Hybrid Collaborative fusion based product recommendation exploiting sentiments from implicit and explicit reviews

Zafar Ali Khan N, R Mahalakshmi

Page No: 92-104

DOI: 10.86493/VEREDAS.2023/V13I9/10

Product recommendation is an important feature of online shopping. The goal of the recommendation system is to recommend products with higher accuracy such that purchase success ratio are increased. User profile, product purchase history etc have been used to provide high quality recommendations. Product reviews is one of the important source for personalized recommendation. Typical collaborative recommendation systems are built upon user rating on products. But in many cases, these rating information are inaccurate or not available. There is also a problem of biased reviews which decreases the accuracy of recommendation systems. This work proposes a collaborative fusion based recommendation system mining the aspects information in the implicit and explicit reviews. The sentiments about different aspects in the reviews are translated to multi dimensional aspect ratings and these ratings information is fused with user profile and demographic attributes to provide high quality of recommendation. The proposed recommendation system has 3.79% lower RMSE, 4.51% lower MAE and 22% lower MRE compared to most recent collaborative filtering based recommendation system.

Citations

APA: Zafar Ali Khan N, R Mahalakshmi (2025). Hybrid Collaborative fusion based product recommendation exploiting sentiments from implicit and explicit reviews. DOI: 10.86493/VEREDAS.2023/V13I9/10

AMA: Zafar Ali Khan N, R Mahalakshmi. Hybrid Collaborative fusion based product recommendation exploiting sentiments from implicit and explicit reviews. 2025. DOI: 10.86493/VEREDAS.2023/V13I9/10

Chicago: Zafar Ali Khan N, R Mahalakshmi. "Hybrid Collaborative fusion based product recommendation exploiting sentiments from implicit and explicit reviews." Published 2025. DOI: 10.86493/VEREDAS.2023/V13I9/10

IEEE: Zafar Ali Khan N, R Mahalakshmi, "Hybrid Collaborative fusion based product recommendation exploiting sentiments from implicit and explicit reviews," 2025, DOI: 10.86493/VEREDAS.2023/V13I9/10

ISNAD: Zafar Ali Khan N, R Mahalakshmi. "Hybrid Collaborative fusion based product recommendation exploiting sentiments from implicit and explicit reviews." DOI: 10.86493/VEREDAS.2023/V13I9/10

MLA: Zafar Ali Khan N, R Mahalakshmi. "Hybrid Collaborative fusion based product recommendation exploiting sentiments from implicit and explicit reviews." 2025, DOI: 10.86493/VEREDAS.2023/V13I9/10