Understanding patterns and mood changes through tweets about disasters

We analyzed a sample of large tweet collections gathered since 2011, to expand understanding about tweeting patterns and emotional responses of different types of tweeters regarding disasters. We selected three examples for each of four disaster types: school shooting, bombing, earthquake, and hurricane. For each collection, we deployed our novel model TwiRole for user classification, and an existing deep learning model for mood detection. We found differences in the daily tweet count patterns, between the different types of events. Likewise, there were different average scores and patterns of moods (fear, sadness, surprise), both between types of events, and between events of the same type. Further, regarding surprise and fear, there were differences among roles of tweeters. These results suggest the value of further exploration as well as hypothesis testing with our hundreds of event and trend related tweet collections, considering indications in those that reflect emotional responses to disasters.

[1]  Jeannie A. Stamberger,et al.  Crowd sentiment detection during disasters and crises , 2012, ISCRAM.

[2]  Derek Ruths,et al.  Gender Inference of Twitter Users in Non-English Contexts , 2013, EMNLP.

[3]  C. Artwick,et al.  News sourcing and gender on Twitter , 2014 .

[4]  Ana-Maria Popescu,et al.  A Machine Learning Approach to Twitter User Classification , 2011, ICWSM.

[5]  Yong-Yeol Ahn,et al.  Twitter's Glass Ceiling: The Effect of Perceived Gender on Online Visibility , 2016, ICWSM.

[6]  Robert Plutchik,et al.  EMOTIONS AND PSYCHOTHERAPY: A PSYCHOEVOLUTIONARY PERSPECTIVE , 1990 .

[7]  Karthik Bhat,et al.  WhatsApp for Monitoring and Response during Critical Events: Aggie in the Ghana 2016 Election , 2017, ISCRAM.

[8]  Philip S. Yu,et al.  Empirical Evaluation of Profile Characteristics for Gender Classification on Twitter , 2013, 2013 12th International Conference on Machine Learning and Applications.

[9]  John D. Burger,et al.  Discriminating Gender on Twitter , 2011, EMNLP.

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

[11]  Eduard H. Hovy,et al.  Weakly Supervised User Profile Extraction from Twitter , 2014, ACL.

[12]  Hemant Purohit,et al.  Classifying User Types on Social Media to inform Who-What-Where Coordination during Crisis Response , 2017, ISCRAM.

[13]  Janez Demšar,et al.  Emotion Recognition on Twitter: Comparative Study and Training a Unison Model , 2020, IEEE Transactions on Affective Computing.

[14]  Fernando Batista,et al.  Twitter gender classification using user unstructured information , 2015, 2015 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[15]  Ke Zhang,et al.  Soft Biometrics in Online Social Networks: A Case Study on Twitter User Gender Recognition , 2017, 2017 IEEE Winter Applications of Computer Vision Workshops (WACVW).

[16]  Cornelia Caragea,et al.  Retweetability Analysis and Prediction during Hurricane Sandy , 2016, ISCRAM.

[17]  D. Ruths,et al.  What's in a Name? Using First Names as Features for Gender Inference in Twitter , 2013, AAAI Spring Symposium: Analyzing Microtext.

[18]  Ana-Maria Popescu,et al.  Democrats, republicans and starbucks afficionados: user classification in twitter , 2011, KDD.

[19]  Firoj Alam,et al.  A Twitter Tale of Three Hurricanes: Harvey, Irma, and Maria , 2018, ISCRAM.

[20]  Yang Feng,et al.  Voting with Feet: Who are Leaving Hillary Clinton and Donald Trump , 2016, 2016 IEEE International Symposium on Multimedia (ISM).

[21]  J O Prochaska,et al.  Factor structure of the Profile of Mood States (POMS): two partial replications. , 1984, Journal of clinical psychology.

[22]  Hiroko Wilensky,et al.  Twitter as a navigator for stranded commuters during the great east Japan earthquake , 2014, ISCRAM.

[23]  Cornelia Caragea,et al.  Mapping moods: Geo-mapped sentiment analysis during hurricane sandy , 2014, ISCRAM.

[24]  Edward A. Fox,et al.  A digital library for water main break identification and visualization , 2012, JCDL '12.

[25]  Changqing Song,et al.  Spatial distribution patterns of global natural disasters based on biclustering , 2018, Natural Hazards.

[26]  Scott Fortmann-Roe.  Effects of hue, saturation, and brightness on color preference in social networks: Gender‐based color preference on the social networking site Twitter , 2013 .

[27]  Axel Schulz,et al.  A fine-grained sentiment analysis approach for detecting crisis related microposts , 2013, ISCRAM.

[28]  Deborah Bunker,et al.  Sydney Siege, December 2014: A Visualisation of a Semantic Social Media Sentiment Analysis , 2018, ISCRAM.

[29]  Philip S. Yu,et al.  Language independent gender classification on Twitter , 2013, 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2013).

[30]  Alexander Zipf,et al.  Does the spatiotemporal distribution of tweets match the spatiotemporal distribution of flood phenomena? A study about the River Elbe Flood in June 2013 , 2014, ISCRAM.

[31]  Edward A. Fox,et al.  PhaseVis1: What, when, where, and who in visualizing the four phases of emergency management through the lens of social media , 2013, ISCRAM.

[32]  D. Lasorsa.  TRANSPARENCY AND OTHER JOURNALISTIC NORMS ON TWITTER , 2012 .

[33]  Kai Fischbach,et al.  Terror Management and Twitter: The Case of the 2016 Berlin Terrorist Attack , 2018, ISCRAM.

[34]  Tal Hassner,et al.  Age and gender classification using convolutional neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[35]  David Yarowsky,et al.  Classifying latent user attributes in twitter , 2010, SMUC '10.

[36]  Hicham G. Elmongui,et al.  Between a Rock and a Cell Phone: Communication and Information Technology Use during the 2011 Uprisings in Tunisia and Egypt , 2013, Int. J. Inf. Syst. Crisis Response Manag..

[37]  David Bamman,et al.  Gender identity and lexical variation in social media , 2012, 1210.4567.