Nurazzah Abd Rahman
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Nurazzah Abd Rahman has a total of 65 co-authors. Here are the top co-authors by number of shared publications:
Zainab Abu Bakar
14 shared publicationsNormaly Kamal Ismail
8 shared publications- Zulhilmi Mohamed Nor
Faculty of Quranic and Sunnah Studies, Universiti Sains Islam Malaysia, Bandar Baru Nilai, 71800, Nilai, Negeri Sembilan, Malaysia
4 shared publications - Muhammad Nazir Alias
Universiti Kebangsaan Malaysia
3 shared publications - Rohana Ismail
Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA, Shah Alam, Selangor, Malaysia
3 shared publications - Shaiful Bakhtiar bin Rodzman
Universiti Teknologi MARA
3 shared publications
Latest Publications
- Open Access
- 1 May 2023
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 30 (2) , 1214-1223
Jahai language repository: a mobile application
The Jahai language is facing extinction primarily because it is among the least spoken language among minority groups in Malaysia. This is due to lesser speakers and the shift to using a more dominant language. The Jahai tribe is one of the community groups living in the Royal Belum Perak State Park. People who need assistance from Jahai people often face difficulties in communicating with them due to the language barrier. Therefore, a mobile translation system was developed to preserve the language. The system translates the Jahai terms into Malay language. This way, by using the system, other ethnics in Malaysia can understand the language especially when communicating with Jahai people. Three main steps are required in the translation process; first, key in the text input via special character keypad. Then, the system will search the matching word in the database. Finally, the meaning of the word will be displayed. The testing results have indicated this system is functional and accepted with the SUS score of 94/100. Several future recommendations could be made such as including voice search function and adding more Jahai terms in other categories so as to improve the functionality and usability of this proposed system.
- 1 May 2023
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 30 (2) , 1214-1223
Open AccessJahai language repository: a mobile application
The Jahai language is facing extinction primarily because it is among the least spoken language among minority groups in Malaysia. This is due to lesser speakers and the shift to using a more dominant language. The Jahai tribe is one of the community groups living in the Royal Belum Perak State Park. People who need assistance from Jahai people often face difficulties in communicating with them due to the language barrier. Therefore, a mobile translation system was developed to preserve the language. The system translates the Jahai terms into Malay language. This way, by using the system, other ethnics in Malaysia can understand the language especially when communicating with Jahai people. Three main steps are required in the translation process; first, key in the text input via special character keypad. Then, the system will search the matching word in the database. Finally, the meaning of the word will be displayed. The testing results have indicated this system is functional and accepted with the SUS score of 94/100. Several future recommendations could be made such as including voice search function and adding more Jahai terms in other categories so as to improve the functionality and usability of this proposed system.
- Open Access
- 1 December 2022
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 11 (4) , 1579-1587
Classification of customer feedbacks using sentiment analysis towards mobile banking applications
Innovation and technology have subsequently transformed banking industry’s way of delivering products and services to their customer. Mobile banking is an effective way of performing transaction as it can be performed anywhere and anytime. The evolution of banking experience is important to fulfil customers’ need and demand especially in highly competitive banking industry. Through mobile banking application, customer can express their satisfaction and dissatisfaction directly on the application store platform. The fulfilment of customer’s satisfaction is important to avoid customer attrition. This research focused on customer feedbacks towards six mobile banking application in Malaysia which is Maybank, Commerce International Merchant Bankers (CIMB), Public Bank, Hong Leong Bank, Rashid Hussein Bank (RHB) and AmBank. This research aims to identify keywords related to customer feedback towards mobile banking, classify the sentiment and evaluate the accuracy performance by using supervised machine learning algorithm of support vector machine (SVM) and naïve Bayes (NB). The result shows that linear SVM is the best model with the highest value in all accuracy, precision, recall, including F1-score with value 97.17%, 97.21%, 97.17% and 97.18% respectively. With this high accuracy value, this model would have better performance in analyzing the classification of customer feedback in mobile banking application.
- 1 December 2022
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 11 (4) , 1579-1587
Open AccessClassification of customer feedbacks using sentiment analysis towards mobile banking applications
Innovation and technology have subsequently transformed banking industry’s way of delivering products and services to their customer. Mobile banking is an effective way of performing transaction as it can be performed anywhere and anytime. The evolution of banking experience is important to fulfil customers’ need and demand especially in highly competitive banking industry. Through mobile banking application, customer can express their satisfaction and dissatisfaction directly on the application store platform. The fulfilment of customer’s satisfaction is important to avoid customer attrition. This research focused on customer feedbacks towards six mobile banking application in Malaysia which is Maybank, Commerce International Merchant Bankers (CIMB), Public Bank, Hong Leong Bank, Rashid Hussein Bank (RHB) and AmBank. This research aims to identify keywords related to customer feedback towards mobile banking, classify the sentiment and evaluate the accuracy performance by using supervised machine learning algorithm of support vector machine (SVM) and naïve Bayes (NB). The result shows that linear SVM is the best model with the highest value in all accuracy, precision, recall, including F1-score with value 97.17%, 97.21%, 97.17% and 97.18% respectively. With this high accuracy value, this model would have better performance in analyzing the classification of customer feedback in mobile banking application.
- 1 January 2022
- Published by Springer Nature
- p. 145-156
Hadith Text Classification on Sanad Part Using Edge List
- 1 January 2022
- Published by Springer Nature
- p. 145-156
Hadith Text Classification on Sanad Part Using Edge List
- Open Access
- 31 July 2020
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 34 (5) , 2151-2160
Characteristics of Malay translated hadith corpus
- 31 July 2020
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 34 (5) , 2151-2160
Open AccessCharacteristics of Malay translated hadith corpus
- Open Access
- 1 January 2020
- Published by European Alliance for Innovation n.o.
Hadith Text Classification: A Literature Review
Hadith text classification is a domain specific research which requires involvement from both-science computer and hadith researcher. This paper presents literature on hadith text classification from different perspective in computer science such as classification process and issues related to it. This research therefore look into develop standard data set for hadith text classification with narrator chain part of the text as the basis. It will be the basis for future research on the classification of Malaytranslated hadith text.
- 1 January 2020
- Published by European Alliance for Innovation n.o.
Open AccessHadith Text Classification: A Literature Review
Hadith text classification is a domain specific research which requires involvement from both-science computer and hadith researcher. This paper presents literature on hadith text classification from different perspective in computer science such as classification process and issues related to it. This research therefore look into develop standard data set for hadith text classification with narrator chain part of the text as the basis. It will be the basis for future research on the classification of Malaytranslated hadith text.
- 9 December 2018
- Published by Science Publishing Corporation in International Journal of Engineering & Technology
- Vol. 7 (4.33) , 1-4
A Comparative Evaluation of Search Engines on Finding Specific Domain Information on the Web
Recently search engines have provided a truly amazing search service, especially in finding general information on the Web. However, the question arises, does search engine perform the same when seeking domain specific information such as medical, geographical or agriculture information? Along with that issue, an experiment has been conducted to test the effectiveness of today’s search engines from the aspect of information searching in a specific domain. There were four search engines have been selected namely Google, Bing, Yahoo and DuckDuckGo for the experiment. While for the domain specific, we chose to test information about the popular fruit in Southeast Asia that is durian. Precision metric has been used to evaluate the retrieval effectiveness. The findings show that Google has outperformed the other three search engines. Nevertheless, the mean average precision value 0.51 given by Google is still low to be satisfied neither by the researcher nor the information seekers.
- 9 December 2018
- Published by Science Publishing Corporation in International Journal of Engineering & Technology
- Vol. 7 (4.33) , 1-4
A Comparative Evaluation of Search Engines on Finding Specific Domain Information on the Web
Recently search engines have provided a truly amazing search service, especially in finding general information on the Web. However, the question arises, does search engine perform the same when seeking domain specific information such as medical, geographical or agriculture information? Along with that issue, an experiment has been conducted to test the effectiveness of today’s search engines from the aspect of information searching in a specific domain. There were four search engines have been selected namely Google, Bing, Yahoo and DuckDuckGo for the experiment. While for the domain specific, we chose to test information about the popular fruit in Southeast Asia that is durian. Precision metric has been used to evaluate the retrieval effectiveness. The findings show that Google has outperformed the other three search engines. Nevertheless, the mean average precision value 0.51 given by Google is still low to be satisfied neither by the researcher nor the information seekers.
- 1 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 122-126
Concepts extraction in ontology learning using language patterns for better accuracy
The identification of concepts and relations via automatic or semiautomatic are tasks in Ontology Learning. The Ontology Learning is important in minimizing effort of ontology development. It has been used in many disciplines including development of Quran ontology. In the Quran ontology development, there have been efforts to identify concepts and relations for ontology development using various methods. Among the methods employed to discover concepts is a regex pattern. The pattern is based on NLP which use tagging in their rules. This paper proposed a method that used patterns to extract concepts for Hajj Ontology development. It also has been compared against a prominence Ontology Learning system i.e. Text2Onto. The patterns also have been compared with Qterm pattern which is specifically designed for Solah domain in the Quran. Results indicate that the proposed patterns improve the precision with 82.4% and recall with 85.7% as compared to the both approaches.
- 1 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 122-126
Concepts extraction in ontology learning using language patterns for better accuracy
The identification of concepts and relations via automatic or semiautomatic are tasks in Ontology Learning. The Ontology Learning is important in minimizing effort of ontology development. It has been used in many disciplines including development of Quran ontology. In the Quran ontology development, there have been efforts to identify concepts and relations for ontology development using various methods. Among the methods employed to discover concepts is a regex pattern. The pattern is based on NLP which use tagging in their rules. This paper proposed a method that used patterns to extract concepts for Hajj Ontology development. It also has been compared against a prominence Ontology Learning system i.e. Text2Onto. The patterns also have been compared with Qterm pattern which is specifically designed for Solah domain in the Quran. Results indicate that the proposed patterns improve the precision with 82.4% and recall with 85.7% as compared to the both approaches.
- 6 April 2018
- Published by Science Publishing Corporation in International Journal of Engineering & Technology
- Vol. 7 (2.14) , 13-16
Single Term Concepts from English Translated Qur’an Using Statistical Methods
Ontology is essential for the success of knowledge based systems because it has the opportunity to share vocabulary, integrate knowledge easily and discover new instances or relations. However, the development of ontology via manual is time consuming and tedious task. Thus, ontology learning comes to play it roles. The ontology learning tries to extract ontological elements to support the ontology development. Concept extraction is one of the important tasks in ontology learning. The Hajj domain of Quranic study, concepts have not fully discovered. Hence, this paper tries to discover concepts by extracting the single terms from Qur’an translated version. It provides result on extracting the single terms as concepts by using statistical methods. Apart from that, it has been experimented for English Translated Quran by Hilali Khan. Result shows that the performance of using tf method as a statistical method is significant with the f-measure value is 0.509. Based on the tf, the comparisons have been made for other statistical methods such as tfidf, Avetf and Ridf.
- 6 April 2018
- Published by Science Publishing Corporation in International Journal of Engineering & Technology
- Vol. 7 (2.14) , 13-16
Single Term Concepts from English Translated Qur’an Using Statistical Methods
Ontology is essential for the success of knowledge based systems because it has the opportunity to share vocabulary, integrate knowledge easily and discover new instances or relations. However, the development of ontology via manual is time consuming and tedious task. Thus, ontology learning comes to play it roles. The ontology learning tries to extract ontological elements to support the ontology development. Concept extraction is one of the important tasks in ontology learning. The Hajj domain of Quranic study, concepts have not fully discovered. Hence, this paper tries to discover concepts by extracting the single terms from Qur’an translated version. It provides result on extracting the single terms as concepts by using statistical methods. Apart from that, it has been experimented for English Translated Quran by Hilali Khan. Result shows that the performance of using tf method as a statistical method is significant with the f-measure value is 0.509. Based on the tf, the comparisons have been made for other statistical methods such as tfidf, Avetf and Ridf.
- 1 March 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Morphological Analysis of Malay Words for Resolving Ambiguity
The issue of morphological uncertainty is broadly tended to in the cutting edge in Natural Language Processing (NLP). For the most part, vagueness is settled with the utilization of substantial physically explained corpora and machine learning. Be that as it may, such strategies do not generally accessible, as great preparing information is not available for all dialects. In this paper, we introduce a technique for disambiguation without highest quality level corpora utilizing a few factual models, to be specific, Braille Translation Algorithms and unambiguous N-grams from the naturally explained corpus. Every one of the strategies was tried on the Corpus of Glosbe and on the Corpus of Dewan Bahasa Pustaka (DBP). Therefore, more than a half of words with uncertain examinations were disambiguated in the two corpora, exhibiting high exactness. Our technique for morphological disambiguation shows that it is conceivable to dispose of a portion of the uncertain examinations in the corpus without particular phonetic assets, just with the utilization of crude information, where all conceivable morphological investigations for each word are shown.
- 1 March 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Morphological Analysis of Malay Words for Resolving Ambiguity
The issue of morphological uncertainty is broadly tended to in the cutting edge in Natural Language Processing (NLP). For the most part, vagueness is settled with the utilization of substantial physically explained corpora and machine learning. Be that as it may, such strategies do not generally accessible, as great preparing information is not available for all dialects. In this paper, we introduce a technique for disambiguation without highest quality level corpora utilizing a few factual models, to be specific, Braille Translation Algorithms and unambiguous N-grams from the naturally explained corpus. Every one of the strategies was tried on the Corpus of Glosbe and on the Corpus of Dewan Bahasa Pustaka (DBP). Therefore, more than a half of words with uncertain examinations were disambiguated in the two corpora, exhibiting high exactness. Our technique for morphological disambiguation shows that it is conceivable to dispose of a portion of the uncertain examinations in the corpus without particular phonetic assets, just with the utilization of crude information, where all conceivable morphological investigations for each word are shown.
- 1 March 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Effectiveness of Latent Dirichlet Allocation Model for Semantic Information Retrieval on Malay Document
Current research usually adopts the standard process of Vector Space Model (VSM) in searching and retrieving information on Malay documents. However, this technique is less effective for semantic information retrieval from the collection. The system will only retrieve documents which contain the user's query terms and ignore semantic information among those terms. Therefore, several documents that have similar context are ignored and several document context that share a single term are retrieved. Due to this problem, Latent Dirichlet Allocation (LDA) model is applied for semantic information retrieval on Malay documents. An experiment was illustrated based on 6 queries text and 50 Hadith documents translated in Malay language, composed of Shahih Bukhari collections. Experimental results proved that the LDA model gives promising results in retrieving semantic information in Malay translated Hadith documents compare to existing techniques. Some limitation from this study can be explored for future work in order to improve the effectiveness of the retrieval results. Overall, LDA is an effective method for semantic information retrieval on Malay document, thus, it can help people to easily search and retrieve semantic information from Malay documents.
- 1 March 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Effectiveness of Latent Dirichlet Allocation Model for Semantic Information Retrieval on Malay Document
Current research usually adopts the standard process of Vector Space Model (VSM) in searching and retrieving information on Malay documents. However, this technique is less effective for semantic information retrieval from the collection. The system will only retrieve documents which contain the user's query terms and ignore semantic information among those terms. Therefore, several documents that have similar context are ignored and several document context that share a single term are retrieved. Due to this problem, Latent Dirichlet Allocation (LDA) model is applied for semantic information retrieval on Malay documents. An experiment was illustrated based on 6 queries text and 50 Hadith documents translated in Malay language, composed of Shahih Bukhari collections. Experimental results proved that the LDA model gives promising results in retrieving semantic information in Malay translated Hadith documents compare to existing techniques. Some limitation from this study can be explored for future work in order to improve the effectiveness of the retrieval results. Overall, LDA is an effective method for semantic information retrieval on Malay document, thus, it can help people to easily search and retrieve semantic information from Malay documents.