AI Ed Wiki logoAI Ed Wiki
Use with AI

📄 Research Article

Artificial Intelligence and Student Engagement in Online Learning: A Literature Review

● high · 2026-08-20 · online-education, online-learning, student-engagement, literature-review, chatbots, affective-computing, learning-analytics, higher-ed

Synthesis: Zhou (2025) systematically reviews 24 studies from the Web of Science database on how AI enhances student engagement in online learning. Six key applications emerge: AI chatbots in course design, emotion/facial/voice recognition and eye tracking, machine learning for data analysis, teacher–student interaction support, personalized feedback and recommendations, and AI-powered bots in smart learning environments. Findings show that integrating diverse AI tools and data sources yields more accurate, real-time insight into cognitive, emotional, and behavioral engagement — while limitations include the single-database scope, the conflation of synchronous and asynchronous contexts, and an engagement-only focus.

Key Findings

  • Six AI applications support engagement. The review classifies AI use into: (1) AI chatbots integrated into online course design, (2) emotion, facial, voice recognition and eye tracking, (3) machine learning for data analysis, (4) teacher–student interaction support, (5) personalized Feedback and recommendations, and (6) AI-powered bots in smart learning environments.
  • Chatbots foster engagement through timely, personalized support. AI-powered chatbots are effective across learning domains and stages — delivering course information, interactive practice, and information retrieval — with comparative analyses finding them especially effective when deployed for personalized, on-demand assistance.
  • Affective and behavioral monitoring. Emotion recognition, facial and voice tracking, and eye tracking enable real-time assessment of behavioral, emotional, and cognitive engagement — recognizing states from boredom and confusion to interest and enjoyment using facial expressions, physiological signals, and voice data.^Affective Computing
  • Common data sources and measurement. Studies rely on video recordings, activity logs, standardized datasets, and surveys; engagement is typically measured through multi-method approaches combining surveys, AI recognition, and coded activity data.
  • Integration improves insight. Combining diverse AI tools and data sources provides more accurate, real-time insight into students' cognitive, emotional, and behavioral engagement than single-source approaches.

Study Design & Method

A systematic literature review of 24 peer-reviewed studies retrieved from the Web of Science database. The review synthesized how AI has been implemented to foster student engagement in fully online learning (excluding blended and flipped contexts), classifying applications and examining the data resources and measurement approaches used. Engagement is treated as a multi-dimensional construct spanning behavioral participation, emotional investment, and cognitive involvement.

Implications for AI in Education

In online learning, where autonomy and self-regulation demands make sustained engagement harder than in person, AI offers real-time monitoring, personalized feedback, and interactive tools to support engagement. For designers, the review recommends integrating multiple AI modalities and data sources rather than relying on a single signal, and measuring engagement across cognitive, emotional, and behavioral dimensions. Future work should examine real-time interventions, long-term impacts, ethical considerations, and the differences between synchronous and asynchronous online learning.

Connected Concepts

Connected Articles

Citation

Zhou, Z. (2025). Artificial intelligence and student engagement in online learning: a literature review. American Journal of Distance Education. Advance online publication.