Enhancements to knowledge discovery framework of SOPHIA textual case-based reasoning

Abstract

Many approaches were presented recently for developing Textual Case-Based Reasoning (TCBR) applications. One of the successful approaches is SOPHisticated Information Analysis (SOPHIA), which is distinguished by its ability to work without prior knowledge engineering, without domain dependency and without language dependency. SOPHIA is based on the distributional document clustering approach, which facilitates an advanced and rich knowledge discovery framework for case-based retrieval.This paper contributes to propose enhancements to SOPHIA approach that aims to enhance the retrieval efficiency and increase the precision degree. It also aimed to grantee that all results will have the same subject of the user query. The enhancements include performing an automatic classification to the case-base before the clustering step in the indexing stage, and include performing an automatic classification to the user query before the retrieval stage. Moreover, proofing that SOPHIA approach is a domain and language independent by applying it in the domain of Islamic jurisprudence in Arabic language.