Leveraging User Comments for Recommendation in E-Commerce

Pang-Ming Chu,Yu-Shun Mao,Chun-Liang Hou,Shie-Jue Lee

doi:10.3390/app10072540

Pang-Ming Chu, Yu-Shun Mao + Show 2 more

Open Access

https://doi.org/10.3390/app10072540

Copy DOI

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.

Highlights

Recommender systems [1,2,3] are able to analyze the past behavior of customers and recommend the products in which they might be interested
We call our approach CFUCC (Collaborative Filtering based on User Comments and Clustering) in the remainder of this section
This is the method that CFUCC adopts. It applies Word2Vec on user comments to get item vectors from which user vectors are obtained, and clusters products and users based on the item and user vectors

Summary

Introduction

Recommender systems [1,2,3] are able to analyze the past behavior of customers and recommend the products in which they might be interested. Recommender systems can roughly be categorized into two types: collaborative filtering and content-based filtering. Content-based filtering [4,5,6] assumes that customers will buy things that are similar to what they have bought in the past. Detailed information about products and users are required for recommendations. The information needed is growing harder to get in the modern age of privacy awareness. Collaborative filtering [7,8,9,10,11,12,13,14,15,16,17]

Methods

Results

Conclusion