Formal Concept Analysis for Arabic Web Search Results Clustering

Recently, Arabic language has become one of the most used languages in the web. However, the majority of existing solutions to improve web usage do not take into account the characteristics of this language. The process of browsing search results is one of the major problems with traditional web search engines, especially with ambiguous queries. Using a ranked list as return result of a specific user request is time consuming and the browsing style seems to not be user-friendly. In this paper, we propose to study how to integrate and adapt the Formal Concept Analysis (FCA) as a new system for Arabic Web Search Results Clustering based on their hierarchical structure. The effectiveness of our proposed system is illustrated by an experimental study using Arabic comprehensive set of documents from the Open Directory Project hierarchy as benchmark, where we compare our system with two others: Suffix Tree Clustering (STC) and Lingo. The comparison focuses on the quality of the clustering results and produced label by different systems. It shows that our system outperforms the two others.