This paper describes our participation to the TRAC-2 Shared Tasks on Aggression Identification. Our team, FlorUniTo, investigated the applicability of using an abusive lexicon to enhance word embeddings towards improving detection of aggressive language. The embeddings used in our paper are word-aligned pre-trained vectors for English, Hindi, and Bengali, to reflect the languages in the shared task data sets. The embeddings are retrofitted to a multilingual abusive lexicon, HurtLex. We experimented with an LSTM model using the original as well as the transformed embeddings and different language and setting variations. Overall, our systems placed toward the middle of the official rankings based on weighted F1 score. However, the results on the development and test sets show promising improvements across languages, especially on the misogynistic aggression sub-task.

Detecting abusive language is a significant research topic, which has received a lot of attention recently. Our work focuses on detecting personal attacks in online conversations. As previous research on this task has largely used deep learning based on embeddings, we explore the use of lexicons to enhance embedding-based methods in an effort to see how these methods apply in the particular task of detecting personal attacks. The methods implemented and experimented with in this paper are quite different from each other, not only in the type of lexicons they use (sentiment or semantic), but also in the way they use the knowledge from the lexicons, in order to construct or to change embeddings that are ultimately fed into the learning model. The sentiment lexicon approaches focus on integrating sentiment information (in the form of sentiment embeddings) into the learning model. The semantic lexicon approaches focus on transforming the original word embeddings so that they better represent relationships extracted from a semantic lexicon. Based on our experimental results, semantic lexicon methods are superior to the rest of the methods in this paper, with at least 4% macro-averaged F1 improvement over the baseline.

The detection of abusive or offensive remarks in social texts has received significant attention in research. In several related shared tasks, BERT has been shown to be the state-of-the-art. In this paper, we propose to utilize lexical features derived from a hate lexicon towards improving the performance of BERT in such tasks. We explore different ways to utilize the lexical features in the form of lexicon-based encodings at the sentence level or embeddings at the word level. We provide an extensive dataset evaluation that addresses in-domain as well as cross-domain detection of abusive content to render a complete picture. Our results indicate that our proposed models combining BERT with lexical features help improve over a baseline BERT model in many of our in-domain and cross-domain experiments.

Detecting abusive language is a significant research topic, which has received a lot of attention recently. Our work focused on detecting personal attacks in online conversations. State-of-the-art research on this task has largely used deep learning with word embeddings. We explored the use of sentiment lexicons as well as semantic lexicons towards improving the accuracy of the baseline Convolutional Neural Network (CNN) using regular word embeddings. This is a work in progress, limited by time constraints and appropriate infrastructure. Our preliminary results showed promise for utilizing lexicons, especially semantic lexicons, for the task of detecting abusive language.