Towards Meaningful Maps of Polish Case Law
This work addresses the challenge of analyzing legal texts for researchers or practitioners in law, but it is incremental as it applies existing methods to a new dataset.
The paper tackled the problem of visualizing Polish case law for exploratory analysis by comparing PCA and t-SNE methods, finding that t-SNE provides better and more interpretable results, such as revealing hidden topical structure related to keywords like 'pension'.
In this work, we analyze the utility of two dimensional document maps for exploratory analysis of Polish case law. We start by comparing two methods of generating such visualizations. First is based on linear principal component analysis (PCA). Second makes use of the modern nonlinear t-Distributed Stochastic Neighbor Embedding method (t-SNE). We apply both PCA and t-SNE to a corpus of judgments from different courts in Poland. It emerges that t-SNE provides better, more interpretable results than PCA. As a next test, we apply t-SNE to randomly selected sample of common court judgments corresponding to different keywords. We show that t-SNE, in this case, reveals hidden topical structure of the documents related to keyword,,pension". In conclusion, we find that the t-SNE method could be a promising tool to facilitate the exploitative analysis of legal texts, e.g., by complementing search or browse functionality in legal databases.