Email Reply Prediction: A Machine Learning Approach
Email has now become the most-used communication tool in the world and has also become the primary business productivity applications for most organizations and individuals. With the ever increasing popularity of emails, email over-load and prioritization becomes a major problem for many email users. Users spend a lot of time reading, replying and organizing their emails. To help users organize and prioritize their email messages, we propose a new framework; email reply prediction with unsupervised learning. The goal is to provide concise, highly structured and prioritized emails, thus saving the user from browsing through each email one by one and help to save time. In this paper, we discuss the features used to differentiate emails, show promising initial results with unsupervised machine learning model, and outline future directions for this work.
KeywordsEmail reply prediction machine learning email messages interrogative words need reply do not need reply email headers unsupervised learning
Unable to display preview. Download preview PDF.
- Whittaker, S., Sider, C.: Email overload: exploring personal information management of email. In: CHI 1996, pp. 276–283. ACM Press, New York (1996)Google Scholar
- Tyler, J., Tang, J.: When can I expect an email response? A study of rhythms in email usage. In: Proc. of ECSCW 2003, pp. 238–258. Oulu Univ. Press (2003)Google Scholar
- Dredze, M., Blitzer, J., Pereira, F.: Reply Expectation Prediction for Email Management. In: CEAS 2005, 2nd Conference on Email and Anti-Spam, Stanford University, CA (2005)Google Scholar
- Kraut, R.E., Attewell, P.: Media use in a global corporation: Electronic mail and organizational knowledge, in Culture of the Internet, pp. 323–342. Lawrence Erlbaum Associates, Mahwah (1997)Google Scholar
- Sproull, L., Kiesler, S.: Connections: New ways of working in the networked organization. MIT Press, Cambridge (1991)Google Scholar