Text mining approach for knowledge extraction in Sahîh Al-Bukhari

Harrag, Fouzi

doi:10.1016/j.chb.2013.06.035

Cited by 29 publications

(22 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Precision is the number of correct hadith extracted by the system divided by the number of all hadith extracted by the system. F-measure is the combines precision and recall; it is used to calculate the performance of text classifier [5]. The recall and precision can be got after computing the true-positives (TP), true-negatives (TN), false-negative (FN) and false-positive (FP); [13] [5].…”

Section: F Classifier Model Evaluatingmentioning

confidence: 99%

“…In this study, the classification technique and supervised learning algorithms plus combination methods have been used to classify the hadith into different categories, according to its topic. Based on the Sahih al-Bukhari book [5] which contains more than 7500 hadith divided into 96 topics [2], [16]. Also, in this study the combination methods are used such as the Stacking algorithm to improve the classification accuracy using 10-fold crossvalidation method, it includes two levels of classification,…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Classification of Hadith According to Its Content Based on Supervised Learning Algorithms

2019

View full text Add to dashboard Cite

Given the importance of the Prophet's Hadith for Muslims all over the world, where it is the second source of Islam after the Qur'an and the fundamental resource of legislation in the Islam community. This study is focused on the Classification of hadith automatically into different categories according to its content, based on Hadith text. The objective of this study is to build a classifier model can classify and differentiate hadith categories, to predict its topic like prayer, fasting, and zakat; using data mining and machine learning techniques. In this study, many supervised learning algorithms plus combination methods such as the stacking algorithm was used to improve classification accuracy. The best three classifiers were evaluated mainly: the Decision Tree (DT), Random Forest (RF), and Naïve Bayes (NB), which achieved higher accuracy reached up to 0.965%, 0.956, and 0.951% respectively. Also, Binary (Boolean algebra) and TF-IDF methods as term weighting was applied to determine the frequency of each word in the hadith text, and identify the most significant features in training dataset using Information Gain (IG), and Chi-square (CHI). The experimental results showed that retrain these classifiers after applying IG and CHI as features selection; gave better accuracy compared to the previous results. Additional to, the best classifier gave high accuracy was DT, it has achieved higher accuracy in most test cases whether in the Boolean algebra or TF-IDF because it can deal with missing values and identifying the most essential features from the training dataset, known as features engineering.

show abstract

Section: F Classifier Model Evaluatingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Classification of Hadith According to Its Content Based on Supervised Learning Algorithms

2019

View full text Add to dashboard Cite

show abstract

“…L.Zhang et al [7] have used ontology in the extraction of a partial building information model from the original complete model. F.Harrag [8] has proposed a methodology in order to detect and extract passages or sequences of words containing relevant to information from the prophetic narrations texts. Generally, knowledge extraction is done by constructing a schema that models the contents of the data.…”

Section: Related Workmentioning

confidence: 99%

Building Information Extraction System Based on Computing Domain Ontology

Thi

2014

Proceedings of the 16th International Conference on Information Integration and Web-Based Applications &Amp; Services

View full text Add to dashboard Cite

In this paper, we present an Information Extraction (IE) system, which is built from unstructured text based on Computing domain ontology. The IE system comprises four sequential processing steps: preprocessing, topic identifier, building domain specific ontology and extracting information from text corpus. The first two steps perform generic Natural Language Processing (NLP) and Machine Learning tasks, while the last two phases are application-specific and require a thorough understanding of the application domain. Furthermore, the paper focuses on evaluating the IE IEsystem by selected methods. One of these methods that we introduced here, is comparative. Comparative evaluation performed in this study use of Key Exchange Algorithm with the same corpus to contrast results. Results generated by such experiments show that this IE system outperforms Key Exchange Algorithm, respectably.

show abstract

“…In [15], Harrag introduced an entity-extraction method based on Finite State Transducers (FST) to extract useful entities from Hadiths of Sahih Al-Bukhari. This method detected a sequence of words containing relevant information from Hadiths.…”

Section: A Hadith-text Processing Researchesmentioning

confidence: 99%

A Novel Hadith Processing Approach Based on Genetic Algorithms

Najeeb

2020

IEEE Access

View full text Add to dashboard Cite

Quran and Hadith are the main religious sources in Islam. Hadith is mainly the saying of Prophet Mohammad, and it consists of two parts: first is ''Isnad''; which is the series of persons (narrators) who report (narrate) Hadith, and the second is ''Matn''; which is the saying or the narration itself. Isnad can be divided into phrases called ''Isnad-Phrases'', which could be tagged according to proposed Part-Of-Isnads (POIs) that represent the entity types of Isnad, such as Narrator Name, Prophet Name and Received Method. One of the main objectives of Hadith sciences is to ascertain the validity of Hadith and determine if it is accepted or rejected; this is known as Hadith judgment. Hadith scholars put many rules to judge Hadiths; some of these rules are related to the chain of narrators. Therefore, to judge Hadith, first, the narrators' names in Isnad should be extracted then judgment rules can be applied. Many researches proposed different methods to extract narrators' names from Isnad. To the best of the author's knowledge, there is no research process Isnad using Genetic Algorithms (GA). In this research, a novel approach is introduced for Isnad processing based on GA. This approach aims to predict the narrators' names and the other POIs for Isnad. The experiments, which conducted on all Hadiths narrated in ''Sahih Muslim'' book, show that the proposed approach achieved 81.44% accuracy. For further research in this genre, investigation of utilizing other approaches for Isnad processing, such as deep learning, is recommended. INDEX TERMS Arabic natural language processing, genetic algorithms, hadith, isnad, tagging.

show abstract

Text mining approach for knowledge extraction in Sahîh Al-Bukhari

Cited by 29 publications

References 7 publications

Classification of Hadith According to Its Content Based on Supervised Learning Algorithms

Classification of Hadith According to Its Content Based on Supervised Learning Algorithms

Building Information Extraction System Based on Computing Domain Ontology

A Novel Hadith Processing Approach Based on Genetic Algorithms

Contact Info

Product

Resources

About