Finding Justice through Network Analysis

Western countries, commercial publishers traditionally provide legal information and support for access. Legal experts write commentaries, editors provide links between different sources and point subscribers to interesting new developments and case law. This chapter focuses on automated enrichment of legal data: using techniques like machine learning, network analysis, and natural language processing to automatically create new metadata for sources of law. It describes several experiments in the field of Dutch immigration law to create a Legal Recommender System. A more advanced approach of comparing the similarity of texts than the bag-of-words approach discussed is that of topic modeling. A topic model represents a document, a court judgment in this case, as a mixture of topics. The network of references can be used to provide users of the legislative portal with relevant judicial decisions given their current focus and moreover, suggest additional relevant legislative sources. Another step is adding legal commentaries and doctrine to the network and possibly parliamentary data.