Overview of MEX-A3T at IberLEF 2019: Authorship and Aggressiveness Analysis in Mexican Spanish Tweets

Mario Ezra Aragón, Miguel Ángel Álvarez Carmona, Manuel Montes-y-Gómez, Hugo Jair Escalante, Luis Villaseñor Pineda, Daniela Moctezuma
2019 Annual Conference of the Spanish Society for Natural Language Processing  
This paper presents the framework and results from the MEX-A3T track at IberLEF 2019. This track considers two tasks, author profiling and aggressiveness detection, both of them using Mexican Spanish tweets. The author profiling task consists on determining the gender, occupation and place of residence of users from their tweets. As a novelty in this year's edition, it considers the use of text and images as information sources, with the aim of studying the relevance and complementarity of
more » ... modal data for profiling social media users. On the other hand, the aggressiveness detection task follows the same design than the previous edition; it aims to discriminate between aggressive and non-aggressive tweets. For both tasks, we have built new corpora considering tweets from Mexican Twitter users. This paper compares and discusses the results of the participants.
dblp:conf/sepln/AragonCMEPM19 fatcat:mnvptnucgfhgbo24h3nzkrykki