Improved Feature-Specific Collaborative Filtering Model for the Aspect-Opinion Based Product Recommendation
Utilizing the benefits of Internet services for the online purchase and online advertising has increased tremendously in the recent year. Therefore, the customer reviews of the product play a major role in the product sale and effectively describe the features quality. Thus, the large size of words and phrases in an unstructured data is converted into numerical values based on the opinion prediction rule. This paper proposes the Novel Product Recommendation Framework (NPRF) for the prediction of overall opinion and estimates the rating of the product based on the user reviews. Initially, preprocessing the set of large size customer reviews to extract the relevant keywords with the help of stop word removal, PoS tagger, Slicing, and the normalization processes. SentiWordNet library database is applied to categorize the keywords which are in the form of positive and negative based polarity. After extracting the related keywords, the Inclusive Similarity-based Clustering (ISC) method is performed to cluster the user reviews based on the positive and negative polarity. The proposed Improved Feature-Specific Collaborative Filtering (IFSCF) model for the feature-specific clusters is used to evaluate the product strength and weakness and predict the corresponding aspects and its opinions. If the user query is matched with the cache memory then shows the opinion or else extract from the knowledge database. This optimal memory access process is termed as the Memory Management Model (MMM). Then, the overall opinion of the products is determined based on the Novel Product Feature-based Opinion Score Estimation (NPF-OSE) process. Finally, the top quality query result and the recommended solution are retrieved. Thus the devised NPRF method enriches its capability in outperforming other prevailing methodologies in terms of precision, recall, F-measure, RMSE, and the MAE.
KeywordsCustomer reviews SentiWordNet Collaborative filtering Aspects Opinions Clustering Memory management model
- 2.Sivapalan, S., Sadeghian, A., Rahnama, H., Madni, A.M.: Recommender systems in e-commerce. In: World Automation Congress (WAC), pp. 179–184. IEEE (2014)Google Scholar
- 12.Opinion Mining, Sentiment Analysis, and Opinion Spam Detection (May 15, 2004). https://www.cs.uic.edu/~liub/FBS/sentiment-analysis.html
- 13.Sangeetha, J., Prakash, V.S.J., Bhuvaneswari, A.: Dual access cache memory management recommendation model based on user reviews. IJCSRCSEIT 169–179 (2017)Google Scholar
- 14.Zheng, L., Noroozi, V., Yu, P.S.: Joint deep modeling of users and items using reviews for recommendation. In: Proceedings of the Tenth ACM International Conference on Web Search and Data Mining, pp. 425–434. ACM (2017)Google Scholar
- 15.Ren, Z., Liang, S., Li, P., Wang, S., de Rijke, M.: Social collaborative viewpoint regression with explainable recommendations. In: Proceedings of the Tenth ACM International Conference on Web Search and Data Mining, pp 485–494. ACM (2017)Google Scholar