Group Recommender Systems aim to support groups in making collective decisions, and research has consistently shown that the more we understand about group members and their interactions, the better support such systems can provide. In this work, we propose a conceptual framework for modeling group dynamics from group chat interactions, with a particular focus on decision-making scenarios. The framework is designed to support the development of intelligent agents that provide advanced forms of decision support to groups. It consists of modular, loosely coupled components that process and analyze textual and multimedia content, which is shared in group interactions, to extract user preferences, emotional states, interpersonal relationships, and behavioral patterns. By incorporating sentiment analysis, summarization, dialogue state tracking, and conflict resolution profiling, the framework captures both individual and collective aspects of group behavior. Unlike existing approaches, our model is intended to operate dynamically and adaptively during live group interactions, offering a novel foundation for group recommender and decision support systems.

Clustering users on social media based on text involves grouping individuals with similar text patterns, language usage, or content interests. This text-based clustering provides insights into user preferences, enables personalized content recommendations, and facilitates understanding of social networking trends and user engagement. However, traditional text clustering methods rely heavily on language-specific features. This limits their applicability in multilingual media environments where linguistic diversity prevails. In this paper, the problem of clustering users on social networks, specifically focusing on text-based clustering independent of the language in which the text is written, is addressed. A practical methodology is presented, outlining an iterative procedure for clustering based solely on language-independent features such as emojis, hashtags, URLs, text length, and punctuation count. The effectiveness of the language-independent clustering approach is compared with the usual text based clustering approach. Comparison of these results shows that for the used dataset, the proposed clustering method using language independent features gives higher quality results than text clustering.