Semantic Information Retrieval For Hadith Based On Query Expansion Of Ontological Knowledge
Arabic is the official language of millions of people and is the religious language of all Muslims, where it is the language of the Quran and Sunnah. The Arabic and Islamic contents on the Web have recently witnessed a steady growth which reinforces the need to build information retrieval systems th...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | en_US |
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Arabic is the official language of millions of people and is the religious language of all Muslims, where it is the language of the Quran and Sunnah. The Arabic and Islamic contents on the Web have recently witnessed a steady growth which reinforces the need to build information retrieval systems that support the Arabic language and meet its requirements. However, certain characteristics of the Arabic language pose serious challenges to information retrieval systems. Those challenges include its complex morphology, polysemy and the rich set of vocabularies represent. The Islamic prophetic traditions (Hadiths) should gain a lot of interest in information retrieval because it is related to a vital aspect in people's thinking and beliefs. However, Hadith is rich source of knowledge with many underlying thoughts, meanings, and it often contains many metaphors and figurative speech that cannot be explained directly which aggregate the Arabic information retrieval systems problems. Information retrieval systems need to model the various entities, concepts and relationships in Hadiths and to provide results based on semantic processing of content, or extract tacit relations and meanings from text. Thus, this research focuses on studying Hadith documents in the field of semantic information retrieval by
providing an intelligent system to retrieve its documents based on ontology. This research proposed a semantic search engine aimed to enhance the effectiveness and the precision of the retrieval process by applying an additional semantic layer to the traditional retrieval systems. The proposed semantic approach adopts similarities captured from both textual contents and specific-designed ontology for intelligent categorization of Hadith documents. An automatic query expansion method is also proposed and included in the system to address the vocabulary problem and to capture the users' intention using both specific-designed thesaurus and ontology. In addition, this study proposes a semantic information retrieval based on a semantic annotation, on ontology based indexing and ranking approaches. The performance of semantic model is tested using common information retrieval measurements such as the precision and recall. The results achieved with precision of 71% and recall of 58%. Such results imply that the proposed system has a competitive performance compared to the state of the art systems. |
|---|