A Data-Driven Approach to Habit Prediction: Computational Modeling and Emotion Analytics

This paper introduces a computational model for gathering data from diverse sources to improve both group and individual communication by integrating visual and audio inputs, emotional sensitivity metrics, and performance evaluations. The ET model analyzes complex data patterns and draws insights into the emotional response using emotional level tokens. The proposed approach will help organizations develop decision-support software to integrate human-data interaction into business processes, which in turn accelerates decision-making and offers a competitive advantage by using emotional analysis to produce actionable business knowledge.