Discovering Significant Topics from Legal Decisions with Selective Inference
This provides an automated tool for legal professionals to analyze case topics correlated with outcomes, though it is incremental in applying existing statistical methods to legal text data.
The authors tackled the problem of automatically discovering legally significant topics from court decisions by developing a pipeline combining topic modeling, penalized regression, and post-selection significance tests. They demonstrated the method on domain name dispute and European human rights cases, showing that the identified topics align with legal doctrines and can support related legal analysis tasks.
We propose and evaluate an automated pipeline for discovering significant topics from legal decision texts by passing features synthesized with topic models through penalised regressions and post-selection significance tests. The method identifies case topics significantly correlated with outcomes, topic-word distributions which can be manually-interpreted to gain insights about significant topics, and case-topic weights which can be used to identify representative cases for each topic. We demonstrate the method on a new dataset of domain name disputes and a canonical dataset of European Court of Human Rights violation cases. Topic models based on latent semantic analysis as well as language model embeddings are evaluated. We show that topics derived by the pipeline are consistent with legal doctrines in both areas and can be useful in other related legal analysis tasks.