• JAKKAMSETTI KEERTHI
• V.SARALA

In current days the collaborative filtering combined with various kinds of deep learning models is considered as the best model for recommendations for getting strong positive results. A lot of users still try to ignore these reviews due to the limitations that are present in the recommendation model. Also in the current recommendation model all the social reviews may not generate the accuracy and following ratio compared with similar category products. Here we try to collect the opinion on products based on rating prediction method by making the use of social users’ sentiment to infer ratings. First, we extract product features from user reviews. Then, we find out the sentiment words, which are used to describe the product features. Here the admin will add a set of pre-defined words which comes under three categories and based on the matching of words from the database, the review was classified in one of the three categories. In this proposed work there is a method to get the comparative report for K-nearest Neighborhood between set of same category products.

Online Social Networks, Deep Learning, Social Reviews, Recommendation Systems, Users’ Sentiment, Rating Prediction.

"Clustering Based Collaborative Filtering Using and Incentivized Penalizing Model", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 6, page no.g317-g323, June-2021, Available :http://www.jetir.org/papers/JETIR2106866.pdf

"Clustering Based Collaborative Filtering Using and Incentivized Penalizing Model", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 6, page no. ppg317-g323, June-2021, Available at : http://www.jetir.org/papers/JETIR2106866.pdf