Leveraging User Comments for Recommendation in E-Commerce

Abstract

Collaborative filtering recommender systems traditionally recommend products to users solely based on the given user-item rating matrix. Two main issues, data sparsity and scalability, have long been concerns. In our previous work, an approach was proposed to address the scalability issue by clustering the products using the content of the user-item rating matrix. However, it still suffers from these concerns. In this paper, we improve the approach by employing user comments to address the issues of data sparsity and scalability. Word2Vec is applied to produce item vectors, one item vector for each product, from the comments made by users on their previously bought goods. Through the user-item rating matrix, the user vectors of all the customers are produced. By clustering, products and users are partitioned into item groups and user groups, respectively. Based on these groups, recommendations to a user can be made. Experimental results show that both the inaccuracy caused by a sparse user-item rating matrix and the inefficiency due to an enormous amount of data can be much alleviated.

Latent based temporal optimization approach for improving the performance of collaborative filtering

“…Summarily, the existing temporal-based approaches have addressed several limitations of recommender systems such as sparsity (Zhang et al, 2020a;Idrissi & Zellou, 2020;Chu et al, 2020), drift issue (Rabiu et al, 2020;Al-Hadi et al, 2017a) and time decay issue (Koren, 2009;Ye & Eskenazi, 2014;Al-Hadi et al, 2018b). Each reviewed approach in this article has one or two research gaps, e.g., learning the personalized features, the drift preferences, and the popularity decay.…”

The Role of e-Commerce: A Systematic Literature Review

“…Other analysis from the variables of efficient system in e-commerce platform significantly enhances the company's probability and volume of export; e-commerce platform enables the company to export various of products to many countries by reducing the cost of market threshold, information and export, while increasing the trading efficiency [11]. By considering to the e-commerce system effectivity, then a system could be built to ease the workers and customers in real online buying, such as price comparison, product's rating, and preferences factor, which is the best offer and information.…”

Peer Review #1 of "Latent based temporal optimization approach for improving the performance of collaborative filtering (v0.1)"

“…Summarily, the existing temporal-based approaches have addressed several limitations of recommender systems such as sparsity (Zhang et al, 2020a;Idrissi and Zellou, 2020;Chu et al, 2020), drift issue (Rabiu et al, 2020;Al-Hadi et al, 2017a) and time decay issue (Koren, 2009;Ye and Eskenazi, 2014;Al-Hadi et al, 2018b). Each reviewed approach in this article has one or two research gaps, e.g., learning the personalized features, the drift preferences, and the popularity decay.…”