SmartTips: Online Products Recommendations System Based on Analyzing Customers Reviews

Abstract

Online customers’ opinions represent a significant resource for both customers and enterprises to extract much information that helps them make the right decision. Finding relevant data while searching the internet is a big challenge for web users, known as the “Problem of Information Overload”. Recommender systems have been recognized as a promising way of solving such problems. In this paper, a product recommendation system called “SmartTips” is introduced. The proposed model is built based on aspect-based sentiment analysis, which exploits customers’ feedback and applies the aspect term extraction model to rate various products and extract user preferences as well. Several factors were considered, including readers’ votes, aspect term frequency, opinion words’ frequencies, etc. We tested our model on benchmark datasets that are widely used, and the results show that it outperforms the baseline methods regarding the mean squared errors of generated predictions.

CredibleExpertRank: Leveraging Social Network Analysis and Opinion Mining to Facilitate Reliable Information Retrieval on Knowledge-Sharing Sites

“…Venkata et al [28] developed a web-based system utilizing natural language processing to extract and present customer reviews in a graphical format, making it easier for users to make informed purchasing decisions. In another work, Noahman et al [6] proposed a model called ''SmartTips'' which leveraged an aspect-based sentiment analysis to evaluate different products based on customer feedback and extract user preferences.…”

“…Therefore, to calculate the user's ''credibility score,'' we analyze the constructed Questioner-Answerer-Recommender (QAR) network using SNA [36], [37], [38]. Then, we combine opinion mining to identify experts, ultimately improving the accuracy of the credibility score [4], [5], [6], [28].…”

“…Based on usage and satisfaction theory, Loc et al [5] explained how to utilize online reviews for making purchasing decisions online. ''SmartTips'' [6] was built on an aspect-based sentiment analysis. It leverages customer feedback and applies aspect term extraction models to rate different products and extract user preferences.…”