Over the past several years, the study of linguistic and social dynamics in online communities has garnered significant attention across multiple disciplines. Research has demonstrated that understanding social behaviors, discourse patterns, and language use in digital spaces can offer valuable insights into a wide range of real-world problems, including hate speech detection, health literacy improvement, and misinformation spread. This research is crucial in areas such as online community health communication, social media analysis, and sentiment classification. The Linguistic and Social Dynamics in Online Communities (AISOC ) Special Session at the 16th International Conference on Computational Collective Intelligence (ICCCI 2025) will focus on methods and models that address classification, prediction, and clustering challenges in the context of social media data, health literacy, and hate speech detection. We aim to provide a platform for researchers and practitioners to explore emerging research directions and present recent advancements in these interdisciplinary fields.
The scope of the session includes, but is not limited to, the following topics:
- Theoretical frameworks for linguistic and social dynamics in online communities
- Machine learning algorithms for text classification, sentiment analysis, and hate speech detection
- Ensemble methods for toxicity detection and hate speech in social media data
- Opinion mining and sentiment analysis in online communities
- Analyzing and improving health literacy through computational models
- Data processing techniques for Big Data and small data sets in social media and health-related research
- Subsampling, feature extraction, and selection for toxicity and hate speech detection
- Diversity, accuracy, interpretability, and fairness in social media data analysis
- Homogeneous and heterogeneous models for detecting toxic behavior and harmful content
- Hybrid models for predicting public sentiment, toxicity, and health outcomes from social media data
- Incremental, evolving, and online learning for real-time analysis of social media content
- Mining data streams in health communication, toxicity detection, and opinion mining
- Ensemble methods for dealing with concept drift in social media toxicity and sentiment data
- Multi-objective learning in online community health research, hate speech, and opinion mining
- Applications of ensemble learning in online community management, hate speech mitigation, and mental health advocacy
- Model implementations and computational tools for analyzing toxicity, sentiment, and social dynamics
- Statistical analysis and performance evaluation of models in online community research, health literacy, and opinion mining
- Applications in public health, mental health, misinformation detection, and online community management
