Personalized Book Recommendations Driven by Emotional Analysis with NLP
Horesh Kumar, A Sivanesan, P A Afsal, M S Don, V P Aneena, R Rudresh · 2025
In today's digital era, the enhanced dissemination of literary text information at a quick pace demands the development of effective summarization and recommendation techniques. The primary issue is the unavailability of proper efficient summarization techniques for long texts, coupled with the need for personalized book recommendations in terms of content and emotional context. The solution used is an automated system based on Natural Language Processing (NLP) techniques to summarize literary works while employing a hybrid book recommendation system concurrently. The primary goal is to create brief summaries and offer personalized, emotion-sensitive book recommendations to maximize reader receptiveness. The used framework employs both extractive and abstractive summarization techniques, sentiment analysis, feature extraction, and a hybrid recommendation model that combines collaborative filtering and content-based filtering. The novelty of this work is the integration of emotion-based filtering with traditional recommendation techniques, thereby offering users emotionally harmonious and highly relevant book recommendations for both experienced and novice users.