An Ai-Based Real-Time Cognitive Attention Drift Detection and Productivity Risk Prediction System For Students

  • Unique Paper ID: 194924
  • Volume: 12
  • Issue: 10
  • PageNo: 6783-6789
  • Abstract:
  • The growing challenge of maintaining cognitive focus during self-directed study has become a critical concern in modern education. Students frequently experience attention drift that goes undetected until it significantly impacts academic performance. Existing monitoring tools rely on invasive hardware such as EEG headsets or cameras. This paper proposes a tri-modal, non-invasive AI-based system that monitors student cognitive attention in real time using behavioral monitoring, speech sentiment analysis, and text sentiment analysis. The system passively tracks keyboard typing speed, idle time, and window switching every 60 seconds and computes deviations from a personal baseline calibrated over three sessions. An ensemble AI model combining Isolation Forest and Random Forest achieved 100% accuracy, with focused sessions averaging 88.13 compared to 2.26 for heavy drift sessions. A context-awareness layer distinguishes Normal Work, Reading and Watching, and Active Learning states. Results are displayed on a Flask-based web dashboard with live focus scores, trend visualization, oral assessment, and session history export.

Copyright & License

Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

BibTeX

@article{194924,
        author = {S.KAMALINI and K.MANIRAJ},
        title = {An Ai-Based Real-Time Cognitive Attention Drift Detection and Productivity Risk Prediction System For Students},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {6783-6789},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194924},
        abstract = {The growing challenge of maintaining cognitive focus during self-directed study has become a critical concern in modern education. Students frequently experience attention drift that goes undetected until it significantly impacts academic performance. Existing monitoring tools rely on invasive hardware such as EEG headsets or cameras. This paper proposes a tri-modal, non-invasive AI-based system that monitors student cognitive attention in real time using behavioral monitoring, speech sentiment analysis, and text sentiment analysis. The system passively tracks keyboard typing speed, idle time, and window switching every 60 seconds and computes deviations from a personal baseline calibrated over three sessions. An ensemble AI model combining Isolation Forest and Random Forest achieved 100% accuracy, with focused sessions averaging 88.13 compared to 2.26 for heavy drift sessions. A context-awareness layer distinguishes Normal Work, Reading and Watching, and Active Learning states. Results are displayed on a Flask-based web dashboard with live focus scores, trend visualization, oral assessment, and session history export.},
        keywords = {Cognitive Attention Monitoring, Attention Drift Detection, Behavioral Signal Analysis, Sentiment Analysis, Ensemble Learning, Isolation Forest, Random Forest, Flask Dashboard, Web Speech API, VADER.},
        month = {March},
        }

Cite This Article

S.KAMALINI, , & K.MANIRAJ, (2026). An Ai-Based Real-Time Cognitive Attention Drift Detection and Productivity Risk Prediction System For Students. International Journal of Innovative Research in Technology (IJIRT), 12(10), 6783–6789.

Related Articles