Millions of posts and comments are created every minute as a result of the widespread use of social media and easy access to the internet.It is essential to create an inclusive environment and forbid the use of abusive language against any individual or group of individuals.This paper describes the approach of team HARMONY for the “Abusive Comment Detection” shared task at the Third Workshop on Speech and Language Technologies for Dravidian Languages.A Transformer-based ensemble learning approach is proposed for detecting abusive comments in code-mixed (Tamil-English) language and Tamil language. The proposed architecture achieved rank 2 in Tamil text classification sub task and rank 3 in code mixed text classification sub task with macro-F1 score of 0.41 for Tamil and 0.50 for code-mixed data.

HOPE speeches convey uplifting and motivating messages that help enhance mental health and general well-being. Hope speech detection has gained popularity in the field of natural language processing as it gives people the motivation they need to face challenges in life. The momentum behind this technology has been fueled by the demand for encouraging reinforcement online. In this paper, a deep learning approach is proposed in which four different word embedding techniques are used in combination with capsule networks, and a comparative analysis is performed to obtain results. Oversampling is used to address class imbalance problem. The dataset used in this paper is a part of the LT-EDI RANLP 2023 Hope Speech Detection shared task. The approach proposed in this paper achieved a Macro Average F1 score of 0.49 and 0.62 in English and Hindi-English code mix test data, which secured 2nd and 3rd rank respectively in the above mentioned share task.