Combination of multiple Deep Learning architectures for Offensive Language Detection in Tweets
This work addresses the problem of identifying offensive content in social media for moderation purposes, but it is incremental as it builds on existing methods for a known challenge.
The paper tackled offensive language detection in tweets by combining multiple deep learning architectures, achieving macro-average F1-scores of 0.76, 0.68, and 0.54 for three specific tasks in the OffensEval 2019 competition.
This report contains the details regarding our submission to the OffensEval 2019 (SemEval 2019 - Task 6). The competition was based on the Offensive Language Identification Dataset. We first discuss the details of the classifier implemented and the type of input data used and pre-processing performed. We then move onto critically evaluating our performance. We have achieved a macro-average F1-score of 0.76, 0.68, 0.54, respectively for Task a, Task b, and Task c, which we believe reflects on the level of sophistication of the models implemented. Finally, we will be discussing the difficulties encountered and possible improvements for the future.