Legal Documents Clustering using Latent Dirichlet Allocation

At present due to the availability of large amount of legal judgments in the digital form creates opportunities and challenges for both the legal community and for information technology researchers. This development needs assistance in organizing, analyzing, retrieving and presenting this content in a helpful and distributed manner. We propose an approach to cluster legal judgments based on the topics obtained from Latent Dirichlet Allocation (LDA) using similarity measure between topics and documents. The developed topic based clustering model is capable of grouping the legal judgments into different clusters in effective manner. As per as our knowledge is concerned this is the first approach to cluster Indian legal judgments using LDA topic model. General Terms Documents Clustering, Similarity measure.