How Service-Related Factors Affect the Survival of B2T Providers: A Sentiment Analysis Approach

ABSTRACT

Nearly one-third of the business-to-team (B2T) websites in China closed down in 2011—the casualties of the intensified competition in the group-buying market. To investigate the critical factors to the survival of online B2T businesses in an overcrowded buyer-side market, we propose a model that links convenience, price, product/service, personalization, and website security/safety to customer satisfaction of B2T websites in light of the related literature. A two-stage approach is applied to validate this model. In Stage I, according to the results of an empirical analysis based on questionnaire responses from 157 B2T website users, we found that convenience and product/service are the top two contributors to the success of B2T business, as measured by customers’ repurchase intentions. In Stage II, topic classification and sentiment analysis are applied to 3046 review comments related to 58 B2T websites. The results from the Stage II study confirm the validity of the Stage I results with further evidence to support our arguments.

Keywords:

• B2T business
• customer repurchase intention
• customer satisfaction
• online group buying
• sentiment analysis

Notes

¹ According to a recent survey on the characteristics of online group-buying users conducted by iResearch (China Online Group Shopping Analysis Report 2010; http://www.iresearch.cn), male users accounted for 47.2% and female users accounted for 52.8% of users of Chinese B2T websites, and more than 85% of such users are between 20 and 30 years of age.

² Sentence tokenization describes the process of breaking a piece of text into individual sentences.

³ Both True positive and True negative mean the correct outcomes, false positive represent the Type I error and False negative means Type II error. In quinary classification, we calculate the precision/recall for each dimension then take the average to get the precision/ recall for quinary classifier.

⁴ We gathered the performance status (living or dead) of all 58 B2T websites, associated with the current market share. We rescaled the data by normalizing all market shares in the range [0, 1], in which those with a score of 0 are considered dead ones.

Additional information

Funding

The research is supported in part by the National Natural Science Foundation of China (NSFC Program No.71072037) and Shanghai Pujiang Program.

Notes on contributors

Ranzhe Jing

Ranzhe Jing received MBA and PhD (Management Science & Engineering) degrees from Xi’an Jiaotong University. He held a postdoctoral position at Tsinghua University from 2007 to 2009, and worked as a visiting scholar and research fellow in the University of Pittsburgh from 2012 to 2013. Since 2009, Dr. Jing has been an associate professor in the School of Information Management and Engineering at the Shanghai University of Finance and Economics. He is a principal investigator of The National High Technology Research and Development Program of China (863 Program) and National Natural Science Foundation of China (NSFC Program). He is also a committee member of China High-tech Industrialization Association. He has published more than 30 papers in several journals and two books. His recent research interests include customer value analysis, e-service, and online financial services.

Yang Yu

Yang Yu is an assistant professor of Management Information Systems in the Saunders College of Business at Rochester Institute of Technology. In 2013, he received his PhD in MIS from Texas Tech University. He also earned another PhD in Management Science from Beijing University of Aeronautics and Astronautics. Yang’s research interests include big data (social media), business intelligence, and e-commerce. He has published papers in such journals as Decision Support Systems, Communications of the ACM, Computers in Human Behavior, and so forth.

Zhangxi Lin

Zhangxi Lin received a Master’s degree in Computer Applications from Tsinghua University in 1982, a second Master’s degree in Economics from the University of Texas at Austin in 1996, and a PhD in Information Systems in 1999 from the University of Texas at Austin. He has been a member of IEEE, INFORMS, and AIS for many years. He is currently a tenured professor at the Rawls College of Business Administration, and the co-director of Center for Advanced Analytics and Business Intelligence, at Texas Tech University. Dr. Lin has been actively involved in research and education in China. His research interests cover a broad range of areas, including e-commerce, business analytics, online service pricing, targeted advertising, Internet finance, and knowledge-based systems. He has published more than 200 peer-reviewed papers in international journals and conferences, such as European Journal of Operation Research, Decision Support Systems, Information Systems Research, Expert Systems with Applications, Information Sciences, Information Systems and E-Business Management, ICIS, ICDM, AAAI, and so on.