TRITAG RECOMMENDER: A HYBRID APPROACH TO STACK OVERFLOW TAG PREDICTION USING TRANSFORMERS AND KEYWORD EXTRACTION

Community question-answering (CQA) platforms offer new opportunities for users to share knowledge online. Tags are added to data on these platforms to define, classify, and discover the information. Accurate tags help find users to answer the question. However, tags may be inaccurate or improper since users tag questions based on their understanding of the question's content and other tags that are on the site. Existing methods often fail to fully capture the semantic context of questions, especially those containing code snippets, leading to suboptimal tag suggestions. This highlights a gap in the literature for models that can effectively handle both natural language and programming content. To address this issue, we propose a novel deep learning approach combining advanced transformer-based architectures with keyword extraction techniques to understand the context in text and code snippets and produce relevant tags. Our proposed method will be able to suggest relevant and appropriate tags and demonstrate superior performance compared to state-of-the-art techniques, thus contributing new insights into context-aware tag recommendations for CQA systems.