Enhancing User Experience with Topic-Based Message Retrieval in Telegram

As reliance on social media and messaging platforms grows, users face increasing challenges in managing and retrieving relevant information. These difficulties often stem from platform designs that prioritize seamless communication over efficient content organization. Given the large volume of messages users receive daily across multiple groups, current research is being conducted to develop systems that can effectively detect emerging conversations about topics of interest. This work proposes a novel approach to enhancing the user experience in Telegram by developing a topic-based identification of new conversations. A two-step approach is employed. First, a conversation model identifies whether a message begins a new conversation. Then, a topic model assigns topics to the conversations based on user preferences. The system was validated using real-world data collected from university-related Telegram groups with six recurring topics including exams, homework, and deadlines. While the model effectively identifies new conversations and relevant topics (F1 score of 0.94%, macro F1 score of 0.68%), it primarily addresses a limited set of topics. For real-world applicability, the system would need to handle a broader range of dynamic, context-dependent topics, which is beyond the scope of this work. The proposed method provides a lightweight, adaptable solution for enhancing message management and user engagement across messaging platforms.