Absit invidia verbo: Comparing Deep Learning methods for offensive language
This work addresses the need for automated moderation of offensive content on social media, but it is incremental as it applies existing deep learning methods to a specific competition dataset.
The paper tackled the problem of building classifiers for offensive language detection in tweets, as part of the OffensEval 2019 competition, and achieved macro-averaged F1-scores of 0.7189, 0.6708, and 0.5442 on three tasks.
This document describes our approach to building an Offensive Language Classifier. More specifically, the OffensEval 2019 competition required us to build three classifiers with slightly different goals: - Offensive language identification: would classify a tweet as offensive or not. - Automatic categorization of offense types: would recognize if the target of the offense was an individual or not. - Offense target identification: would identify the target of the offense between an individual, group or other. In this report, we will discuss the different architectures, algorithms and pre-processing strategies we tried, together with a detailed description of the designs of our final classifiers and the reasons we choose them over others. We evaluated our classifiers on the official test set provided for the OffenseEval 2019 competition, obtaining a macro-averaged F1-score of 0.7189 for Task A, 0.6708 on Task B and 0.5442 on Task C.