Techniken, um mit Informationen vor allem der internetbasierten Medien sicherer umzugehen.
26
Simmler, Urs. "Simulation-News in Creo 1.0 & Creo 2.0." Universitätsbibliothek Chemnitz, 2012. http://nbn-resolving.de/urn:nbn:de:bsz:ch1-qucosa-87115.
Full textAbstract:
Simulation-News in Creo 1.0 & Creo 2.0
- Mechanica (neu: Simulate)
Druckbehälter: Schraubenvorspannung / Betriebslast
- Live-Präsentation in Creo 2.0
Berechnung eine Druckbehälters unter Berücksichtigung von:
Schraubenvorspannung, Betriebslast, zeitabhängiger Lastaufbringung
27
Chuck, Lisa. "A PREDICTIVE MODEL FOR BENCHMARKING ACADEMIC PROGRAMS (PBAP)USING U.S. NEWS RANKING DATA FOR ENGINEERING COLLEGES OFFERING GRADU." Doctoral diss., University of Central Florida, 2005. http://digital.library.ucf.edu/cdm/ref/collection/ETD/id/2397.
Full textAbstract:
Improving national ranking is an increasingly important issue for university administrators. While research has been conducted on performance measures in higher education, research designs have lacked a predictive quality. Studies on the U.S. News college rankings have provided insight into the methodology; however, none of them have provided a model to predict what change in variable values would likely cause an institution to improve its standing in the rankings. The purpose of this study was to develop a predictive model for benchmarking academic programs (pBAP) for engineering colleges. The 2005 U.S. News ranking data for graduate engineering programs were used to create a four-tier predictive model (pBAP). The pBAP model correctly classified 81.9% of the cases in their respective tier. To test the predictive accuracy of the pBAP model, the 2005 U.S .News data were entered into the pBAP variate developed using the 2004 U.S. News data. The model predicted that 88.9% of the institutions would remain in the same ranking tier in the 2005 U.S. News rankings (compared with 87.7% in the actual data), and 11.1% of the institutions would demonstrate tier movement (compared with an actual 12.3% movement in the actual data). The likelihood of improving an institution's standing in the rankings was greater when increasing the values of 3 of the 11 variables in the U.S. News model: peer assessment score, recruiter assessment score, and research expenditures.Ed.D.
Department of Educational Research, Technology and Leadership
Education
Educational Leadership
28
Miranda, Ackerman Eduardo Jacobo. "Extracting Causal Relations between News Topics from Distributed Sources." Doctoral thesis, Saechsische Landesbibliothek- Staats- und Universitaetsbibliothek Dresden, 2013. http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-130066.
Full textAbstract:
The overwhelming amount of online news presents a challenge called news information overload. To mitigate this challenge we propose a system to generate a causal network of news topics. To extract this information from distributed news sources, a system called Forest was developed. Forest retrieves documents that potentially contain causal information regarding a news topic. The documents are processed at a sentence level to extract causal relations and news topic references, these are the phases used to refer to a news topic. Forest uses a machine learning approach to classify causal sentences, and then renders the potential cause and effect of the sentences. The potential cause and effect are then classified as news topic references, these are the phrases used to refer to a news topics, such as “The World Cup” or “The Financial Meltdown”. Both classifiers use an algorithm developed within our working group, the algorithm performs better than several well known classification algorithms for the aforementioned tasks.
In our evaluations we found that participants consider causal information useful to understand the news, and that while we can not extract causal information for all news topics, it is highly likely that we can extract causal relation for the most popular news topics. To evaluate the accuracy of the extractions made by Forest, we completed a user survey. We found that by providing the top ranked results, we obtained a high accuracy in extracting causal relations between news topics.
29
Dallmann, Christine, and Ralf Vollbrecht. "Editorial: Kindernachrichten." Saechsische Landesbibliothek- Staats- und Universitaetsbibliothek Dresden, 2016. http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-196014.
Full textAbstract:
Kinder sind neugierig auf die Welt. Und sie erfahren über diese Welt auch in den Medien, jedoch gibt es nur wenige Medienangebote mit kindgerechten Nachrichten. Dennoch bekommen Kinder Vieles mit: aus Gesprächen von Erwachsenen oder auch aus Nachrichtensendungen und Online-Angeboten, die nicht für Kinder gemacht und geeignet sind. So sind auch Berichterstattungen zu Kriegen, Natur- und sogenannten „humanitären“ Katastrophen sowie zu welt- und innenpolitischem Geschehen Bestandteil der alltäglichen Lebenswelt von Kindern. Diese gehen damit ganz unterschiedlich um. Sie reagieren auf Bedrohliches oder Unverständliches verunsichert, geängstigt oder auch interessiert – sie bleiben jedoch mit ihren Fragen und Ängsten oft allein, denn nicht immer stehen Erwachsene zur Verfügung. Vor diesem Hintergrund haben es sich Kindernachrichtensendungen zur Aufgabe gemacht, Nachrichten auf eine an den Bedürfnissen und Horizonten von Kindern orientierte Weise zu vermitteln.
In dieser Ausgabe der Medienwelten analysieren Jessica Klinger und Antje Müller vergleichend die Kindernachrichtensendungen „Newsround“ und „logo!“ und sie stellen heraus, welche Qualitätskriterien mit der Orientierung an dieser Zielgruppe verbunden sein müssen.
30
Riedel, Ursula, Frank Richter, Uwe Huebner, Jan Wunderlich, Holger Trapp, Matthias Clauss, Karsten Baensch, et al. "Mitteilungen des URZ 1/2/1996." Universitätsbibliothek Chemnitz, 1996. http://nbn-resolving.de/urn:nbn:de:bsz:ch1-199600134.
Full text
31
Chuck, Lisa Gay Marie. "A Predictive Model for Benchmarking Academic Programs (pBAP) Using U.S. News Ranking Data for Engineering Colleges Offering Graduate Programs." Doctoral diss., University of Central Florida, 2005. http://digital.library.ucf.edu/cdm/ref/collection/ETD/id/2396.
Full textAbstract:
Improving national ranking is an increasingly important issue for university administrators. While research has been conducted on performance measures in higher education, research designs have lacked a predictive quality. Studies on the U.S. News college rankings have provided insight into the methodology; however, none of them have provided a model to predict what change in variable values would likely cause an institution to improve its standing in the rankings. The purpose of this study was to develop a predictive model for benchmarking academic programs (pBAP) for engineering colleges. The 2005 U.S. News ranking data for graduate engineering programs were used to create a four-tier predictive model (pBAP). The pBAP model correctly classified 81.9% of the cases in their respective tier. To test the predictive accuracy of the pBAP model, the 2005 U.S .News data were entered into the pBAP variate developed using the 2004 U.S. News data. The model predicted that 88.9% of the institutions would remain in the same ranking tier in the 2005 U.S. News rankings (compared with 87.7% in the actual data), and 11.1% of the institutions would demonstrate tier movement (compared with an actual 12.3% movement in the actual data). The likelihood of improving an institution's standing in the rankings was greater when increasing the values of 3 of the 11 variables in the U.S. News model: peer assessment score, recruiter assessment score, and research expenditures.Ed.D.
Department of Educational Research, Technology and Leadership
Education
Educational Leadership
32
Hagen, Lutz M. "Relevance of News in the Digital Age: Journalism between Vanishing Business Models and an Unchained Public." Sächsische Landesbibliothek - Staats- und Universitätsbibliothek Dresden, 2017. https://slub.qucosa.de/id/qucosa%3A16402.
Full text
33
Simmler, Urs. "Mechanism-News in PTC Creo." Universitätsbibliothek Chemnitz, 2014. http://nbn-resolving.de/urn:nbn:de:bsz:ch1-qucosa-141525.
Full textAbstract:
Der Vortrag gibt einen Überblick der Neuerungen im Werkzeug Mechanism der Creo Versionen 1.0 und 2.0.
Zudem werden 10 hilfreiche "Tips und Tricks" vorgestellt, welche den Mechanismuseinsatz vereinfachen.
34
Glaser, Karen. "News from the pragmatics classroom: Contrasting the inductive and the deductive approach in the teaching of pragmatic competence." De Gruyter, 2016. https://ul.qucosa.de/id/qucosa%3A21364.
Full textAbstract:
While the role of pragmatic skills in a foreign or second language has been receiving increased attention both from a research and a language teaching perspective, there is still a lamentable scarcity of systematic empirical studies into the effectiveness of instructional methods in the teaching of pragmatics. Addressing this research gap, this article reports about a quasi-experimental study into possible differences between an explicit-inductive and an explicitdeductive instructional approach in the teaching of pragmatic skills in English as a Foreign Language (EFL), more specifically the teaching of offer refusals to 49 advanced adult EFL learners in Germany. The instruction consisted of three 90-minute lessons, which were spread out over the duration of a 15-week academic semester and designed according to the deductive principle and the inductive principle, respectively. While the deductive group was provided with metapragmatic rules directly at the beginning of the instruction, the inductive group only encountered such rules after engaging in language use and guided discovery. Production data was elicited by means of DCTs and role play in a pretest-posttest format. Effectiveness of instruction was operationalized by means of two indicators: Indicator 1 measured the increased usage of the strategies taught in class, while indicator 2 measured the approximation to a native speaker target. The results indicate that the gains in the inductive group surpassed those in the deductive group, suggesting that when situated within the explicit framework, inductive instruction is more effective in the teaching of pragmatic skills.
35
Lindblom, Rebecca. "News Value Modeling and Prediction using Textual Features and Machine Learning." Thesis, Linköpings universitet, Interaktiva och kognitiva system, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-167062.
Full textAbstract:
News value assessment has been done forever in the news media industry and is today often done in real-time without any documentation. Editors take a lot of different qualitative aspects into consideration when deciding what news stories will make it to the first page. This thesis explores how the complex news value assessment process can be translated into a quantitative model, and also how those news values can be predicted in an effective way using machine learning and NLP. Two models for news value were constructed, for which the correlation between modeled and manual news values was measured, and the results show that the more complex model gives a higher correlation. For prediction, different types of features are extracted, Random Forest and SVM are used, and the predictions are evaluated with accuracy, F1-score, RMSE, and MAE. Random Forest shows the best results for all metrics on all datasets, the best result being on the largest dataset, probably due to the smaller datasets having a less even distribution between classes.
36
Fischer, Günther, Ludwig Wolf, Jens Wagner, Wolfgang Riedel, Steffen Brose, Ursula Riedel, Rolf Köbe, and Frank Richter. "Mitteilungen des URZ 4/1995." Universitätsbibliothek Chemnitz, 1995. http://nbn-resolving.de/urn:nbn:de:bsz:ch1-199500125.
Full text
37
Svensson, Pontus. "Automated Image Suggestions for News Articles : An Evaluation of Text and Image Representations in an Image Retrieval System." Thesis, Linköpings universitet, Interaktiva och kognitiva system, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-166669.
Full textAbstract:
Multimodal machine learning is a subfield of machine learning that aims to relate data from different modalities, such as texts and images. One of the many applications that could be built upon this technique is an image retrieval system that, given a text query, retrieves suitable images from a database. In this thesis, a retrieval system based on canonical correlation is used to suggest images for news articles. Different dense text representations produced by Word2vec and Doc2vec, and image representations produced by pre-trained convolutional neural networks are explored to find out how they affect the suggestions. Which part of an article is best suited as a query to the system is also studied. Also, experiments are carried out to determine if an article's date of publication can be used to improve the suggestions. The results show that Word2vec outperforms Doc2vec in the task, which indicates that the meaning of article texts are not as important as the individual words they consist of. Furthermore, the queries are improved by rewarding words that are particularly significant.
38
Lin, Song-Hua, and 林頌華. "Automatic Classification of News Titles." Thesis, 1999. http://ndltd.ncl.edu.tw/handle/35886847351662807519.
Full text
39
Wei, Huang Chung, and 黃仲瑋. "Automatic Classification of Medical News." Thesis, 1999. http://ndltd.ncl.edu.tw/handle/98507899902441991263.
Full textAbstract:
碩士國立交通大學
資訊科學系
87
There is hundreds of medical news everyday. Can we find out an efficient method to collect these data? Moreover, the computer can feed news automatically, store it in the server, analyze the context of news, and then find out which assortment the specific news is. In other words, it is not necessary for doctors and nurses to spend time on searching medical news. They only have to run this program, and then the classified medical news will appear in front of them. In this paper, I introduce how improved search of keywords can replace the function of sentence analysis. Furthermore, I discuss the special methods of cutting sentences which can increase the accurateness of analysis. At last I will show you how to record each sentence''s information by multi-words and special comparison rules. All of them are presented by HTML showcase.
40
Lee, Yen-Lung, and 李儼倫. "Dictionary-based news category classification : using sports news as example." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/f6g5au.
Full textAbstract:
碩士淡江大學
資訊工程學系碩士班
104
Rapid and vigorous development of information network technology has resulted in the largest data repository. Collecting relevant information in such a large body of data is rather difficult for any user. This paper is aimed to help users to grasp key information in a short period of time. We observe that term frequency in a article can be used as keyword for that article. Article theme can be easily grasped based on these keywords. Therefore, users can find the information they want through keyword and significantly reduce unnecessary search time. Proper word segmentation enables article theme extraction. And article classification can be achieved by theme differentiation. We use 320 articles in the theme classification experiment. These articles are divided into two categories: training and testing. There are 285 training samples, all belonging to the sports news theme. There are 15 testing samples that are consists of themes picked at random. The result is able to pick out 6 articles which belonging to sport news theme among the 15 testing samples. Among the 20 negative samples, there are 4 false positives, all due to names related to sports events.
41
Shen, Shih-Yun, and 沈時宇. "Automatic Web News Classification and Subscription." Thesis, 2002. http://ndltd.ncl.edu.tw/handle/56278137447557477758.
Full textAbstract:
碩士國立中正大學
資訊工程研究所
90
With the rapid growth of Internet, Web News becomes more and more popular. And many people have changed the habit of reading News, instead of reading News from newspapers or TV channel they read News from WWW now. But most News web sites are short of automated process, they need to invoke human effort to classify or select their News in the news page. Therefore, our system was built to solve these problems, and it can fetch News data, classifies and clusters News content automatically. Our system will reduce the human effort invoked and increase the efficiency of the process from getting the News to showing the result. In our thesis, we utilize the HTML format to make the result of the classification more accurate. We define the similarity between documents, and use the k-means algorithm to make the cluster process more efficient. Our system also provides two kinds of User Interfaces to make users reading News more efficiently and more conveniently.
42
Lin, Ta-Che, and 林大澈. "Automatic Classification System of News Pages." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/02316906563335323642.
Full textAbstract:
碩士淡江大學
資訊工程學系碩士班
98
There are more and more information in the Internet by the vigorous development of the Internet. But this rapid development has brought about a new problem. That is there are such a large number of news and information, and the classifications of all the news sites are not the same. How to quickly organize the data and absorb them is a need to face. In this paper, a classification system is set up through several researches focusing on the news page classification. It can automatically update the news pages and go on automatic classification. This system is based on Naïve Bayes Classifier. When it calculates the probability of news classification, it also calculates the weight of each word at the same time. Thus, it can increase the accuracy of classification and decrease the occurrence of a variety of classifications or not being classified (belong to all categories). This classification system has the basic ability to distinguish information after training module has trained 960 news. Afterwards, by testing 200 news, the system’s average recall rate can be 78%, achieving acceptable results. Experimental results show that this system is able to have good performance of classification in the way that the text in the news are divided into broken words by word thesaurus as a feature information of training module, go on to count the word frequency information, combining concept of the weight with Naïve Bayes Classifier.
43
Hsieh, Wei-Che, and 謝維哲. "A Classification Oriented News Summary Model." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/58132459684812522469.
Full textAbstract:
碩士中原大學
資訊管理研究所
97
The Internet has been applied more and more widely in recent years. Therefore, various information has been digitized to facilitate its spread on the Internet. With the development of digitization, huge amount of information has been created and it’s not as difficult for users to acquire information as before. As a result, it is important for users to exclude unnecessary information to get what they really need. Traditionally, the single-document summarization method has been used to present the single news summary. With the development of the news automatic clustering technology, most news portal sites also classify news, but they do not give different summaries to different news types. As a result, readers may not quickly find the news they care about or they may miss relative news by the search of this kind of news summaries. This research is to come out with a news summary method that combines with the classification-oriented technology. This method creates news summaries by the concept of information retrieval, the calculation of TF*IDF weight of the words, K-means clustering, and document summarization. We then define the top 10% words of the classified news by their weight as relevant words. In addition, since the headlines are usually the key points of the news, and the first sentence of the first paragraph is usually the main point and the last sentence of the last paragraph is usually the conclusion, this research also adjusts the weights of relevant words according to those concepts. The purpose of the research is to provide a method of classification-oriented news summary so that readers can get the main points of the news in a short time and determine whether the news is what they want.
44
Ming, Chien Chun, and 簡俊銘. "Text Classification Using the News Headlines." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/13721581226405198270.
Full textAbstract:
碩士華梵大學
資訊管理學系碩士班
102
With the increasing popularity of Internet, information dependence on the Internet also gives rise. How to use the electronic media to spread information quickly and efficiently obtain useful information on their needs, is an important issue. This study discussed the classification using the news headlines. The automatic document classification (text classification) method was adopted. The word processing and the frequency information of words were used to extract the attributes (features) for the classification of the news articles using the Weka data mining system. We discussed the impacts of the ratio of the files (1:1, 1:5, 1:10) and the numbers of attributes (128, 256, 512, 1024, 2048) for the classification of news. The classifications using the contents and the headlines of the news articles were also compared. The experimental results show that the classification of the news content gets the accuracy of 96.3636%, and slightly higher than the correct rate of 93.6364% for the headlines. The difference is 2.0454%. The results show that the proposed method can be used for the classification of the real-time electronic news using the title field of the news. Keywords: text classification, news headlines, data mining
45
Tien, Kao-Ming, and 田高銘. "Empirical Study of News Sentiment Classification: Evidence from Anue Financial News." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/9zndbp.
Full textAbstract:
碩士國立中山大學
財務管理學系研究所
107
Nowadays, online news has become one of the judgments for investors to make investment decisions. However, a large amount of information generated by financial news websites everyday makes investors unable to use traditional human reading and screening methods to judge and verify the current market sentiment reflected by each news report. In order to help investors understand the current market sentiment quickly, we use the techniques of text mining and text classification to classify new sentiments. This study collects Taiwanese stock market news of Anue Financial News and use different methods of text pre-processing and classifier to achieve the best classification performance. The empirical results show：(1) N-gram feature extraction can improve the accuracy of all classifiers, especially the naive Bayes classifier which can effectively overcome shortcomings of the independence assumptions. (2) TF-IDF feature selection only effective for naive Bayes classifier. Under the circumstances of the number of words decreasing, it can improve the accuracy and reduce the training time. (3) The Chi-square test and mutual information feature selection can improve the accuracy of both fastText and Multi-layer Perceptron. Furthermore, the combination of Chi-square test feature and fastText achieved the best performance in this study.
46
Lu, Wen-Jane, and 呂文蓁. "Finding a Suitable Hierarchical Classification for News." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/11208911446932580156.
Full textAbstract:
碩士國立成功大學
資訊管理研究所
96
Online news has became a trend, manual text classification distributes text documents into one or more pre-defined categories of similar documents. It is essential to develop an automatic classification method to reduce manual work. Currently, the news is a hierarchical structure. We wonder if a classification method applicable to each level. In this paper, we first collected most popular classification methods. Several suitable combinations are selected and applied to different hierarchical level. Unlike other papers, they all apply one method in all level to classify news. We use three most popular text classification algorithms, Support Vector Machine, Naïve Bayes and K-Nearest-Neighbor, to classify Reuter Corpus, Volume 1. We expect to find a better combinatorial classification method to improve classification accuracy and performance.
47
Rodrigues, João Filipe Carriço. "Fake news classification in European Portuguese language." Master's thesis, 2020. http://hdl.handle.net/10071/22194.
Full textAbstract:
All over the world, many initiatives have been taken to fight fake news. Governments (e.g.,
France, Germany, United Kingdom and Spain), on their own way, started to take actions
regarding legal accountability for those who manufacture or propagate fake news. Different media outlets have also taken plenty initiatives to deal with this phenomenon, such as
the increase of the discipline, accuracy and transparency of publications made internally.
Some structural changes have been made in those companies and in other entities in order to evaluate news in general. Many teams were built entirely to fight fake news, the
so-called “fact-checkers”. Those teams have been adopting different types of techniques in
order to do those tasks: from the typical use of journalists, to find out the true behind a
controversial statement, to data-scientists, in order to apply forefront techniques such as
text mining, and machine learning to support journalist’s decisions. Many of those entities,
which aim to maintain or rise their reputation, started to focus on high standards of quality
and reliable information, which led to the creation of official and dedicated departments
of fact-checking. In the first part of this work, we contextualize European Portuguese language regarding fake news detection and classification, against the current state-of-the-art.
Then, we present an end-to-end solution to easily extract and store previously classified European Portuguese news. We used the extracted data to apply some of the most used text
minning and machine learning techniques, presented in the current state-of-the-art, in order to understand and evaluate possible limitations of those techniques, in this specific
context.Um pouco por todo o mundo foram tomadas várias iniciativas para combater fake news. Muitos governos (França, Alemanha, Reino Unido e Espanha, por exemplo), à sua maneira, começaram a tomar medidas relativamente à responsabilidade legal para aqueles que fabricam ou propagam notícias falsas. Foram feitas algumas mudanças estruturais nos meios de comunicação sociais, a fim de avaliar as notícias em geral. Muitas equipas foram construídas inteiramente para combater fake news, mais especificamente, os denominados "fact-checkers". Essas equipas têm vindo a adotar diferentes tipos de técnicas para realizar as suas tarefas: desde o uso dos jornalistas para descobrir a verdade por detrás de uma declaração controversa, até aos cientistas de dados, que através de técnicas mais avançadas como as técnicas de Text Minning e métodos de classificação de Machine Learning, apoiam as decisões dos jornalistas. Muitas das entidades que visam manter ou aumentar a sua reputação, começaram a concentrar-se em elevados padrões de qualidade e informação fiável, o que levou à criação de departamentos oficiais e dedicados de verificação de factos. Na primeira parte deste trabalho, contextualizamos o Português Europeu no âmbito da detecção e classificação de notícias falsas, fazendo um levantamento do seu actual estado da arte. De seguida, apresentamos uma solução end-to-end que permite facilmente extrair e armazenar notícias portuguesas europeias previamente classificadas. Utilizando os dados extraídos aplicámos algumas das técnicas de Text Minning e de Machine Learning mais utilizadas, apresentadas na literatura, a fim de compreender e avaliar as possíveis limitações dessas técnicas, neste contexto em específico
48
Yu, Tung-lin, and 余東霖. "Two-phase Classification Approach for Identifying News Category." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/71868724106650851383.
Full textAbstract:
碩士國立中央大學
資訊管理研究所
98
The news classification problem is concerned with how to assign the correct category for the unclassified news. Although a large number of past studies have studied this problem, a common weakness of these studied is that their classification algorithms were usually designed from technical perspective and they seldom considered how experts really classify the news in a practical classification process. In this research, we first observe how media workers classify news in their daily operations, and we find that their classification process mainly consists of the following operations. (1) If some important keywords or phrases are present in the news, then they directly assign the news to certain categories. (2) Otherwise, they must check in details the whole content of news to determine which category it should belong to. (3) Since a news category may contain several independent but related subcategories, the news is usually classified by assigning it to the most appropriate subcategory, which can in turn determine its category. By imitating the above working process, we proposed a news classification algorithm. In the learning phase, we use associative classification rules to find representative keywords in each category. In addition, we further generate a number of subcategories by clustering news under each category. In the classification phase, we assign unclassified news the most appropriate category by using associative classification rules if rules’ confidence is high enough. Otherwise, we will determine the category by measuring the similarity between unclassified news and subcategories. The experimental comparison shows that our approach has better and more stable classification performance than traditional algorithms.
49
Che-Min, Chen. "A Cross-Trainging Approach for Bilingual Web News Classification." 2006. http://www.cetd.com.tw/ec/thesisdetail.aspx?etdun=U0009-0112200611330653.
Full text
50
Wang, Zhi-Hong, and 王誌鴻. "Developing Ontological Mechanisms for Chinese News Analysis and Classification." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/76675601423260626884.
Full textAbstract:
碩士中原大學
資訊管理研究所
95
The common ways of context analysis have been limited to human understanding of vocabularies, speech judgment and synonym mapping, resulting in a lack of understanding of the deeper implications of the content of the text. Based on an ontology knowledge classification structure, our research aims to analyze news semantics and classify news scenarios. The integration of a scenario analysis mechanism into the knowledge structure would allow for different readings of news under different scenarios, benefiting classification of information. In this research we collected relevant knowledge element properties, attributes and any existing classifying structures first. Following Formal Concept Analysis (FCA), we then integrate the elements and dominant/recessive attributes analyzed by the experts into a concept plan which shows the relationship among all the elements, their properties, and classification structures. To enhance the analysis of news contents from an information level to a semantic level, this research utilizes a two-step process, Resource Description Framework (RDF) and Web Ontology Language (OWL); the former improves the expression of vocabularies and the latter adds descriptive logic to help express knowledge under different scenarios. We used the “IC Components” of the electronics industry as a case study to collect the knowledge the experts have regarding the different scenarios the manufacturers encounter. The knowledge was then used to analyze the Chinese news headlines based on the mechanism of ontology and establish a semantics classification as affected by different scenarios afterwards, which will be used as empirical application.