[Note on 9 June 2013: Click here for a PDF of the full text of the thesis. HT Eric Mill]
Staffan Malmgren of Stockholm University and the free access to law service of Sweden, lagen.nu, has posted his Master’s thesis, Towards a Theory of Jurisprudential Relevance Ranking – Using Link Analysis on EU Case Law (2011). Here is the abstract:
The concept of relevance is central to both jurisprudence and information retrieval. But what do we mean when we say that something is relevant? Is there a difference between how relevance is understood in jurisprudence and in information science? Which aspects that are unique to legal information have effect on relevance? And can we use this to build better information retrieval systems for legal information?
This thesis discusses the concept of relevance, both as it is used in general and in legal contexts. It describes the retrieval models used in modern information systems, and what notion these models have of relevance. By examining the legal reasoning process, in particular the process of ﬁnding legal information, it attempts to ﬁnd a retrieval model and a function for ranking that is adapted to legal information.
This function is implemented and evaluated against a traditional probabilistic ranking algorithm. It is shown to perform substantially better for all tested information need scenarios.