SigmaLaw PBSA - A Deep Learning Approach For Aspect Based Sentiment Analysis in Legal Opinion Texts  (pp101-115)
         Isanka Rajapaksha, Chanika Ruchini Mudalige, Dilini Karunarathna, Nisansa de Silva, Gathika Ratnayaka, and Amal Shehan Perera
         doi: https://doi.org/10.26421/JDI3.1-1
Abstracts: When lawyers and legal officers are working on a new legal case, they are supposed have properly studied prior cases similar to the current case, as the prior cases can provide valuable information which can have a direct impact on the outcomes of the current court case. Therefore, developing methodologies which are capable of automatically extracting information from legal opinion texts related to previous court cases can be considered as an important tool when it comes to the legal technology ecosystem. In this study, we focus on finding advantageous and disadvantageous facts or arguments in court cases, which is one of the most critical and time-consuming tasks in court case analysis. The Aspect-based Sentiment Analysis concept is used as the base of this study to perform legal information extraction. In this paper, we introduce a solution to predict sentiment value of sentences in legal documents in relation to its legal parties. The proposed approach employs a fine-grained sentiment analysis (Aspect-Based Sentiment Analysis) technique to achieve this task. Sigmalaw PBSA is a novel deep learning-based model for ABSA which is specifically designed for legal opinion texts. We evaluate the Sigmalaw PBSA model and existing ABSA models on the SigmaLaw-ABSA dataset which consists of 2000 legal opinion texts fetched from a public online data base. Experiments show that our model outperforms the state-of-the-art models. We also conduct an ablation study to identify which methods are most effective for legal texts.
Key words: Legal Information Extraction, Legal domain, Aspect-Based Sentiment Analysis, Deep learning, NLP