@article {1968, title = {Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior}, year = {2018}, publisher = {AAAI}, address = {Stanford, California}, abstract = {

In recent years, offensive, abusive and hateful language, sexism, racism and other types of aggressive and cyberbullying behavior have been manifesting with increased frequency, and in many online social media platforms. In fact, past scientific work focused on studying these forms in popular media, such as Facebook and Twitter. Building on such work, we present an 8-month study of the various forms of abusive behavior on Twitter, in a holistic fashion. Departing from past work, we examine a wide variety of labeling schemes, which cover different forms of abusive behavior, at the same time. We propose an incremental and iterative methodology, that utilizes the power of crowdsourcing to annotate a large scale collection of tweets with a set of abuse-related labels. In fact, by applying our methodology including statistical analysis for label merging or elimination, we identify a reduced but robust set of labels. Finally, we offer a first overview and findings of our collected and annotated dataset of 100 thousand tweets, which we make publicly available for further scientific exploration.

}, author = {Antigoni-Maria Founta and Constantinos Djouvas and Despoina Chatzakou and Ilias Leontiadis and Jeremy Blackburn and Gianluca Stringhini and Athena Vakali and Michael Sirivianos and Nicolas Kourtellis} }