Contrasting Public Opinion Dynamics and Emotional Response During Crisis

We propose an approach for contrasting spatiotemporal dynamics of public opinions expressed toward targeted entities, also known as stance detection task, in Russia and Ukraine during crisis. Our analysis relies on a novel corpus constructed from posts on the VKontakte social network, centered on local public opinion of the ongoing Russian-Ukrainian crisis, along with newly annotated resources for predicting expressions of fine-grained emotions including joy, sadness, disgust, anger, surprise and fear. Akin to prior work on sentiment analysis we align traditional public opinion polls with aggregated automatic predictions of sentiments for contrastive geo-locations. We report interesting observations on emotional response and stance variations across geo-locations. Some of our findings contradict stereotypical misconceptions imposed by media, for example, we found posts from Ukraine that do not support Euromaidan but support Putin, and posts from Russia that are against Putin but in favor USA. Furthermore, we are the first to demonstrate contrastive stance variations over time across geo-locations using storyline visualization (Storyline visualization is available at http://www.cs.jhu.edu/~svitlana/) technique.

[1]  Naren Ramakrishnan,et al.  SourceSeer: Forecasting Rare Disease Outbreaks Using Multiple Data Sources , 2015, SDM.

[2]  A. Smeaton,et al.  On Using Twitter to Monitor Political Sentiment and Predict Election Results , 2011 .

[3]  Carlo Strapparava,et al.  WordNet Affect: an Affective Extension of WordNet , 2004, LREC.

[4]  Brendan T. O'Connor,et al.  From Tweets to Polls: Linking Text Sentiment to Public Opinion Time Series , 2010, ICWSM.

[5]  Isabell M. Welpe,et al.  Predicting Elections with Twitter: What 140 Characters Reveal about Political Sentiment , 2010, ICWSM.

[6]  Kristina Lerman,et al.  The Simple Rules of Social Contagion , 2013, Scientific Reports.

[7]  Dan Mercea,et al.  Serial activists: Political Twitter beyond influentials and the twittertariat , 2016, New Media Soc..

[8]  Trevor Cohn,et al.  A user-centric model of voting intention from Social Media , 2013, ACL.

[9]  Tingshao Zhu,et al.  Classify Sina Weibo users into High or Low happiness Groups Using Linguistic and Behavior Features , 2015, ArXiv.

[10]  Andrew E. Johnson,et al.  Visualizing the Evolution of Community Structures in Dynamic Social Networks , 2011, Comput. Graph. Forum.

[11]  Jeffrey Heer,et al.  Tracing genealogical data with TimeNets , 2010, AVI.

[12]  Hanan Samet,et al.  Mining future spatiotemporal events and their sentiment from online news articles for location-aware recommendation system , 2012, MobiGIS.

[13]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[14]  Kwan-Liu Ma,et al.  Software evolution storylines , 2010, SOFTVIS '10.

[15]  Leysia Palen,et al.  Microblogging during two natural hazards events: what twitter may contribute to situational awareness , 2010, CHI.

[16]  TesTing rules for a senTimenT analysis sysTem , 2013 .

[17]  Armin R. Mikler,et al.  Text and Structural Data Mining of Influenza Mentions in Web and Social Media , 2010, International journal of environmental research and public health.

[18]  Marcel Salathé,et al.  Assessing Vaccination Sentiments with Online Social Media: Implications for Infectious Disease Dynamics and Control , 2011, PLoS Comput. Biol..

[19]  Le T. Nguyen,et al.  Predicting collective sentiment dynamics from time-series social media , 2012, WISDOM '12.

[20]  Svitlana Volkova,et al.  On Predicting Sociodemographic Traits and Emotions from Communications in Social Networks and Their Implications to Online Self-Disclosure , 2015, Cyberpsychology Behav. Soc. Netw..

[21]  J. Krosnick,et al.  National Surveys Via Rdd Telephone Interviewing Versus the Internet Comparing Sample Representativeness and Response Quality , 2009 .

[22]  Natalia V. Loukachevitch,et al.  Evaluating Sentiment Analysis Systems in Russian , 2013, BSNLP@ACL.

[23]  Maarten Sap,et al.  Developing Age and Gender Predictive Lexica over Social Media , 2014, EMNLP.

[24]  Zeynep Tufekci,et al.  Big Questions for Social Media Big Data: Representativeness, Validity and Other Methodological Pitfalls , 2014, ICWSM.

[25]  G. Eysenbach,et al.  Pandemics in the Age of Twitter: Content Analysis of Tweets during the 2009 H1N1 Outbreak , 2010, PloS one.

[26]  P. Ekman.  An argument for basic emotions , 1992 .

[27]  Aron Culotta,et al.  Tweedr: Mining twitter to inform disaster response , 2014, ISCRAM.

[28]  Eugene Agichtein,et al.  Towards Tracking Political Sentiment through Microblog Data , 2014 .

[29]  Mengchen Liu,et al.  StoryFlow: Tracking the Evolution of Stories , 2013, IEEE Transactions on Visualization and Computer Graphics.

[30]  Munmun De Choudhury,et al.  Happy, Nervous or Surprised? Classification of Human Affective States in Social Media , 2012, ICWSM.

[31]  Johan Bollen,et al.  Twitter mood predicts the stock market , 2010, J. Comput. Sci..

[32]  Nina Wacholder,et al.  Identifying Sarcasm in Twitter: A Closer Look , 2011, ACL.

[33]  Cláudio de Souza Baptista,et al.  A Spatial and Temporal Sentiment Analysis Approach Applied to Twitter Microtexts , 2015, J. Inf. Data Manag..

[34]  Saif Mohammad,et al.  Using Hashtags to Capture Fine Emotion Categories from Tweets , 2015, Comput. Intell..

[35]  N. V. Loukachevitch,et al.  Open evaluation of sentiment-analysis systems based on the material of the Russian language , 2014, Scientific and Technical Information Processing.

[36]  Mark Dredze,et al.  Combining Search, Social Media, and Traditional Data Sources to Improve Influenza Surveillance , 2015, PLoS Comput. Biol..

[37]  Bo Pang,et al.  Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

[38]  Kwan-Liu Ma,et al.  An Efficient Framework for Generating Storyline Visualizations from Streaming Data , 2015, IEEE Transactions on Visualization and Computer Graphics.

[39]  A. Culotta,et al.  A Demographic Analysis of Online Sentiment during Hurricane Irene , 2012 .

[40]  Rui Fan,et al.  Anger Is More Influential than Joy: Sentiment Correlation in Weibo , 2013, PloS one.

[41]  Nello Cristianini,et al.  Effects of the recession on public mood in the UK , 2012, WWW.

[42]  R.J.P. Stronkman,et al.  Towards a realtime Twitter analysis during crises for operational crisis management , 2012, ISCRAM.

[43]  Natalia V. Loukachevitch,et al.  Уточнение русскоязычных словарей эмоциональной лексики с использованием тезауруса RuThes (Refinement of Russian Sentiment Lexicons Using RuThes Thesaurus) , 2014, RCDL.

[44]  Nello Cristianini,et al.  Flu Detector - Tracking Epidemics on Twitter , 2010, ECML/PKDD.