Using Latent Dirichlet Allocation to Explore the Dimensionality of the U.S. Practice of Law

Over the centuries, the U.S. practice of law has evolved into a complex and amorphous profession. To facilitate improved analysis and understanding, this exploratory study seeks to partition law practice areas into meaningful subgroups. The study applies Latent Dirichlet Allocation (“LDA”) as a soft clustering method to 437,210 individual U.S. lawyer profiles in private practice in 2000. The profiles came from a nationally recognized directory. The resulting subgroupings contain terms consistent with the hypothesized relationships. The results also suggest the possibility of systematically binning individual practice areas into discrete practice area distributions. As such, this study makes contributions to the existing literature in at least three areas: 1) it provides support for the existence of the hypothesized law practice relationships; 2) it provides an empirical basis for developing an improved measurement of the U.S. practice of law; and 3) this study also suggests additional research to advance the field.