Shilad Sen

  • MSCS Department
  • 1600 Grand Avenue
  • St. Paul, MN 55105

I'm a Professor at Macalester College in St. Paul and a Principal Scientist at Microsoft. As a teacher, I strive to convey the joys of computer science to undergraduates and prepare them for their lives after graduation. As a researcher, I build systems that empower people to be better contributors to online communities.

My research draws on techniques from data-mining, interface design, and social science to encourage members to contribute better content to their communities, and enable communities to identify high-quality contributions from members. I also currently serve as a Principal Scientist for Microsoft Corporation, helping them develop AI systems that advance products such as Microsoft Outlook.

I received my Ph.D. under John Riedl at the University of Minnesota with GroupLens Research. Before that, I worked at Sourcelight Technologies, a startup that built movie recommenders for companies like Blockbuster Video and Comcast. I have also worked for Google, IBM Research, Thomson Reuters R & D, and Target Corporation.

When not teaching or researching, I play jazz saxophone, squash, and spend time with my family

Publications

You can find my updated publication list on Google Scholar.

Academic Projects

Cartograph

Cartograph creates thematic maps from non-geographical data. Our maps use neural networks trained on Wikipedia content and user behavior to reveal connections between points in a dataset that might otherwise appear unconnected. The maps support zoom, pan, and other features that enhance the geographic metaphor.

Localness

This study examines geographic barriers to information in Wikipedia. Focusing on millions of articles about geographic entities (e.g. cities, points of interest) in 79 language editions of Wikipedia, we examine the localness of both the editors working on articles and the sources of the information they cite. We find extensive geographic inequalities in localness, with the degree of localness varying with the socioeconomic status of the local population and the health of the local media.

WikiBrain

The WikiBrain Java framework provides easy and efficient access to multi-lingual Wikipedia data. It supports all Wikipedia language editions, providing tools that download and organize datasets published by the Wikimedia foundation. The library provides algorithms that detect identical and related concepts across language editions. WikiBrain was retired in 2020 after thousands of downloads.

Macademia

The Macademia website connects scholars who share research interests. Over 2500 researchers have created profiles from 250 institutions. Macademia visualizes the interest graph to help users discover people with similar interests. Macademia also serves as experimental research platform for algorithms and interfaces that navigate the interest graph. Macademia was retired in 2020.