A Comparsion Study Between Generic and Metadata Search Engines in an E-learning Environment Leyla Zhuhadar, Olfa Nasraoui, and Robert Wyatt Dept of Computer Engineering and Computer Science, University of Louisville, Louisville, KY, USA Office of Distance Learning, Western Kentucky University, Bowling Green, KY, USA Abstract— The huge explosion of the amount of infor- mation on the web makes it difficult for online students to find specific information with a specific media format unless a prior analysis has been made. In this paper, we present a comparison study between Generic and Metadata Search engines in a multimedia repository of lectures. Both Search engines were modified to index text, powerpoint, audio, video, podcast, and vodcast lectures. These lectures are stored in a prototype E-learning web- based platform. Each lecture in this platform has been tagged with metadata using the domain-knowledge of these resources. This comparison study was evaluated based on precision. Index Terms— Information Retrieval, Metadata, Search Engine, Ranking Algorithm, E-learning. I. I NTRODUCTION Nowadays, the Web contains billions of dynamic re- sources. Searching for information, which could be a docu- ment, an image, an audio, or a video file, a podcast, a vodcast, a blog, etc. from online repositories, such as digital libraries can be a difficult task in IR. Therefore, new techniques in IR emerged to increase the quality of searching. These techniques focused on three areas of interest: the capability of handling a new indexing format (which allows the indexing of images, audio, video, rss, etc.), enhancing the indexing to have a faster response time for queries and the quality of the information retrieval systems. Only minimal work has been done on proactively merging efforts from Information Retrieval (IR) with Education, such as [23], [5] which is not directly related to the E-learning domain research. The need for this synergy arises from the fact that the number of online students has been growing significantly; nearly 20% of all U.S. higher education students were taking at least one online course in the fall of 2006, and almost 3.5 million students were taking at least one online course during the fall 2006 term; a nearly 10% increase over the number reported the previous year, and an increase of 9.7% growth rate for online enrollments far exceeds the 1.5% growth of the overall higher education student population. These facts are based on a survey that represents the fifth annual report on the state of online learning in U.S. higher education. 1 In this paper, we present a metadata topic-driven search engine that uses Information Retrieval methods to enhance the indexing and searching of learning objects in an E-learning repository. The Search engine is embedded on top of a web-based platform to allow indexing of text, powerpoint, audio, video, podcast, and vodcast lectures. These lectures are stored in a prototype “HyperManyMedia” E-learning web-based platform. II. P REVIOUS WORK Recently, two notions of search engines started to gain popularity: the metadata search engine and the fo- cused/topical search engine. The metadata search engine is based on a metadata structure, which is “machine under- standable information about web resources” 2 . The metadata search engines have been studied intensively in [11], [18], [4], [6], [10], [12], [20]. On the other hand, focused/topical search engines were introduced for the first time in [3] and a great deal of research related to them has been presented in [4], [7], [13], [15], [16], [20], [22]. Our approach uses hybrid “metadata” and “topic-driven” mechanisms and it is capable of indexing and fetching many different media for- mat resources from text, powerpoint, audio, video, podcast, and vodcast. Since our search engine is built on top of the domain-knowledge of (E-learning), this knowledge represen- tation was extracted from the subject area, which combines topics and media formats about online resources. Finally, we mapped this knowledge into “metadata” to enhance the Educational (E-learning) search mechanism. We have organized the paper as follows. Sections 3 presents our methodology and implementation of a metadata search engine. Section 4 presents our results and evaluation measures. Section 5 includes our conclusions and future works and finally, section 6 provides the references. 1 http://www.sloan-c.org/publications/ survey/survey07.asp 2 http://www.w3.org/DesignIssues/Metadata