Saturday, March 5, 2011

Legal Insights Gained from Computer Science

The New York Times has an intriguing article, "Armies of Expensive Lawyers Replaced by Cheaper Software," which quotes one of my colleagues in the Computer Science Department at UMass Amherst, Professor Andrew McCallum. The article states that thanks to advances in artificial intelligence, “e-discovery” software can analyze documents in a fraction of the time for a fraction of the cost. In January, for example, Blackstone Discovery of Palo Alto, Calif., helped analyze 1.5 million documents for less than $100,000.

What I find intriguing is the use of software to identify such issues as "sentiment" and even "emotion" or strength of an individual's feelings about issues based on language in email messages.

McCallum is recognized in this article for making available the database behind the millions of emails in the Enron prosecution case to researchers. We had invited McCallum to speak on his research in our UMass Amherst INFORMS Speaker Series and just look at the amazing lineup we had that semester. His talk title and abstract:

TITLE: Bayesian Models of Social Networks and Text
Abstract: The field of social network analysis studies mathematical models of patterns in the interactions between people or other entities. In this talk I will present several recent advances in generative, probabilistic modeling of networks and their per-edge attributes. The Author-Recipient-Topic model discovers role-similarity between entities by examining not only network connectivity, but also the words communicated on on those edges; I'll demonstrate this method on a large corpus of email data subpoenaed as part of the Enron investigation. The Group-Topic model discovers groups of entities and the "topical" conditions under which different groupings arise; I'll demonstrate this on coalition discovery from many years worth of voting records in the U.S. Senate and the U.N. I'll conclude with further examples of Bayesian networks successfully applied to relational data, as well as discussion of their applicability to trend analysis, expert-finding and bibliometrics.

Joint work with colleagues at UMass and Google: Xuerui Wang, Natasha Mohanty, and Andres Corrada.

Coincidentally, yesterday, I marched over across the UMass Amherst campus with one of my doctoral students to attend a talk in the Computational Social Science Speaker Series, which is a new initiative here at UMass Amherst. The speaker was Dr. James Kitts of the Graduate School of Business at Columbia University and he spoke on "Group Processes and Local Network Dynamics." He brought up some fascinating issues, which would be challenging, but intriguing, to model.

I very much appreciate how analytics and computer science are making an impact on so many different disciplines.