• Ms. Mugdha Kshirsagar
• Prof. Anagha Chaudhari
• Mr. Rugved Kulkarni
• Mr. Pranav Lad
• Ms. Arya Kale

In the rapidly evolving landscape of e-commerce, personalized product recommendations play a pivotal role in enhancing user engagement and driving sales. This research paper presents a comprehensive study on the integration of collaborative filtering techniques and sentiment analysis to deliver more accurate and effective product recommendations. Leveraging a dataset comprising user interactions and product reviews, our recommendation system employs collaborative filtering algorithms, particularly Singular Value Decomposition (SVD), to analyze user behavior and generate personalized recommendations. Additionally, sentiment analysis is applied to user reviews to capture the underlying sentiment associated with products, providing a deeper understanding of user preferences and opinions. We conducted experiments on real-world datasets, including Amazon Electronics and Retail Rocket, to evaluate the performance of our recommendation system. The results demonstrate the superiority of collaborative filtering, especially SVD, when applied to the Amazon Electronics dataset, showcasing its effectiveness in capturing latent user preferences and providing accurate recommendations. Furthermore, our system incorporates aspect-based sentiment analysis to offer more targeted insights into user sentiment, contributing to the refinement of product recommendations. This research contributes to the advancement of recommendation systems in e-commerce by demonstrating the efficacy of combining collaborative filtering and sentiment analysis techniques for personalized and context-aware product recommendations.

Recommender Systems, Collaborative Filtering, SVD(Singular Value Decomposition), User-Item Interactions, Large Datasets, Personalized Recommendations, Comparative Analysis, Scalability, Efficiency, Real-world Implementation, Challenges and Opportunities, Hybrid Models, RMSE, MAE, Precision, Recall, Mean Log Squared Error, Sentiment Analysis, E-commerce Datasets, Amazon electronics ratings datasets, Rule-based approaches.

"RecommendoMart: Empowering E-commerce with Intelligent Product Recommendations and Sentiment Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 3, page no.f434-f451, March-2024, Available :http://www.jetir.org/papers/JETIR2403555.pdf

"RecommendoMart: Empowering E-commerce with Intelligent Product Recommendations and Sentiment Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 3, page no. ppf434-f451, March-2024, Available at : http://www.jetir.org/papers/JETIR2403555.pdf