A Transformer-based Multimodal Approach For CyberbullyingDetection

With the increase of interactions on the web and social media such as Twitter, a large amount of content is produced by users, and as a result, it has led to the continuous expansion of online harassment, insults, and attacks, which is called cyberbullying or internet harassment. Identifying texts containing internet harassment has become challenging in natural language processing tasks. Therefore, designing efficient methods to automatically identify such content has become integral to most social media platforms. In this study, we put forward several ALEBERT-based models to classify cyberbullying. To that end, we obtained data from Twitter and proposed the base model BPM, which solely utilizes the textual content of a tweet for categorization. Afterwards, we integrated social network relationships quantified by the number of friends and followers, the number of likes, as well as the number of retweets. We investigated the effect of individual features and their combinations on the performance of the principal model. Our findings demonstrate that incorporating user communication attributes can enhance the accuracy of the baseline model. Specifically, the BPM_LC_RC_FC model, which involves tweet content and all suggested features, resulted in the best overall accuracy and F۱-Score of ۹۸.۸۰ in comparison to previous methods. This promising outcome is noteworthy as it represents the first multimodal approach to cyberbullying classification.

Keywords:

Cyberbullying , Internet Harassment , Social Media , Transformer , ALBERT