Accepted Papers |
Day of Workshop |
Workshop Notes |
Call for Participation |
Sentiment Analysis on Personal Email Archives
Sudheendra Hangal, Monica S. Lam
A significant portion of a user’s digital past is recorded in the form of email messages, SMS texts, tweets, status up- dates and blog posts. We view this personal text archive as a personal informatics system that captures deep and meaningful information for the user. However, it is a challenge to efficiently browse and extract useful infor- mation from an unstructured text corpus spanning tens of thousands of entries accumulated over many years. We propose the use of sentiment analysis techniques on users’ personal text archives to aid in the task of per- sonal reflection and analysis . We have built and publicly released a system called Muse that processes an email archive, and slices it across different sentiment facets, such as those expressing various emotions, congratula- tory messages, and messages related to family matters, religion, and health. These slices are used for visualizing the archive and as entry point into browsing the actual messages. We describe some early experiences with this system.