1939-1382 (c) 2019 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information. This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/TLT.2019.2937084, IEEE Transactions on Learning Technologies Maedeh Mosharraf, Fattaneh Taghiyareh Abstract—Rapid development of Open Educational Resources (OER) is often motivated by a new educational paradigm. This paradigm tends to cover current challenges such as reusing, goal- oriented remixing, revising, and redistributing OER. This paper proposes a system to automatically remix, which is a step towards automatic course generation. This system uses an Agent-Based Modeling (ABM) approach to profile OER and simulate the process of selecting and linking the appropriate ones. Each resource profile provides us with metadata that shows its domain and is completed using an appropriate ontology before agents’ interactions. ABM enables cooperation between OER to satisfy requirements of the input syllabus. Using the interaction ability, the most compatible agents, which cover the concepts of the input syllabus, can be linked. The efficiency of the proposed method is evaluated through applying the implemented system on two datasets: ARIADNE and SlideShare. In our experimental results on OER related to the domain of eLearning we report on the system precision and user satisfaction. Our approach is generic; it can be used with any OER repository and any content management system with free reuse and remix licenses. Index Terms—Agent-Based Modeling, Computer-assisted instruction, Computer uses in education, E-learning tools, Open Educational Resources, OER I. INTRODUCTION ncreasing popularity of Open Educational Resources (OER) brings availability and accessibility of OER-specific repositories and tools as prerequisites in the world of education. MIT as a pioneer in providing OER announced the opening of course materials for the public in the open courseware initiative in 2001 [1]. Considering the importance of OER and the necessity for being widely provided and spread, endorsed by UNESCO in 2002 [2], other providers started to make their educational materials such as different courseware and learning modules freely accessible. In addition, many scholarly discourses, research papers, and technical innovations have been accomplished around OER. According to most of the published documentations, OER are contents and tools with the possibility of Reuse, Redistribution, Revision, and Remixing, which create new opportunities and challenges not presented in many works [3], [4]. Each of these R’s represents an increasing level of openness, so that [5] arranges these features of OER as a framework titled 4Rs. To maximize the openness of a resource, which is a necessity for revising and remixing processes, it should be licensed by the least restrictive license possible (such M. Mosharraf and F. Taghiyareh are with the Technology Enhanced Learning Laboratory, Department of Computer and Electrical Engineering, University of Tehran, North Kargar st., Tehran, Iran. P.O.Box: 14395-515, (e- mail: m.mosharraf@ut.ac.ir, ftaghiyar@ut.ac.ir) as the Creative Commons Attribution). Involving the beneficial possibilities such as 4Rs, which are brought by the concept of openness, leads to the potential use of OER in different learning programs. Reusing existing OER as the most basic level of openness [5] can save significant time and effort for course developers. Revising them provides the possibility of adaptation, modification, and translation. The possibility of both reusing and revising provides the remixing option, which allows people to take two or more existing resources and combine them to create a new one. Finally, the redistributing facility engages people with sharing the work with others and continues the cycle of OER. This paper aims to implement a system which provides the capability of automatic OER remixing. Using an Agent-Based Modeling (ABM) approach, this system profiles the OER extracted from different repositories. In this respect, each resource is matched to an agent that contains its profile information. The high number of OER and their profile elements, various concepts of input syllabus, and processes that put together the appropriate OER to compose a course make the agent-based approach a worthy choice. After interactions of agents to find appropriate pairs of OER, the process of linking is accomplished and a package containing the contents of a new course is created. Satisfying some requirements such as similarity in technical and educational criteria as well as related titles and learning outcomes is considered in the OER linking process. We claim that facilitating the process of appropriate selection and combination of OER by automatically remixing them will increase their usage. From another point of view, if our system will be able to accomplish a goal-oriented remix, there are many different areas which potentially may benefit. In corporate learning, it can be beneficial to produce project role-oriented courses for each employee according to his/her current projects as well as current role. In multidisciplinary courses, it would be easy to create a personalized course according to prior knowledge of each learner. In blended learning, it can facilitate providing appropriate contents according to students’ needs and proportional to be presented in classrooms. In advanced search systems, which need a phase of combining multiple documents to respond to a query, the approach can also be effective. The rest of the paper is organized as follows: In section 2, we have a look at the background of our work by introducing the concepts of OER and remix. Section 3 explains our ABM approach for automatic OER remixing. The system experiments are described in section 4. Section 5 describes the process of system assessment and compares it with two baseline experiments. Some further discussions are imparted in section 6, and finally the paper is concluded in section 7. Automatic Syllabus-Oriented Remixing of Open Educational Resources Using Agent-Based Modeling I