Analyzing #LasTesis Feminist Movement in Twitter Using Topic Models

Nowadays, social networks have created a massive mean of communication, that was unthinkable many years ago. Informal communication, blogging, and online discussions have transformed the Web into a huge repository of remarks on numerous themes, producing a potential wellspring of data for various areas. In this paper we analyze, using Topic Models, a recent widespread feminist movement. Las Tesis is a feminist collective that initiated a protest against sexual abuse, and that was replicated in more than dozen different countries in matter of days. We use LDA and BTM to detect automatically the topics in over 627643 tweets that were gathered from the 25th November until the 5th January. The resulting topics obtained, from tweets in Spanish and English, show that these algorithms are able to capture the real-world events that occurred in Chile and Turkey.

[1]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[2]  H. Christensen,et al.  Detecting suicidality on Twitter , 2015 .

[3]  Thomas Hofmann,et al.  Probabilistic Latent Semantic Indexing , 1999, SIGIR Forum.

[4]  Andrew Tomkins,et al.  How to build a WebFountain: An architecture for very large-scale text analytics , 2004, IBM Syst. J..

[5]  Efthimis N. Efthimiadis,et al.  Conversational tagging in twitter , 2010, HT '10.

[6]  Nick Koudas,et al.  BlogScope: A System for Online Analysis of High Volume Text Streams , 2007, VLDB.

[7]  Roger Burrows,et al.  The Coming Crisis of Empirical Sociology , 2007, Sociology.

[8]  S. Dumais Latent Semantic Analysis. , 2005 .

[9]  John Yen,et al.  Probabilistic Community Discovery Using Hierarchical Latent Gaussian Mixture Model , 2007, AAAI.

[10]  Bernard J. Jansen,et al.  Twitter power: Tweets as electronic word of mouth , 2009 .

[11]  David M. Blei,et al.  Connections between the lines: augmenting social networks with text , 2009, KDD.

[12]  Andrew McCallum,et al.  Joint Group and Topic Discovery from Relations and Text , 2006, SNA@ICML.

[13]  H. Voorveld Brand Communication in Social Media: A Research Agenda , 2019, Journal of Advertising.

[14]  Yan Liu,et al.  Topic-link LDA: joint models of topic and author community , 2009, ICML '09.

[15]  Barbara Poblete,et al.  Nowcasting earthquake damages with Twitter , 2019, EPJ Data Science.

[16]  Dongjin Yu,et al.  Hierarchical Topic Modeling of Twitter Data for Online Analytical Processing , 2019, IEEE Access.

[17]  Andrea Esuli,et al.  SENTIWORDNET: A Publicly Available Lexical Resource for Opinion Mining , 2006, LREC.

[18]  Xiaohui Yan,et al.  A biterm topic model for short texts , 2013, WWW.