Horizon CDT Research Highlights

Research Highlights

SNS Data Mining and Feature Design for E-commerce Platform Optimisation

  Weiqiang Lin (2015 cohort)   www.nottingham.ac.uk/~psxwl9

Online shopping has developed rapidly over the past couple of decades and gradually became a mainstream shopping experience. The implemented shopping platforms are continuously optimized by the platform providers, using various means to provide more effective operations and interactions between the buying customers and the vendors who are selling their products. My PhD typically observes three main stakeholders in online shopping environments: the customers (i.e., buyers of goods), providers of products (manufacturiers or distributeurs), and the shopping platform that enables the value exchange between the two.

My PhD research will be conducted in close collaboration with one of the largest online shopping company in China — JD.com. The objective of the research is to explore how analysis of product reviews, combined with the analysis of content on Social Network Services (SNS) could increase the value of the shopping platform (SP). Specifically, we want to explore how the presentation of information from reviews can

  • Help consumers make better decisions about their purchases
  • Help manufacturers improve their products and market targeting. Those shopping platforms that provide assistance to buyers and sellers are expected to gain trust and popularity. Thus, we aim to conduct research to explore opportunities for innovative services. In particular we will
  • Take into account the inter-relationship between customers, product providers, and the shopping platform
  • Exploit diverse information within the platform (the product descriptions, the marketing material, and the user reviews) and integrate alternative resources (professional reviews, product announcements, and social network opinions) Design, implement, and evaluate services that increase the value to all the parties in the ecosystem: the informed decision by consumers, the improved products by the manufacturers, and the increased sales on the shopping platform.


  1. M. Hu and B. Liu, “Mining and summarizing customer reviews,” Proc. 2004 ACM SIGKDD Int. Conf. Knowl. Discov. data Min. KDD 04, vol. 04, p. 168, 2004.
  2. M. Hu and B. Liu, “Mining Opinion Features in Customer Reviews,” 19th Natl. Conf. Artifical Intell., pp. 755–760, 2004.
  3. A. F. Tavana, S. Fili, A. Tohidy, R. Vaghari, and S. Kakouie, “Theoretical Models of Customer Relationship Management in Organizations,” Int. J. Bus. Behav. Sci., vol. 3, no. 11, pp. 63–70, 2013.
  4. B. Liu, W. Hsu, Y. Ma, and B. Ma, “Integrating Classification and Association Rule Mining,” Knowl. Discov. Data Min., pp. 80–86, 1998.
  5. A. M. Popescu and O. Etzioni, “Extracting product features and opinions from reviews,” in Natural Language Processing and Text Mining, 2007, pp. 9–28.
  6. V. Hatzivassiloglou and K. R. McKeown, “Predicting the semantic orientation of adjectives,” Proc. eighth Conf. Eur. chapter Assoc. Comput. Linguist. -, pp. 174–181, 1997.
  7. P. D. Turney, “Thumbs up or thumbs down? Semantic Orientation applied to Unsupervised Classification of Reviews,” Proc. 40th Annu. Meet. Assoc. Comput. Linguist., no. July, pp. 417–424, 2002.
  8. B. Pang, L. Lee, and S. Vaithyanathan, “Thumbs up?: sentiment classification using machine learning techniques,” Proc. ACL-02 Conf. Empir. methods Nat. Lang. Process. - EMNLP ’02, vol. 10, no. July, pp. 79–86, 2002.
  9. R. McKerlich, C. Ives, and R. McGreal, “Sentiment Strength Detection for the Social Web,” Int. Rev. Res. Open Distance Learn., vol. 14, no. 4, pp. 90–103, 2013.

This work was carried out at the International Doctoral Innovation Centre (IDIC). The authors acknowledge the financial support from Ningbo Education Bureau, Ningbo Science and Technology Bureau, China's MOST, the University of Nottingham, and JD. The work is also partially supported by EPSRC grant no EP/L015463/1.