AI-Powered Book Discovery: Integrating Semantic Search, Hybrid Recommendation, and Explainable AI in a Full-Stack Platform

Nanditha B M; Mrs. Sowmya V

doi:10.36948/ijfmr.2025.v07i06.59750

AI-Powered Book Discovery: Integrating Semantic Search, Hybrid Recommendation, and Explainable AI in a Full-Stack Platform

Author(s)	Ms. Nanditha B M, Mrs. Sowmya V
Country	India
Abstract	This paper presents the design and implementation of a full-stack, AI-powered online bookstore plat-form that ad dresses key limitations in existing e-commerce systems. Traditional platforms largely de-pend on keyword-based search and basic recommendation engines, which struggle to interpret natural language queries, fail to deliver meaningful personalization, and lack transparency in recommendation generation. The proposed system introduces four major innovations. First, it implements dual search functionality: a baseline keyword search and a semantic search pipeline using Sentence-BERT (SBERT) embeddings with Facebook AI Similarity Search (FAISS), enabling context-aware retrieval. Second, a hybrid recommendation engine integrates collaborative filtering, content similarity, review sentiment, and trending analysis to enhance personalization and diversity. Third, sentiment analysis of user re views, per-formed using transformer-based models, classifies feed back into positive, neutral, or negative categories. These signals strengthen recommendation quality and provide community driven insights. Fourth, explainable AI (XAI) modules generate human-readable justifications for search and recommendation outputs, improving transparency and user trust. The platform is implemented using a modular, service-oriented architecture: a React frontend, Node.js/Express backend, FastAPI-based NLP microservice, and MongoDB database. Com prehensive evaluation demonstrates significant improvements in retrieval accuracy, personalization quality, and explainability compared to keyword-based baselines, while preserving near real time responsiveness. By unifying semantic search, sentiment-aware personalization, and explainable recommendations within a scalable full stack framework, this work contributes a deployable, human-centered solution for intelligent online book discovery
Keywords	Full-Stack Development, Semantic Search, Recommendation System, Explainable AI (XAI), Sentiment Analysis, Natural Language Processing (NLP), SBERT, FAISS, E-Commerce Architecture, Personalized Recommendations.
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 7, Issue 6, November-December 2025
Published On	2025-11-06
DOI	https://doi.org/10.36948/ijfmr.2025.v07i06.59750

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 3 Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

AI-Powered Book Discovery: Integrating Semantic Search, Hybrid Recommendation, and Explainable AI in a Full-Stack Platform

Share this