Conference Proceeding Article
Social media provides a convenient way for customers to express their feedback to companies. Identifying different types of customers based on their feedback behavior can help companies to maintain their customers. In this paper, we use a machine learning approach to predict a customer’s feedback behavior based on her first feedback tweet. First, we identify a few categories of customers based on their feedback frequency and the sentiment of the feedback. We identify three main categories: spiteful, one-off, and kind. Next, we build a model to predict the category of a customer given her first feedback. We use profile and content features extracted from Twitter. We experiment with different algorithms to create a prediction model. Our study shows that the model is able to predict different types of customers and perform better than a baseline approach in terms of precision, recall, and F-measure. © Springer International Publishing AG 2016.
Customer relationship management, Machine learning, Social media
Communication | Social Media
Software and Cyber-Physical Systems
Proceedings of 8th International Conference on Social Informatics (SocInfo 2016): Seattle, USA,
City or Country
SULISTYA, Agus; SHARMA, Abhishek; and David LO.
Spiteful, one-off, and kind: Predicting customer feedback behavior on Twitter. (2016). Proceedings of 8th International Conference on Social Informatics (SocInfo 2016): Seattle, USA,. 10047, 368-381. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/3614