Please use this identifier to cite or link to this item:
https://ptsldigital.ukm.my/jspui/handle/123456789/475658Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | Lailatul Qadri, Dr. | - |
| dc.contributor.author | Soad Saleh A.S Balgasem (P69277) | - |
| dc.date.accessioned | 2023-10-05T06:40:46Z | - |
| dc.date.available | 2023-10-05T06:40:46Z | - |
| dc.date.issued | 2015-08-30 | - |
| dc.identifier.other | ukmvital:82219 | - |
| dc.identifier.uri | https://ptsldigital.ukm.my/jspui/handle/123456789/475658 | - |
| dc.description | Hadith is one of the two main fundamental resources for Muslims, which contains a collection of quotes that have been said by the Prophet Mohammed (SAW). In order to validate Hadith, there are two main factors that can identify the strength of a certain hadith, which are the context (context of the hadith itself) and the narrators (the persons who narrate this hadith). Therefore, the process of identifying the narrators' names plays an essential role in terms of validating a specific hadith. This process is called the Named Entity Recognition, which is a field that has been coming up as a significant approach in Natural Language Processing. It aims to identify the names of the persons, organizations, locations and numeric entities. In fact, Hadith narrators contain Arabic names which have some complexity due to the compostional that lies in Arabic names. A person's name may yield a multi-word that indicates his first name such as عبد الله. This means that recognizing Arabic names requires treating multi-word expressions. Many researchers have proposed methods for extracting Arabic multi-word expressions and Arabic named entities as well. However, there is a lack of research efforts that could treat Arabic names as a multi-word case. hence, this study is collected from an online resource, Islam Web.net which contains Hadith from Al-Bukhari. The framework of this study consists of six major phases including dataset, transformation, pre-processing, Part-Of-Speech tagging, rule based method and statistical methids. The proposed rule-based method is relying on a keyword trigger which aims to utilize specific words that could be used to indicate a narrator's name. The statistical measures that were used are Log-likelihood Ration (LLR), Point-wise Mutual Information (PMI), S-cost, R-cost and U-cost. The experimental results have shown that the proposed hybrid method achieved an 82% of F-measure. By comparing the proposed method with the related work, it has been concluded that the hybrid method of rule-based and statistical methods has a significant impact on recognizing Arabic multi-word named entities, which leads to enhancement in terms of effectiveness.,Certification of Master's/Doctoral Thesis" is not available | - |
| dc.language.iso | eng | - |
| dc.publisher | UKM, Bangi | - |
| dc.relation | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | - |
| dc.rights | UKM | - |
| dc.subject | Hadith | - |
| dc.subject | Narrators name | - |
| dc.subject | Hybrid method | - |
| dc.subject | Arabic names | - |
| dc.subject | Dissertations, Academic -- Malaysia | - |
| dc.title | A hybrid method of rule-based approach and log likehood ratio measures for recognizing narrators name in hadith | - |
| dc.type | Theses | - |
| dc.format.pages | 81 | - |
| Appears in Collections: | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.