Retrieval Performance for Malay Quran

Information Retrieval (IR) plays an important role in retrieving information related to the user’s query. IR relies on finding relevant data from a set of knowledge resources, such as the Quran. Finding information from the Quran can be based on metadata, indexing, or other content-based methods. The Quran is the most widely read book in the world and automating knowledge retrieval from this religious book in general is very challenging. One of the challenging tasks is when the Quran has been translated into various languages around the world by Muslim experts, such as Malay. This has led to the development of a number of search applications in multiple languages, which can retrieve knowledge based on keywords. Retrieving the knowledge from the Quran using keywords has several fundamental problems. In many cases, the searching cannot retrieve the relevant concept or knowledge and verses. Therefore this research investigated the existing problems related to the study of Quran and studies the current search techniques used in research on the Quran, especially the Malay Quran. This research will help researchers understand and learn the current scenario of research on the Quran. Keyword: The Quran; Malay Quran; Semantic Search; Ontology; Information Retrieval. The Quran is fundamental to all Muslims because it contains comprehensive guidance to Muslims in all aspects of life. Muslims are required to read and learn not only the Quran but the meaning of Quran in languages they understand. This will help Muslims to perform their daily routine efficiently. Nowadays, people are looking for the easiest ways to learn the Quran. Many search applications have been built to facilitate the retrieval of knowledge from the Quran. Current approaches that can be exploited for searching and retrieving information from Quran use semantic-based and keyword-based techniques. The semantic-based technique is a concept-based search tool that retrieves results based on word meaning, or concept match, whereas the keyword-based technique returns results based on letters matching word(s) as queries (Alqahtani & Atwell, 2016). At the moment, most Quran search tools employ the keyword search technique. Information Retrieval (IR) plays an important role in retrieving information related to the user’s query. The creation of computer and internet has made easier and faster the task of retrieving information. Despite of that, there are still issues pertaining retrieving information. For example, if a International Journal on Islamic Applications in Computer Science And Technology, Vol. 5, Issue 2, June 2017, 13-25 14 user types “Malay Quran” in a search engine, it will retrieve many results. Although this contains relevant information required by the user, it is hard for the user to look at all links. If a user limits the search to a specific version of Malay Quran, the user may loose a few other links that contains valuable information about the Quran (Wahid, 2014). The study of Ullah Khan et al., (2013) highlighted that searches and retrieval of knowledge in the Quran is sometimes unclear and less accurate due to the non-implementation of dynamic ways for retrieving knowledge or verses. Furthermore, the present way of searching in the Quran is not based on knowledge classification (Ullah Khan et al., 2013). Therefore, this shows that there are weaknesses in searching and retrieving the verses in the Quran due to the non-use of appropriate techniques. In conjunction with that, this research investigates the existing problems related to the study of the Quran and studies the current search techniques used in research on the Quran, especially the Malay Quran. 2.1 Information Retrieval Information Retrieval (IR) can be defined as discovering information that meets an information need using expansive accumulations of text usually stored on computers (Manning et al., 2008). At the beginning of the emergence of IR, only a few people were involved directly with retrieval and searching process such as librarians, paralegals etc. (Baeza-Yates & Ribeiro-Neto, 2011). Presently the situation has changed and a huge number of people now consistently engage with IR when they use World Wide Web (WWW) search tools, for instance, Google or Yahoo. According to Baeza-Yates & Ribeiro-Neto (2011), the main goal of IR is to retrieve all documents relevant to a user’s query, while at the same time retrieving as few non-relevant documents as possible. It is a balancing act between finding a large amount of potentially-relevant information and losing some potentially valuable information (Wahid, 2014).