Evaluation Of Search Engines In Retrieving Relevant Document On Prophet Muhammad

Main Article Content

Jide Hassan Oyebanji Zainab Binti Abu Bakar


The main purpose of this experiment is to explore the concept information retrieval on search engines. Identifying the search engine that returns the most relevant and accurate results is sought which best satisfies a number of queries regarding the prophet Muhammad(SAW). The concept of IR tries to achieve is to obtain relevant required information resources from a collection of information resources and at the same time, returning results with minimal irrelevant documents. An example of an IR system which is prevalently used today are search engines.
IR is the technology which is been used to power and make search engines as efficient as they are today. Over the decades, different companies have sprouted into existence developing their own search engine. With this, users have at their disposal different types of search engine, it is just a matter of preference that determines which search engine the users then intend to make use of. The concept of using search engines in retrieving documents has over the years gained a reputation by many and a reason for such rapid growth would be attributed to efforts and researches which have been made in order to make them very efficient. Amongst many of the things searched over the internet via the use of search engine are matters and questions which has to do with religion. Narrowing it down to the context of this dissertation, the person of Prophet Muhammad is the scope of this research. Many a times, individuals intending to have certain question answered about him resort to the search engine online. But a question which arises is that how do users then get to know what search engine of repute would best give in return relevant documents from site links. Absence of such knowledge leaves the users confronted with the myriad of websites which the search engines gives in return and as a result, leaving the users with so many relevant and irrelevant documents. And this translates to an uncontrolled dissemination of wrong information’s about the prophet. During the course of the research, test collections about the prophet were explored. This experiment entailed trying to gather both relevant judgement documents as well as result documents gotten from some selected search engines. Then with these documents, some human and computational judgements were made to see examine the closeness of the search engine results in accurately answering the queries on the subject matter earlier stated. Although in writing this paper. the experiment is yet to be completed, so the initial three chapters would be discussed and then a summary explanation of the earlier stages of the experiment would be discussed and likewise a brief discussion of the expected results would be briefly discussed too.

Article Details

Artificial intelligence