6hqwlphqw $qdo\vlv Rq 3huvrqdo (pdlo $ufklyhv

Copyright is held by the author/owner(s). CHI 2011, May 7-12. Vancouver, Canada ACM 978-1-4503-0268-5/11/05. Abstract A significant portion of a user’s digital past is recorded in textual form, for example, in email messages, SMS texts, tweets, status updates and blog posts. We view this 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 information from an unstructured text corpus spanning 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 personal 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, congratulatory messages, and messages related to family matters, religion, and health. These slices are used for visualizing the archive and as an entry point into browsing the actual messages. We describe some early experiences with this system.