An Experimental Study of Text Representation Methods forCross-Site Purchase Preference Prediction Using the Social Text Data

• Published in: 计算机科学技术学报：英文版 Vol. 32; no. 4; pp. 828 - 842
• Main Author: Ting Bai Hong-Jian Dou Xin Zhao Ding-Yi Yang Ji-Rong Wen
• Format: Journal Article
• Language: English
• Published: 2017
• Subjects: deep; e-commerce; media; network; neural; preference; purchase; social; website
• ISSN: 1000-9000; 1860-4749

Nowadays, many e-commerce websites allow users to login with their existing social networking accounts.When a new user comes to an e-commerce website, it is interesting to study whether the information from external socialmedia platforms can be utilized to alleviate the cold-start problem. In this paper, we focus on a specific task on cross-siteinformation sharing, i.e., leveraging the text posted by a user on the social media platform （termed as social text） to inferhis/her purchase preference of product categories on an e-commerce platform. To solve the task, a key problem is how toeffectively represent the social text in a way that its information call be utilized on the ecommerce platform. We studytwo major kinds of text representation methods for predicting cross-site purchase preference, including shallow textualfeatures and deep textual features learned by deep neural network models. We conduct extensive experiments on a largelinked dataset, and our experimental results indicate that it is promising to utilize the social text for predicting purchasepreference. Specially, the deep neural network approach has shown a more powerful predictive ability when the number ofcategories becomes large.