Guided Semi-Supervised Non-negative Matrix Factorization on Legal Documents
This work addresses the need for guided topic modeling and classification in legal document analysis, though it appears incremental as it builds on prior semi-supervised and guided NMF methods.
The authors tackled the problem of jointly performing classification and topic modeling on legal documents by proposing Guided Semi-Supervised Non-negative Matrix Factorization (GSSNMF), which incorporates supervision from document labels and seed words, resulting in improved classification accuracy and topic coherence compared to existing methods.
Classification and topic modeling are popular techniques in machine learning that extract information from large-scale datasets. By incorporating a priori information such as labels or important features, methods have been developed to perform classification and topic modeling tasks; however, most methods that can perform both do not allow for guidance of the topics or features. In this paper, we propose a method, namely Guided Semi-Supervised Non-negative Matrix Factorization (GSSNMF), that performs both classification and topic modeling by incorporating supervision from both pre-assigned document class labels and user-designed seed words. We test the performance of this method through its application to legal documents provided by the California Innocence Project, a nonprofit that works to free innocent convicted persons and reform the justice system. The results show that our proposed method improves both classification accuracy and topic coherence in comparison to past methods like Semi-Supervised Non-negative Matrix Factorization (SSNMF) and Guided Non-negative Matrix Factorization (Guided NMF).