Stance Detection: A Review<\/p>\n
Assoc. Prof. Dr. Dilek K\u00fc\u00e7\u00fck
\nTUB\u0130TAK Marmara Research Center (MRC)<\/p>\n
Automatic elicitation of semantic information from natural language\u00a0texts is an important research problem with many practical application
\nareas. Especially after the recent proliferation of the online content\u00a0through channels such as social media sites, news portals, and forums;
\nsolutions to problems such as sentiment analysis,\u00a0sarcasm\/controversy\/veracity\/rumour\/fake news detection, and argument
\nmining gained increasing impact and significance, revealed with large\u00a0volumes of related scientific publications. In this talk, we tackle an
\nimportant problem from the same family and present a review of stance\u00a0detection in social media posts and online regular texts. Although
\nstance detection is defined in different ways in different application\u00a0settings, the most common definition is “automatic classification of the
\nstance of the producer of a piece of text, towards a target, into one of\u00a0these three classes: {Favor, Against, Neither}”. Our talk includes
\ndefinitions of related problems and concepts, classifications of the\u00a0proposed approaches so far, descriptions of the relevant datasets and
\ntools, observations and recommendations for stance detection\u00a0researchers, and future research topics. We will also present the
\nresults of stance detection experiments on tweets in Turkish, performed\u00a0so far. Stance detection is a recent and fruitful natural language
\nprocessing topic for both researchers and practitioners, with its\u00a0diverse application areas and several lines of future work.<\/p>\n
KEYWORDS: Stance detection, Twitter, Social media analysis, Natural\u00a0language processing<\/p>\n
BIO: Dilek K\u00fc\u00e7\u00fck, Ph.D, is an associate professor and chief\u00a0researcher at the Energy Institute of TUB\u0130TAK Marmara Research Center
\n(MRC) in Ankara. She is also the leader of Power Systems Information\u00a0Technologies Group at the institute. Her group is the recipient of the
\nbest research group award of TUB\u0130TAK MRC for the year 2017. She\u00a0received her B.Sc., M.Sc. and Ph.D. degrees in Computer Engineering all
\nfrom Middle East Technical University in 2003, 2005, and 2011,\u00a0respectively. Between May 2013 and May 2014, she studied as a
\npost-doctoral researcher at European Commission’s Joint Research Centre\u00a0in Italy. Her research interests include energy informatics, social
\nmedia analysis, natural language processing, and data mining. She is the\u00a0author or co-author of 15 papers published in SCI-indexed journals and\u00a0more than 35 papers presented at international conferences.<\/p>\n
DATE: 13 December 2019, Friday @ 09:40
\nPLACE: EA 409<\/p>\n","protected":false},"excerpt":{"rendered":"
Stance Detection: A Review Assoc. Prof. Dr. Dilek K\u00fc\u00e7\u00fck TUB\u0130TAK Marmara Research Center (MRC) Automatic elicitation of semantic information from natural language\u00a0texts is an important research problem with many practical application areas. Especially after the recent proliferation of the online content\u00a0through channels such as social media sites, news portals, and [\u2026] <\/p>\n