Harnessing Emotionally Adaptive AI to Boost Academic Motivation and Combat Dropout Rates in Virtual Learning Environments
Year: 2025
Type: article
Study design: Observational Study
Abstract: This quantitative research explored the effect of emotionally adaptive AI interventions on students' academic motivation and dropout prevention who were involved in virtual learning environments in Pakistan. Following a descriptive research approach and simple random sampling, 150 students' data were collected with the help of a structured Likert-scale questionnaire. Statistical procedures such as regression, multiple regression, and ANOVA were used to analyze the relationship between AI-based emotional support, motivation, and dropouts. The results validated the presence of strong positive correlation between emotional adaptive AI and motivational academicity (H1), where AI intervention was strongly predictive of high levels of motivation. Multi-regression analysis (H2) also revealed that AI intervention has significant impact on student engagement by acting in the role of a moderator for emotional experience with demographic variables mediating in the above dynamic. ANOVA findings (H3) of statistically significant variation in dropout rates between academic level and region indicate contextual factors influencing AI effectiveness. The findings suggest that emotionally intelligent AI can motivate, enhance emotion and memory and help students learn more in virtual classrooms. The report stresses that combining cultural and psychological elements into AI on online learning must be done to encourage better student engagement and lower attrition. The findings mean that educational institutions ought to enhance their virtual learning environment by using AI-powered emotional support services for students. It is recommended that future researchers analyze the continuous effects and international use of emotionally adaptive AI in schools.
DOI: 10.59075/hsaqxf40
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: hybrid
OpenAlex ID: W4410780791