AI-Powered Personalized Learning Platform: NLP-Driven Article-Centric Chatbot with Sentiment Analysis

Overview

Most AI learning tools answer from a giant pre-trained knowledge base, which means they hallucinate, drift off-topic, and can't be controlled. This IEEE-published system takes a different approach: upload any article, and the chatbot answers only from that content. Built with NLP, TF-IDF vectorisation, cosine similarity, and an SVM-based sentiment classifier, the platform achieved 90% question-answering accuracy and 90.84% precision, with zero reliance on large language models. Designed specifically for educational environments where transparency and controlled knowledge sources matter.

About This Research

The core problem with most AI-powered learning tools is that they don't know what they don't know. General-purpose chatbots hallucinate answers, pull from stale or irrelevant knowledge, and give students no way to verify where the information came from. In educational settings — where accuracy and source transparency are non-negotiable — this is a serious problem.

This system solves it with a strict constraint: the chatbot can only answer from the article the user uploads. Nothing else. No pre-trained knowledge base, no external retrieval. If it's not in the document, it doesn't answer.

The technical architecture is deliberately lightweight and interpretable — a deliberate choice over heavier transformer-based models:

— Text is tokenised and normalised (lowercase, stopword removal, stemming/lemmatisation) — Queries and article content are vectorised using TF-IDF — Semantic relevance is measured via cosine similarity to find the most relevant passage — An SVM classifier runs sentiment analysis on content tone in parallel

This design avoids the hallucination problem entirely. Responses are bounded by the source material, making the system fully auditable and trustworthy for classroom use.

The chatbot also provides relevant image links alongside text responses — a multimodal learning feature that improves engagement without adding computational overhead.

The key insight behind this work: for educational applications, a lightweight, interpretable, document-bounded system consistently outperforms over-engineered solutions. Students and teachers need to trust the source. This system makes that possible.

Published at the 2026 International Conference on Next-Gen Quantum and Advanced Computing (NQComp), IEEE.