International Journal on Data Science and Technology 2022; 8(1): 22-35 http://www.sciencepublishinggroup.com/j/ijdst doi: 10.11648/j.ijdst.20220801.14 ISSN: 2472-2200 (Print); ISSN: 2472-2235 (Online) Customized Learning in Online Tutoring Systems by Mining Learning Units from Tasks and Examples Ritu Chaturvedi 1,* , Christie I. Ezeife 2 1 School of Computer Science, University of Guelph, Guelph, Canada 2 School of Computer Science, University of Windsor, Windsor, Canada Email address: chaturvr@uoguelph.ca (R. Chaturvedi) * Corresponding author To cite this article: Ritu Chaturvedi, Christie I. Ezeife. Customized Learning in Online Tutoring Systems by Mining Learning Units from Tasks and Examples. International Journal on Data Science and Technology. Vol. 8, No. 1, 2022, pp. 22-35. doi: 10.11648/j.ijdst.20220801.14 Received: February 9, 2022; Accepted: March 10, 2022; Published: March 30, 2022 Abstract: In recent years, technology has enabled Universities and Colleges to offer web-based courses, in which, teachers (or experts) design, curate and upload all course material required to teach the course online so that students can learn at their own pace, time and location. This research proposes a tutoring framework called Example Recommendation System (ERS) that is based on example-based learning (EBL) instructional method. ERS focuses on students devoting their time and cognitive capacity to studying worked-out examples so that they can enhance their learning and apply it to graded tasks assigned to them. ERS uses regular expression analysis to extract basic learning units (LU) (e.g. scanf is a LU in C programming) from all task solutions and worked-out examples and represents this knowledge in vector space. Then, these vectors are mined to generate a customized list of worked-out examples for each assigned task. The prime contribution of ERS’s extraction module is its extendibility to new domains without requiring highly trained experts. Besides extendibility, ERS extracts LUs with 81% correctness for the domain of “Programming in C” and 95% for domain of “Programming in Miranda”. ERS’s data mining model used for customization has 93% accuracy and 88% f score. ERS’s educational impact is also evident from experiments that show that students score an average of 89% in tasks for which they use ERS’s recommended worked-out examples, as opposed to an average of 73% for those tasks that students attempt without ERS’s assistance. Keywords: Customized Learning, ITS, Domain Model, Tasks and Examples, Knowledge Extraction, Regular Expressions, K-nearest Neighbors 1. Introduction There are several diverse learning environments to teach a course in today’s technological world such as traditional in-class, distance learning, web-based online systems and blended environments that combine classroom teaching and web-based technology. According to Moore’s definition [1], distance learning is a form of instruction in which the instructor and learner need not be at the same place at any time for the instructions to be delivered. Online learning is a newer version of distance learning which uses technology (such as the web) and shows some transformation of an individual’s experience into the individual’s knowledge using different levels of interactivity. For example, if student s1 has browsed a resource (such as a worked-out example on adding 2 fractions) n number of times (s1’s experience), then s1 is assumed to have mastered the resource (s1’s knowledge). Examples of commonly used online learning environments are Learning Management Systems (e.g. Blackboard [2])) and Intelligent Tutoring Systems (ITS) (e.g. Wayang Outpost [3]). For an ITS to achieve the core functionalities of adaptation and intelligence, it requires to capture student data that defines both their learning behavior (e.g. time spent on a worked-out example) and their knowledge on the subject taught by the ITS (e.g. marks in a test or task). It also requires to store and manage its domain resources efficiently. Section 1.1 explains briefly the domain and student components required by any ITS.