Journal of Control Science and Engineering 4 (2016) 36-49 doi:10.17265/2328-2231/2016.01.004 Linked Data-based Slide Repository: The Episodic Slide Retrieval Using the Episodic Keyword Networks Tomohiro Iwasa, Yudai Kato, Shun Shiramatsu, Tadachika Ozono and Toramatsu Shintani Department of Computer Science and Engineering, Graduate School of Engineering, Nagoya Institute of Technology, Gokiso-cho, Showa-ku, Nagoya, Aichi 466-8555, Japan Abstract: This paper focuses on developing a system that allows presentation authors to effectively retrieve presentation slides for reuse from a large volume of existing presentation materials. We assume episodic memories of the authors can be used as contextual keywords in query expressions to efficiently dig out the expected slides for reuse rather than using only the part-of-slide-descriptions-based keyword queries. As a system, a new slide repository is proposed, composed of slide material collections, slide content data and pieces of information from authors’ episodic memories related to each slide and presentation together with a slide retrieval application enabling authors to use the episodic memories as part of queries. The result of our experiment shows that the episodic memory-used queries can give more discoverability than the keyword-based queries. Additionally, an improvement model is discussed on the slide retrieval for further slide-finding efficiency by expanding the episodic memories model in the repository taking in the links with the author-and-slide-related data and events having been post on the private and social media sites. Key words: Slide retrieval, linked data-based slide repository, episodic keyword networks, linked data, episodic memories, social media, life event. 1. Introduction Our goal in this study is to create a new presentation slide management method and a system to support the presentation authors with easily finding out the reusable presentation slides that have been created before for new presentation opportunities. Reuse of the existing presentation slides is commonly accepted in authoring the new presentation and alleviates the time and effort rather than cases to create the presentation slides from zero. Actually, individuals, teams and groups such as laboratories, and enterprises frequently create new presentation slides based on the existing presentation slides. For example, some researchers reuse one’s own existing presentation slides and others reuse some other’s presentations. According to an online survey, 105 out of 108 survey participants (i.e. 97%) are reported on the reusing presentation content [1]. However, finding the desired presentation slides from a large number of Corresponding author: Tomohiro Iwasa, Ph.D. Candidate. existing presentation materials stored in the file servers is often a hard work especially for authors in a group at a large organization that may maintains collections of hundreds of presentations [2]. To address the desirability in effectively finding the reusable presentation slides, we propose to make use of the episodic information as cues in the presentation slide search process because the episodic memories of the authors that have been associated with each slide would be easily recalled rather than the specific keywords being contained in the presentation slide materials. Concretely, we construct Episodic Keyword Networks in the form of an episode-based relational data model and slide contents, composed of slides, episodic information such as matters relevant to the subject of slides to be reminded, some personal life events or social events occurred when the slides were created, and their links. We call such links as Linked Data. According to the the Linked Data community web site http://linkeddata. D DAVID PUBLISHING