Multilingual stance detection in social media political debates

Abstract Stance Detection is the task of automatically determining whether the author of a text is in favor, against, or neutral towards a given target. In this paper we investigate the portability of tools performing this task across different languages, by analyzing the results achieved by a Stance Detection system (i.e. MultiTACOS) trained and tested in a multilingual setting. First of all, a set of resources on topics related to politics for English, French, Italian, Spanish and Catalan is provided which includes: novel corpora collected for the purpose of this study, and benchmark corpora exploited in Stance Detection tasks and evaluation exercises known in literature. We focus in particular on the novel corpora by describing their development and by comparing them with the benchmarks. Second, MultiTACOS is applied with different sets of features especially designed for Stance Detection, with a specific focus to exploring and combining both features based on the textual content of the tweet (e.g., style and affective load) and features based on contextual information that do not emerge directly from the text. Finally, for better highlighting the contribution of the features that most positively affect system performance in the multilingual setting, a features analysis is provided, together with a qualitative analysis of the misclassified tweets for each of the observed languages, devoted to reflect on the open challenges.

[1]  Wei Hu,et al.  Mutually Enhancing Community Detection and Sentiment Analysis on Twitter Networks , 2013 .

[2]  Daniel DellaPosta,et al.  Why Do Liberals Drink Lattes?1 , 2015, American Journal of Sociology.

[3]  Swapna Somasundaran,et al.  Recognizing Stances in Online Debates , 2009, ACL.

[4]  Diego Marcheggiani,et al.  You Shall Know a User by the Company It Keeps: Dynamic Representations for Social Media Users in NLP , 2019, EMNLP.

[5]  Marie-Francine Moens,et al.  A machine learning approach to sentiment analysis in multilingual Web texts , 2009, Information Retrieval.

[6]  Owen Rambow,et al.  Sentiment Analysis of Twitter Data , 2011 .

[7]  James W. Pennebaker,et al.  Linguistic Inquiry and Word Count (LIWC2007) , 2007 .

[8]  S. V. Vychegzhanin,et al.  Stance Detection Based on Ensembles of Classifiers , 2019, Programming and Computer Software.

[9]  Paolo Rosso,et al.  Stance Evolution and Twitter Interactions in an Italian Political Debate , 2018, NLDB.

[10]  Alexandra Balahur,et al.  Comparative experiments using supervised learning and machine translation for multilingual sentiment analysis , 2014, Comput. Speech Lang..

[11]  Preslav Nakov,et al.  SemEval-2015 Task 10: Sentiment Analysis in Twitter , 2015, *SEMEVAL.

[12]  Paolo Rosso,et al.  Extracting Graph Topological Information and Users' Opinion , 2017, CLEF.

[13]  Paolo Rosso,et al.  Overview of the Task on Stance and Gender Detection in Tweets on Catalan Independence , 2017, IberEval@SEPLN.

[14]  C. Whissell.  Using the Revised Dictionary of Affect in Language to Quantify the Emotional Undertones of Samples of Natural Language , 2009, Psychological reports.

[15]  Jean-Loup Guillaume,et al.  Fast unfolding of communities in large networks , 2008, 0803.0476.

[16]  Guido Zarrella,et al.  MITRE at SemEval-2016 Task 6: Transfer Learning for Stance Detection , 2016, *SEMEVAL.

[17]  Stephen Shaoyi Liao,et al.  Sentiment community detection in social networks , 2011, iConference '11.

[18]  Helmut Schmid,et al.  Part-of-Speech Tagging With Neural Networks , 1994, COLING.

[19]  Xin Liu,et al.  Condensed Convolution Neural Network by Attention over Self-attention for Stance Detection in Twitter , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[20]  Mykola Pechenizkiy,et al.  SentiCorr: Multilingual Sentiment Analysis of Personal Correspondence , 2011, 2011 IEEE 11th International Conference on Data Mining Workshops.

[21]  Saif Mohammad,et al.  SemEval-2016 Task 6: Detecting Stance in Tweets , 2016, *SEMEVAL.

[22]  Huan Liu,et al.  Identifying Users with Opposing Opinions in Twitter Debates , 2014, SBP.

[23]  Saif Mohammad,et al.  Stance and Sentiment in Tweets , 2016, ACM Trans. Internet Techn..

[24]  Finn Årup Nielsen,et al.  A New ANEW: Evaluation of a Word List for Sentiment Analysis in Microblogs , 2011, #MSM.

[25]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[26]  Janyce Wiebe,et al.  Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis , 2005, HLT.

[27]  Kerstin Denecke,et al.  Using SentiWordNet for multilingual sentiment analysis , 2008, 2008 IEEE 24th International Conference on Data Engineering Workshop.

[28]  Fabio Celli,et al.  Predicting Brexit: Classifying Agreement is Better than Sentiment and Pollsters , 2016, PEOPLES@COLING.

[29]  Cristina Bosco,et al.  Social Media Analysis for Monitoring Political Sentiment , 2018, Encyclopedia of Social Network Analysis and Mining. 2nd Ed..

[30]  Réka Albert,et al.  Near linear time algorithm to detect community structures in large-scale networks. , 2007, Physical review. E, Statistical, nonlinear, and soft matter physics.

[31]  Kalina Bontcheva,et al.  Stance Detection with Bidirectional Conditional Encoding , 2016, EMNLP.

[32]  C. Bosco,et al.  Tweeting in the Debate about Catalan Elections , 2016 .

[33]  Wenji Mao,et al.  A Target-Guided Neural Memory Model for Stance Detection in Twitter , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[34]  Jingfang Xu,et al.  Exploring Answer Stance Detection with Recurrent Conditional Attention , 2019, AAAI.

[35]  Carlos Almendros Cuquerella,et al.  CriCa Team: MultiModal Stance Detection in Tweets on Catalan 1Oct Referendum (MultiStanceCat) , 2018, IberEval@SEPLN.

[36]  Saif Mohammad,et al.  CROWDSOURCING A WORD–EMOTION ASSOCIATION LEXICON , 2013, Comput. Intell..

[37]  Isabel Segura-Bedmar.  LABDA's Early Steps Toward Multimodal Stance Detection , 2018, IberEval@SEPLN.

[38]  Saif Mohammad,et al.  A Dataset for Detecting Stance in Tweets , 2016, LREC.

[39]  Dilek Küçük,et al.  A Tweet Dataset Annotated for Named Entity Recognition and Stance Detection , 2019, ArXiv.

[40]  Paolo Rosso,et al.  Friends and Enemies of Clinton and Trump: Using Context for Detecting Stance in Political Tweets , 2016, MICAI.

[41]  Oksana Smal,et al.  POLITICAL DISCOURSE CONTENT ANALYSIS: A CRITICAL OVERVIEW OF A COMPUTERIZED TEXT ANALYSIS PROGRAM LINGUISTIC INQUIRY AND WORD COUNT (LIWC) , 2020, Naukovì zapiski Nacìonalʹnogo unìversitetu «Ostrozʹka akademìâ». Serìâ «Fìlologìâ».

[42]  Xiao Zhang,et al.  pkudblab at SemEval-2016 Task 6 : A Specific Convolutional Neural Network System for Effective Stance Detection , 2016, *SEMEVAL.

[43]  Martin Tutek,et al.  TakeLab at SemEval-2016 Task 6: Stance Classification in Tweets Using a Genetic Algorithm Based Ensemble , 2016, *SEMEVAL.

[44]  Cristina Bosco,et al.  Annotating Italian Social Media Texts in Universal Dependencies , 2017, DepLing.

[45]  Darrell M. West,et al.  Polling effects in election campaigns , 1991 .

[46]  Preslav Nakov,et al.  SemEval-2013 Task 2: Sentiment Analysis in Twitter , 2013, *SEMEVAL.

[47]  Mirko Lai,et al.  iTACOS at IberEval2017: Detecting Stance in Catalan and Spanish Tweets , 2017, IberEval@SEPLN.

[48]  Paolo Rosso,et al.  Overview of the Task on Multimodal Stance Detection in Tweets on Catalan #1Oct Referendum , 2018, IberEval@SEPLN.

[49]  Saroj Kaushik,et al.  Topical Stance Detection for Twitter: A Two-Phase LSTM Model Using Attention , 2018, ECIR.

[50]  Michele Zappavigna.  Searchable talk: the linguistic functions of hashtags , 2015 .

[51]  Timothy Baldwin,et al.  #ISISisNotIslam or #DeportAllMuslims?: predicting unspoken views , 2016, WebSci.