Learnova – ML Powered Smart Learning System

DOI

10.2991/978-94-6239-707-1_9How to use a DOI?

Keywords

Machine Learning; Natural Language Processing (NLP); OCR; Topic Modelling; Keyword Extraction; TextRank; Educational Data Mining; PYQ Analysis; Intelligent Learning Systems

Abstract

Students often struggle to prioritize concepts during exam preparation due to the lack of structured insights from Previous Years’ Question Papers (PYQs), which remain one of the most valuable yet underutilized academic resources. We have proposed Machine Learning (ML)- powered smart PYQ analyser system designed to help college students to identify high-weightage and frequently asked topics by analysing Previous Years’ Question Papers. Learnova (name given to our proposed solution) automates this entire process by extracting questions from scanned or digital PYQ documents using a pre-trained CNN-based Optical Character Recognition (OCR) model. The extracted text is processed through advanced Natural Language Processing (NLP) pipelines, where keyword extraction, topic identification and frequency computation are performed using techniques such as RAKE and TextRank. Additionally, a Sentence-BERT (SBERT) model is trained to generate semantic embeddings, enabling accurate semantic clustering of conceptually similar topics. After clustering, frequency mapping is applied to quantify topic recurrence across multiple question papers. Finally, the system ranks and displays the top ten high-weightage topics that are most likely to reappear in future examinations. By converting unstructured question papers into data-driven insights, Learnova enables efficient revision, reduces manual analysis time from several hours to just 40 seconds and enhances exam preparedness. Comparative analysis shows that the proposed system achieves 86% accuracy, significantly outperforming traditional manual methods and basic keyword-search systems in both precision and processing speed.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Pragati Thawkar
AU  - Mendu Vaishnavi
AU  - Mittapalli Aneesha
AU  - Saurav Dabhade
AU  - Shrikant Salve
PY  - 2026
DA  - 2026/06/18
TI  - Learnova – ML Powered Smart Learning System
BT  - Proceedings of the International Conference on Recent Advances in Intelligent and Sustainable Technologies (RAIST 2026)
PB  - Atlantis Press
SP  - 100
EP  - 109
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-707-1_9
DO  - 10.2991/978-94-6239-707-1_9
ID  - Thawkar2026
ER  -