Sarcasm Detection in Tamil Code-Mixed Data Using Transformers

Social media analytics has been increasingly gaining popularity due to the extensive amount of customer data it offers, benefiting businesses of all sizes, from local ventures to global brands. Analysing textual contents aids context understanding and also enables content moderation to maintain a positive user experience. Sarcasm detection in social media is essential to maintain constructive and respectful online communication, preventing misunderstandings, minimizing conflicts, and fostering a positive and inclusive digital environment. We propose a Transformer based model for sarcasm detection in Tamil code-mixed text. The model consists of two custom-designed layers: Encoder and Embedding layer. It incorporates multi-head self-attention layer and feed-forward neural networks, followed by normalisation and dropout layers. The proposed model has outperformed compared to other state-of-art models for sarcasm detection by achieving an impressive weighted \(F_1\) score of 0.77. This proposed model effectively addressed the unique challenges posed by the Tamil code-mixed text.