Enhancing group-based emotional intelligence in children through an adaptive activity system driven by artificial intelligence

Emotional intelligence (EI) is a crucial skill set because it impacts the social interactions, decision making ability and general well-being of the kids. This study focuses on the creation of adaptive activity generator which aims to improve the emotional intelligence of kids between the ages of 4 to 12 years. The responses from Strengths and Difficulties Questionnaire (SDQ) are used to identify the weak emotional intelligence dimensions. In order to dynamically create customized activities that are according to the child’s developmental stage and particular EI problems, it makes use of a Large Language Model (LLM). The system also forms groups of children who share the same weak emotional intelligence (EI) dimension and belong to the same age group, in order to promote collaborative learning and teamwork. Activities are divided into three difficulty levels (low, medium, and high) and focus on specific emotional intelligence (EI) skills, such as self-awareness, empathy, motivation, self-regulation, and social skills. Using hierarchical clustering, clustering analysis produced four unique groupings based on similar behavioral and emotional traits. Most participants showed overall improvement, while a smaller group required further development in certain EI dimensions. The results suggest that the adaptive activity generator is an effective tool for enhancing emotional intelligence in children. A paired T-test confirmed a statistically significant decrease in weak dimensions after the intervention demonstrating the effectiveness of the adaptive activity generator. This approach seeks to fill gaps in current educational practices by offering parents, teachers, and psychologists a scalable and interactive way to support children’s emotional development.