GloSOPHIA: An Enhanced Textual Based Clustering Approach by Word Embeddings

Abstract

Textual case based reasoning (TCBR) is a challenging problem because a single case may consist of different topics and complex linguistic terms. Many efforts have been made to enhance retrieval process in TCBR using clustering methods. This paper proposes an enhanced clustering approach called GloSOPHIA (GloVe SOPHIA). It is based on extending SOPHIA by integrating word embeddings technique to enhance knowledge discovery in TCBR. To evaluate the quality of the proposed method, we will apply the GloSOPHIA to an Arabic newspaper corpus called watan-2004 and will compare the results with SOPHIA (SOPHisticated Information Analysis), K-means, and Self-Organizing Map (SOM) with different types of evaluation criteria. The results show that GloSOPHIA outperforms the 3 other clustering methods in most of the evaluation criteria.