Bilkent University
Department of Computer Engineering
S E M I N A R

 

Stance Detection: A Review

 

Assoc. Prof. Dr. Dilek Küçük
TUBÝTAK Marmara Research Center (MRC)

Automatic elicitation of semantic information from natural language texts is an important research problem with many practical application areas. Especially after the recent proliferation of the online content through channels such as social media sites, news portals, and forums; solutions to problems such as sentiment analysis, sarcasm/controversy/veracity/rumour/fake news detection, and argument mining gained increasing impact and significance, revealed with large volumes of related scientific publications. In this talk, we tackle an important problem from the same family and present a review of stance detection in social media posts and online regular texts. Although stance detection is defined in different ways in different application settings, the most common definition is "automatic classification of the stance of the producer of a piece of text, towards a target, into one of these three classes: {Favor, Against, Neither}". Our talk includes definitions of related problems and concepts, classifications of the proposed approaches so far, descriptions of the relevant datasets and tools, observations and recommendations for stance detection researchers, and future research topics. We will also present the results of stance detection experiments on tweets in Turkish, performed so far. Stance detection is a recent and fruitful natural language processing topic for both researchers and practitioners, with its diverse application areas and several lines of future work.

Keywords: Stance detection, Twitter, Social media analysis, Natural language processing

Bio: Dilek Küçük, Ph.D, is an associate professor and chief researcher at the Energy Institute of TUBÝTAK Marmara Research Center (MRC) in Ankara. She is also the leader of Power Systems Information Technologies Group at the institute. Her group is the recipient of the best research group award of TUBÝTAK MRC for the year 2017. She received her B.Sc., M.Sc. and Ph.D. degrees in Computer Engineering all from Middle East Technical University in 2003, 2005, and 2011, respectively. Between May 2013 and May 2014, she studied as a post-doctoral researcher at European Commission’s Joint Research Centre in Italy. Her research interests include energy informatics, social media analysis, natural language processing, and data mining. She is the author or co-author of 15 papers published in SCI-indexed journals and more than 35 papers presented at international conferences.

 

DATE: 13 December 2019, Friday @ 09:40
PLACE: EA 409