An Empirical Study Based on Big Data Analysis to Analyze Social Media Group Sentiment and Its Impact on Consumer Psychology

As social media becomes the core domain of information interaction in the era of big data, the emotional information contained in the vast amount of user-generated content provides an unprecedented data foundation for understanding group psychology and behavioral laws. Based on the intersection of big data engineering and psychology, this study aims to construct a comprehensive analytical framework to explore the law of group mood swings in social media and its predictive effects on consumer psychology and behavior. This study comprehensively uses natural language processing, machine learning and time series analysis to comprehensively calculate and model sentiment in multi-platform social media texts, and constructs a consumer psychology prediction model based on this. Empirical analysis reveals the evolution patterns of group sentiment under the influence of time, event-driven, and social network structures, and confirms the critical role of sentiment traits in predicting consumer behavior. This study not only enriches the theoretical enlightenment of computational psychology and consumer behavior, but also provides data-based decision support and practical paths for enterprise precision marketing, public sentiment governance, and personal consumption decision-making.