Diana MacLean : POMI 2020 Workshop


Tuesday, April 27, 2010
Location: Fisher Conference Center, Arrillaga Alumni Center

"Mining Social Topologies from Email for Online Data Sharing"


As people accumulate hundreds of "friends" in social media, a flat list of connections becomes unmanageable. Interfaces agnostic to social structure hinder the nuanced sharing of personal data such as status updates, photos, news feeds, and comments. To address this problem, we propose social topologies that represent the structure and content of a person's social network as a first-class object: a set of hierarchically organized and potentially overlapping social groups. We contribute an algorithm for creating social topologies by mining communication history and identifying likely groups based on co-occurrence patterns. We use our algorithm to populate a browser interface that supports creation and editing of social groups via simple drag-and-drop interactions. A user study confirms that our approach models subjects' social topologies well, and that our interface enables intuitive browsing and management of a personal, social landscape.


This is my first year as a Computer Science PhD student at Stanford. Originally, I hail from Johannesburg, South Africa; however, I completed my undergraduate education at Harvard College, where I studied Computer Science and Criminology. My interests include large-scale data mining and visualization, social network analysis (particularly if related to crime) and statistics. In my spare time I like to travel, ride horses, and read.