The Precydent Search Engine and the Web of Law

My colleague at USD Tom Smith has a fascinating study on lately legal citation networks. In his paper The Web of Law he researches the structure of citation of nearly four million American legal precedents to shed light on how the legal system evolves, demonstrating that the American case law network has the overall structure that network theory predicts it would, with clusters, node and patterned aging.

Now Tom and his co-author Antonio Tomarchio, a mathematics graduate student at the Polytechnic of Milan and the Ecole Centrale Paris, have launched http://www.precydent.com. Tom desribes it as “a new kind of legal search engine…Unlike the search engines at Westlaw, Lexis and other legal research services, the Precydent search engine is based on the legal citation network and various Web 3.0 technologies.  Like Google's PageRank algorithm, Precydent's algorithm traces its intellectual ancestry to important discoveries about networks made by Cornell computer scientist Jon Kleinberg, who also generously assisted Antonio in his academic research on the legal citation network.  The algorithm and its many innovative features are the creations of the Precydent team. The search engine does use sophisticated techniques to analyze click streams in order to adapt to users' individual and collective preferences.  While I do not think this raises any privacy concerns, I should at least note this feature of the technology.  Analyzing user behavior is an important part of Web 3.0 technology.” When the founders compared the performance of the Precydent search engine to that of the natural language search engines of Westlaw and Lexis, they found that “Precydent does a much better job in returning relevant and authoritative US Supreme Court cases (as judged by human experts) than do the natural language engines of Westlaw and Lexis.”

(cross posted on Prawfsblawg)

Comments

[Searchboth]

Searchboth.net is the first site to place google and yahoo side by side on one split screen. The web site takes the user's query and creates a browser window with two frames, with the results from Yahoo! on one side and those from google on the other. It has completely end up the hassles involved while searching different search engines at the same time.