In a way to make the result of Information Retrieval (IR) more accurate, a stemmer is needed to differentiate the words in searching useful information. This research aims to analyze both processing speed and accuracy of the Malay Language Stemmer such as Fatimah Stemmer and UniSZA Stemmer. This research will also compare the performance of Fuzzy Logic Ranking Function using the both stemmer. Evaluation of Recall and Precision using the relevant judgement list by the expert. The results presented UniSZA Stemmer clearly dominated the Fatimah Stemmer processing speed performance with faster times recorded in each set of the experiment, however, in term of accuracy, unfortunately Fatimah Stemmer has clearly dominated the UniSZA stemming accuracy performance with having much more correct stemmed words for each set of the experiment. The results also showed that Fuzzy Logic Ranking with Fatimah Stemmer has outperformed Fuzzy Logic Ranking with UniSZA Stemmer and English Porter Stemmer on 5 out of 8 Topic Set of query results on the Mean Average Precision measure. Fuzzy Logic Ranking with Fatimah Stemmer also gets the best result on the Precision at Rank 10, Mean Average Precision and the percentage of no relevant document in the top ten retrieved measures, on the topic that has most queries which is topic 'Umum' that has a total of 11 queries.

Sanad is one of important part used to determine the authentication of hadith. However, very little research work has been found on classification of Malay translated Hadith based on sanad. There are some researches done using machine learning approach on hadith classification based on sanad but using different objective with different language. This research is to see how Machine Learning techniques are used to classify Malay translated Hadith document based on sanad. In this paper, SVM, NB and k-NN are used to identify and evaluate the performance of Malay translated hadith based on sanad. The performances are evaluated based on standard performance metrics used in text classification which is accuracy and response time. The results show that SVM has the highest accuracy and k-NN has the best response time (time taken in process for classification data) compare to other classifier. In future, we plan to extend this paper with the analysis on interclass similarity and also test on larger dataset.

Ranking function acts as a predictive algorithm that is used to establish a simple ordering of documents according to its relevance and this process shows the effectiveness, quality and the accuracy for the variety type of Information Retrieval (IR) such as, Domain Specific Retrieval of Malay Translated Hadith. In this research, a Hierarchical Fuzzy Logic Controller of Mamdani-type Fuzzy Inference System has been built to define the ranking function based on the BM25 Model. The model examines four-inputs which are Ontology BM25 Score, Fabrication Rate of Hadith, Shia Rate of Hadith from the previous works of the researchers and the New additional Positive Rate of Hadith. It also examines four-output values of Final Ranking Score which consist of three triangular membership functions. The new Positive Rate of hadith is based on the score value of the automatic text summarization that was executed in pre-processing phase. The proposed system has outperformed the BM25 original score and the Vector Space Model (VM) on 5 topic of queries and 26 queries in the term of individual queries, while the BM25 original score and Vector Space Model only yielded better result in 3 and 0 queries respectively on the P@10, %no measures and MAP. P@10 represent the values of Precision at Rank 10 P@10), %no measures represent the percentage of queries with no relevant documents in the top ten retrieved and MAP represents Mean Average Precision of the queries. The results show the proposed system have capability to demote negative documents and move up the relevant documents in the ranking list with positive indicator and its capability to recall unseen document with the application of ontology in text retrieval. For the future works, the researcher would like to apply the usage of new ranking indicator such as reliability score from the expert and the lay users of the Domain Specific Retrieval of Malay Translated Hadith.

Text representation plays an important role in text classification. Commonly, text representation uses the term frequency technique. Hadith texts consist of two parts; they are the chain of narrators and the content. The term frequency technique is usually used for the content text representation. This research explains the text representation for chain of narrators in hadith texts. The chain of narrators was depicted using graph technique as text representation. A total of 18 hadith texts were used in representing chain of narrators as text representation. The narrator's name and relationships between narrators extracted from hadith texts which produced 82 narrator names and 85 connections between narrators. The 82 names were used as nodes, while the 85 connections as the relationships. The text representation graph subsequently used in the hadith text classification research based on chain of narrators.

Ranking is likely the most important process of an Information Retrieval (IR) system that will be used to evaluate and measure the effectiveness of an IR system. This paper aims to produce the implementation of Fuzzy Logic Controller of Mamdani-type Fuzzy Inference System for defining the ranking function by using the BM25 Model in the Malay IR System that also includes the Malay Stemmer. The result of the ranking function then will be compared to the result of Vector Space Model that is also applied in Malay IR System and be evaluated using relevant document by the Hadith expert. The results showed that FBMIR has slightly outperformed Vector Space Model on 3 Topic Set of query results such as Iman,Ilmu and Wuduk on the Precision at Rank 10 and the percentage of no relevant document in the top ten retrieved measures.

Text document expresses enormous sort of information but it lacks the imposed structure of a traditional database. Unstructured data, particularly free running text data has to be transformed into a structured data. Extracting information from text is part of NLP process. The implementation of the NER algorithm for NLP is normally influenced by the domain of the studies. Besides, there is no existing system that is designed to detect the types of named entity in hadith text; develop POS tags and rule based extraction for narrator's name in Hadith Text in the Malay language. The POS tags were developed from 1000 hadith texts. The POS tags were created involving a total of 256 words which is part of narrator's names. The rule based was developed to determine five types of narrator's chain. Further research will determine the relationship between each narrator and the construction of narration's chain.