EdRecSys 2017

The 4th International Workshop on Educational Recommender Systems (EdRecSys) held in conjunction with the ACM Conference on User Modelling, Adaptation and Personalization (UMAP’17), July, 2017, Bratislava, Slovakia

URL: https://edrecsys2017.wordpress.com/

Workshop chairs (in alphabetical order):

Kurt Driessens, University of Maastricht, The Netherlands, kurt.driessens@maastrichtuniversity.nl
Irena Koprinska, University of Sydney, Australia, irena.koprinska@sydney.edu.au
Olga C. Santos, Spanish National University for Distance Education, Spain, ocsantos@dia.uned.es
Evgueni Smirnov, University of Maastricht, The Netherlands, smirnov@maastrichtuniversity.nl
Kalina Yacef, University of Sydney, Australia, kalina.yacef@sydney.edu.au
Osmar Zaiane, University of Alberta, Canada, zaiane@ualberta.ca

Program committee (in alphabetical order):

José Luis Balcázar, BarcelonaTech, Spain
Jesus Boticario, Spanish National University for Distance Education, Spain
Francois Bouchet, University of Paris 6, France
Robin Burke, DePaul University, USA
Hendrik Drachsler, Open University of the Netherlands, The Netherlands
Mehdi Elahi, Free University of Bozen-Bolzano, Italy
Sabine Graf, Athabasca University, USA
Guibing Guo, Northwestern University, China
Judy Kay, University of Sydney, Australia
Pythagoras Karampiperis, Agroknow Technologies, Greece
Amruth Kumar, Ramapo College of New Jersey, USA
Agathe Merceron, Beuth University of Applied Sciences, Germany
Mykola Pechenizkiy, Eindhoven University of Technology, The Netherlands
Sole Pera, Boise State University, USA
Mimi Recker, Utah State University, USA
Sergey Sosnovsky, German Centre for Artificial Intelligence, Germany
Jerry Spanakis, University of Maastricht, The Netherlands
Marko Tkalčič, Free University of Bozen-Bolzano, Italy
Katrien Verbert, Catholic University Leuven, Belgium
Yong Zheng, Illinois institute of Technology, USA

Accepted Papers

Personalized Behavior Recommendation: A case study of the applicability to 13 courses on edX
Steven Tang and Zach Pardos

Abstract: Individualized and personalized learning has taken on different forms in the context of digital learning environments. In intelligent tutoring systems, individualization is focused on estimation of the cognitive mastery of the student and the speed at which the student progresses through the material is conditioned on her individual rate of mastery. In prior work, a recommendation framework based on learner behaviors, rather than learner’s cognitive abilities, was proposed and developed. This framework trained a behavior model on millions of previous student actions in order to estimate how a future learner might behave. This behavior model can incorporate the amount of time spent on each course page, such that the model can take into account a learner’s previous behaviors and provide a specific course page recommendation to where the learner may want to go next where they can be expected to spend a significant amount of time on. We stipulate that this approach touches on factors more aligned with personalization, since the prediction of behavior is an aggregation of the student’s cognitive abilities, affective state, and preferences. This model was applied to a hand-picked pair of MOOC offerings where model results were expected to be favorable. In this paper, we investigate the suitability of this behavioral prediction approach by applying it to an expanded set of 13 UC Berkeley MOOCs run on the edX platform. Preliminary results from applying the time-augmented RNN behavior model approach to several courses are presented and compared to baseline course-syllabus results. These findings contribute to the discussion of when and in what context this form of personalized recommendation is appropriate in MOOCs.

Discovering Hidden Course Requirements and Student Competences from Grade Data
Mara Houbraken, Chang Sun, Evgueni Smirnov and Kurt Driessens

Abstract: This paper presents a data driven approach to autonomous course-competency requirement and student-competency level discovery starting from the grades obtained by a sufficiently large set of students. The approach relies on collaborative filtering techniques, more precisely matrix decomposition, to derive the hidden competency requirements and levels that together should be responsible for observed grades. The discovered hidden features are translated into human understandable competencies by matching the computed values to expert input. The approach also allows for grade prediction for so far unobserved student course combinations, allowing for personalized study planning and student guidance. The technique is demonstrated on data from a “Data Science and Knowledge Engineering” bachelor, Maastricht University.

Comparing peer recommendation strategies in a MOOC
Hugues Labarthe, François Bouchet, Kalina Yacef and Rémi Bachelet

Abstract: Lack of social relationship has been shown to be an important contribution factor for attrition in Massive Open Online Courses (MOOCs). Helping students to connect with other students is therefore a promising solution to alleviate this phenomenon. Fol-lowing up on our previous research showing that embedding a peer recommender in a MOOC had a positive impact on students’ engagement in the MOOC, we compare in this paper the impact of three different peer recommenders.: one based on socio-demographic criteria, one based on current progress made in the MOOC, and the last one providing random recommendations. We report our results and analysis (N= 2025 students).

Course-Driven Teacher Modeling for Learning Objects Recommendation in the Moodle LMS
Carlo De Medio, Fabio Gasparetti, Carla Limongelli, Filippo Sciarrone and Marco Temperini

Abstract: During the phases of course construction, in a Learning Management System,  teacher can be valuably helped by system’s recommendations about the learning objects to use in the course. A usual protocol is in that the teacher performs a query, looking for suitable learning material, and the system proposes a list of learning objects, with information shown for each one; then the teacher is supposed to make her choice, basing on the displayed information.  Here we present a Recommender System for Learning Objects retrieved from Learning Objects Repositories, that is based on a “social teacher model”, based on the similarities with the teacher in the system, and evolving with it. The proposed system is available as a Moodle plug-in. In the paper we show the details of the information decorating the learning objects retrieved after a query, the definition of the teacher model, and the similarity concept that allows to polarize the recommendations.

 RUTICO: Recommending successful learning paths Under TIme COnstraints
Amir Hossein Nabizadeh, Alipio Mario Jorge and Jose Paulo Leal
Abstract: Nowadays using E-learning systems such as Intelligent Tutoring Systems (ITS) that support users to learn subjects has become a routine. Despite the availability and the advantages of these systems, they ignore the learners’ time limitation for learning a subject. In this paper we propose RUTICO, that recommends successful learning paths with respect to a learner’s knowledge background and under a time constraint. In RUTICO, which is an example of Long Term goal Recommender Systems (LTRS), after locating a learner in the course graph, it utilizes a Depth-first search (DFS) algorithm to find all possible paths for a learner given a time restriction. RUTICO also estimates learning time and score for the paths and finally, it recommends a path with the maximum score that satisfies the learner time restriction. In order to evaluate the ability of RUTICO in estimating time and score for paths, we used the Mean Absolute Error and Error. Our results show that we were able to generate a learning path that maximizes a learner’s score under a time restriction.

Content Wizard: Concept-based Recommender System for Instructors of Programming Courses
Hung Chau, Jordan Barria-Pineda and Peter Brusilovsky

Abstract: Authoring an adaptive educational system is a complex process which involves allocating a large range of educational contents within a fixed sequence of units. Given this scenario, in this paper we describe Content Wizard, a concept-based recommender system for recommending learning materials that meet the instructor’s pedagogical goals during the creation of an online programming course. Here, the instructors are asked to provide a set of code examples that jointly reflect the learning goals associated with each course unit. The Wizard is built on the top of our course authoring tool, and it helps to decrease the time instructors spend on the task and to maintain the coherence of the sequential structure of the course. It also provides instructors with additional information to identify the contents that might be not appropriate for the unit they are creating. We conducted an off-line study with data collected from an introductory Java course previously taught at the University of Pittsburgh, in order to evaluate the practicalness and effectiveness of the system. We found that the proposed recommendation’s performance is relatively close to the teacher expectation in creating a computer-based adaptive course.

Recommending Programming Languages By Identifying Skill Gaps Using Analysis of Experts – A Study Of Stack Overflow
Obaro Odiete, Tanvi Jain, Ifeoma Adaji, Julita Vassileva and Ralph Deters

Abstract: The increasing variety of programming languages available to computer programmers has led to the discussion of what language(s) should be learned. A key point in the choice of a programming language is the availability of support from experienced programmers. In this paper, we explore the use of graph theory in recommending programming languages to novice and expert programmers in a question and answer collaborative learning environment, Stack Overflow. Using social network analysis techniques, we investigate the relationship between experts (using an expertise graph) in different programming languages in order to identify what languages can be recommended to novice and experienced programmers. In addition, we explore the use of the expertise graph in inferring the importance of a programing language to the community. Our results suggest that programming languages can be recommended within organizational borders and programming domains. In addition, a high number of experts in a programming language does not always mean that the language is popular. Furthermore, disconnected nodes in the expertise graph suggest that experts in some programming languages are primarily on Stack Overflow to support that language only and do not contribute to questions or answers in other languages. Finally, developers are comfortable with mastering a single, general purpose language. The results of our study can help educators and stake holders in computer education to understand what programming languages can be suggested to students and what languages can be taught and learned together.