Published on:

The arrival of text mining and its implications for tracking ideas important to law department management

Software is now available that could take all the blog posts on GC Metrics’ Law Department Management and all the articles written in the past five years and all the books about leading law departments and analyze their contents.  A combination of algorithms that use machine learning, network analysis, data mining techniques, and graphics could enable new understandings of the prevalence of ideas about management in corporate legal settings. These tools, which involve statistical parsing and aggregation of large amounts of text, could give us a different picture of how ideas generate, spread, and become mainstream, marginal, or moribund.


For example the notion (and the term itself) of convergence might have first appeared in the early 1990s but its frequency peaked by a decade later – or did it.


Comments posted on social networks such as LinkedIn and Legal OnRamp could be ore for this mine.  With all that material available, analysts could track the use of words over time come, compare related words, and graph them.  Think of one form of the output as a concept geneology.


These ideas came from an article in the NY Times, January 27, 2013 at BU 3. They would allow people with experience in running corporate legal teams to see their conceptual world from a different, quantitative perspective.  Consultants could make use of this material and there would be ample benchmarking opportunities