Mavericks at BLP-2023 Task 1: Ensemble-based Approach Using Language Models for Violence Inciting Text Detection
This work addresses the problem of detecting harmful content on social media for Bangla speakers, but it is incremental as it applies existing ensemble methods to a new dataset.
The paper tackled violence-inciting text detection in Bangla, a low-resource language, using an ensemble of BERT-based models, achieving a macro F1 score of 0.737 and ranking 10th in a shared task.
This paper presents our work for the Violence Inciting Text Detection shared task in the First Workshop on Bangla Language Processing. Social media has accelerated the propagation of hate and violence-inciting speech in society. It is essential to develop efficient mechanisms to detect and curb the propagation of such texts. The problem of detecting violence-inciting texts is further exacerbated in low-resource settings due to sparse research and less data. The data provided in the shared task consists of texts in the Bangla language, where each example is classified into one of the three categories defined based on the types of violence-inciting texts. We try and evaluate several BERT-based models, and then use an ensemble of the models as our final submission. Our submission is ranked 10th in the final leaderboard of the shared task with a macro F1 score of 0.737.