Filters








740 Hits in 5.9 sec

TV program detection in tweets

Paolo Cremonesi, Roberto Pagano, Stefano Pasquali, Roberto Turrin
2013 Proceedings of the 11th european conference on Interactive TV and video - EuroITV '13  
In this paper, we present a solution to identify whether a tweet posted by a user refers to one among a set of known TV programs.  ...  However, eliciting preferences from a tweet requires to understand if the tweet refers to a specific TV program, a task particularly challenging due to the nature of tweets -e.g., the limited length and  ...  Tweets are mapped onto TV showsassuming that each tweet can be at most mapped onto a TV program -on the basis of the data available from the EPG (Electronic Programming Guide).  ... 
doi:10.1145/2465958.2465960 dblp:conf/euroitv/CremonesiPPT13 fatcat:y4xgda6oynenjahfre2txe4jey

Filtering microblogging messages for social tv

Ovidiu Dan, Junlan Feng, Brian Davison
2011 Proceedings of the 20th international conference companion on World wide web - WWW '11  
From this annotated data set, we train an initial classifier. The features are designed to capture the association between the TV program and the message.  ...  We propose a bootstrapping approach to collecting microblogging messages related to a given TV program.  ...  Current Social TV applications search for these messages by issuing queries to social networks with the full title of the TV program.  ... 
doi:10.1145/1963192.1963288 dblp:conf/www/DanFD11 fatcat:5m36b2owknh7rli4l25mp2uusm

RESLVE

Elizabeth L. Murnane, Bernhard Haslhofer, Carl Lagoze
2013 Proceedings of the 22nd International Conference on World Wide Web - WWW '13 Companion  
In such settings, the lack of linguistic features and sparse lexical context result in a high degree of ambiguity and sharp performance drops of nearly 50% in the accuracy of conventional NED systems.  ...  We address the Named Entity Disambiguation (NED) problem for short, user-generated texts on the social Web.  ...  EXPERIMENTS Data Collection and Preparation We collected tweets posted on Twitter, videos posted on YouTube, and photos posted on Flickr.  ... 
doi:10.1145/2487788.2487823 dblp:conf/www/MurnaneHL13 fatcat:3h4drygadrf5nd4xpknl64voau

RESLVE: Leveraging User Interest to Improve Entity Disambiguation on Short Text [article]

Elizabeth L. Murnane, Bernhard Haslhofer, Carl Lagoze
2013 arXiv   pre-print
In such settings, the lack of linguistic features and sparse lexical context result in a high degree of ambiguity and sharp performance drops of nearly 50% in the accuracy of conventional NED systems.  ...  We address the Named Entity Disambiguation (NED) problem for short, user-generated texts on the social Web.  ...  EXPERIMENTS Data Collection and Preparation We collected tweets posted on Twitter, videos posted on YouTube, and photos posted on Flickr.  ... 
arXiv:1304.2401v1 fatcat:ioagdwdqcbcchmqpdgkxfgcoxy

RESLVE

Elizabeth L. Murnane, Bernhard Haslhofer, Carl Lagoze
2013 Proceedings of the 22nd International Conference on World Wide Web - WWW '13 Companion  
In such settings, the lack of linguistic features and sparse lexical context result in a high degree of ambiguity and sharp performance drops of nearly 50% in the accuracy of conventional NED systems.  ...  We address the Named Entity Disambiguation (NED) problem for short, user-generated texts on the social Web.  ...  EXPERIMENTS Data Collection and Preparation We collected tweets posted on Twitter, videos posted on YouTube, and photos posted on Flickr.  ... 
doi:10.1145/2487788.2488162 dblp:conf/www/MurnaneHL13a fatcat:ejghrqkqlrerba4pamp22xbjmm

Wikipedia based semantic smoothing for twitter sentiment classification

Dilara Torunoglu, Gurkan Telseren, Ozgun Sagturk, Murat C. Ganiz
2013 2013 IEEE INISTA  
We apply our approach to sentiment classification of tweets.  ...  Sentiment classification is one of the important and popular application areas of text classification in which texts are labeled as positive and negative.  ...  They showed how to automatically collect a corpus for sentiment analysis and opinion mining purposes. They performed linguistic analysis of the collected corpus.  ... 
doi:10.1109/inista.2013.6577649 fatcat:jvyyfalhojag5g7ybdql7mqtde

Multi-source named entity typing for social media

Reuth Vexler, Einat Minkov
2016 Proceedings of the Sixth Named Entity Workshop  
Typed lexicons that encode knowledge about the semantic types of an entity name, e.g., that 'Paris' denotes a geolocation, product, or person, have proven useful for many text processing tasks.  ...  Evaluation in the challenging domain of social media shows that multi-source learning improves performance compared with rule-based KB lookups, boosting typing results for some semantic categories.  ...  We considered a corpus of 2,400 tweets collected by Ritter et al. (2011) .  ... 
doi:10.18653/v1/w16-2702 dblp:conf/aclnews/VexlerM16 fatcat:bbambkuanfbrrc7a3f3usnsiwi

D3.1 TV programme annotation model

Raphael Troncy, Ismail Harrando, Benoit Huet, Jean Carrive, Steffen Lalande, Michael Stormbom, Tiina Lindh-Knuutila, Lauri Saarikoski, Kim Viljanen
2019 Zenodo  
This deliverable describes also a number of tools that perform named entity recognition and disambiguation on both automatic transcription and true subtitles of TV programs.  ...  TV programs) and which has been investigated during the first 6 months of the project.  ...  Acknowledgements This work has been partially supported by the French National Research Agency (ANR) within the ASRAEL project (ANR-15-CE23-0018), the French Fonds Unique Interministériel (FUI) within the NexGen-TV  ... 
doi:10.5281/zenodo.4796668 fatcat:4yfr45rvojfzrha2lcgkmkpxtu

Proceedings of Symposium on Data Mining Applications 2014 [article]

Basit Qureshi, Yasir Javed
2020 arXiv   pre-print
The symposium will provide opportunities for technical collaboration among data mining and machine learning researchers around the Saudi Arabia, GCC countries and Middle-East region.  ...  SDMA is organized by MEGDAM to advance the state of the art in data mining research field and its various real world applications.  ...  News Labeled by the Number of Tweets A collection of manually labeled documents was created.  ... 
arXiv:2001.11324v1 fatcat:ezplxohltvbvrggurw3hdkdhz4

Impact of Unreliable Content on Social Media Users during COVID-19 and Stance Detection System

Mudasir Ahmad Wani, Nancy Agarwal, Patrick Bours
2020 Electronics  
Analysis of collected data was carried out in five phases where we investigate the engagement of E, D, Q, and N users, tone of the tweets, and the consequence upon repeated exposure of such information  ...  A labeled dataset is prepared where each tweet is assigned one of the four reaction polarities, namely, E (endorse), D (deny), Q (question), and N (neutral).  ...  Acknowledgments: This work was carried out during the tenure of an ERCIM Alain Bensoussan Fellowship Program.  ... 
doi:10.3390/electronics10010005 fatcat:hswgttd2pvhn7lm3zbvpeduizm

A linguistic approach for determining the topics of Spanish Twitter messages

David Vilares, Miguel A. Alonso, Carlos Gómez-Rodríguez
2014 Journal of information science  
for multi-label classification tasks.  ...  The TASS 2013 General corpus, a collection of tweets which has been specifically annotated to perform text analytics tasks, is used as the dataset in our evaluation framework.  ...  Appendix A and Appendix B show the topic distribution of tweets in the collection, for both training and test sets. The classes of the training set are unbalanced.  ... 
doi:10.1177/0165551514561652 fatcat:f5x5lyjdtvhtlas2zapfpyq77a

Utilising Wikipedia for Text Mining Applications

Muhammad Atif Qureshi
2016 SIGIR Forum  
Supervised Learning Methods from Text Data Supervised learning methods are a category of methods that exploit training data (i.e., pairs of input data points with a label for the corresponding output point  ...  Reputation Dimensions' Classification Task Using the feature sets described in 5.5.2, we train a random forest classifier over the training data and then use it to predict labels for the test data.  ...  Appendix B Use of Wikipedia Articles' Hyperlink for Filtering Task B.1 Introduction Here, we explain our previous approach for addressing the filtering task in the context of CLEF RepLab 2013 filtering  ... 
doi:10.1145/2888422.2888449 fatcat:lck3kkxoazcj5powaqhjs6epty

What's Happening Around the World? A Survey and Framework on Event Detection Techniques on Twitter

Zafar Saeed, Rabeeh Ayaz Abbasi, Onaiza Maqbool, Abida Sadaf, Imran Razzak, Ali Daud, Naif Radi Aljohani, Guandong Xu
2019 Journal of Grid Computing  
We also describe and compare data collection techniques, the effectiveness and shortcomings of various Twitter and non-Twitterbased features, and discuss various evaluation measures and benchmarking methodologies  ...  It explores recent research trends and techniques for event detection using Twitter data.  ...  Supervised Learning Supervised learning is an approach that generates class labels from training data. The training data consists of a set of examples (typically vectors) and a class label.  ... 
doi:10.1007/s10723-019-09482-2 fatcat:lypwnpnmonb3laa3koftllchby

User-Generated Content (UGC) Credibility on Social Media Using Sentiment Classification

Esraa Afify, Ahmed Sharaf Eldin, Ayman E. Khedr, Fahad Kamal Alsheref
2019 النشرة المعلوماتیة فی الحاسبات والمعلومات  
approach for measuring posts credibility.  ...  This paper adapted some of the existing literature and concluded that many previous approaches have investigated information credibility on Twitter and a limited number of Facebook for proposing a new  ...  Both classifiers were trained over labeled data, obtained using crowdsourcing tools.  ... 
doi:10.21608/fcihib.2019.107506 fatcat:w4vazjtyl5h6zdz2kol2vn5hsy

Lessons learnt from the Named Entity rEcognition and Linking (NEEL) challenge series

Giuseppe Rizzo, Bianca Pereira, Andrea Varga, Marieke van Erp, Amparo Elizabeth Cano Basave, Andreas Hotho, Robert Jäschke, Kristina Lerman, Andreas Hotho, Robert Jäschke, Kristina Lerman
2017 Semantic Web Journal  
tweets, ensuring high quality labelled data that facilitates comparisons between different approaches.  ...  This problem has attracted the attention of industry and research communities, resulting in algorithms for the automatic extraction of semantics in tweets and linking them to machine readable resources  ...  Acknowledgments This work was supported by the FREME project (GA no. 644771) and by the CLARIAH-CORE project financed by the Netherlands Organisation for Scientific Research (NWO).  ... 
doi:10.3233/sw-170276 fatcat:lr45tai2unbotp5nrag5z7pjxy
« Previous Showing results 1 — 15 out of 740 results