A Stackelberg Game Approach for Incentivizing Participation in Online Educational Forums with Heterogeneous Student Population

Increased interest in web-based education has spurred the proliferation of online learning environments. However, these platforms suffer from high dropout rates due to lack of sustained motivation among the students taking the course. In an effort to address this problem, we propose an incentive-based, instructor-driven approach to orchestrate the interactions in online educational forums (OEFs). Our approach takes into account the heterogeneity in skills among the students as well as the limited budget available to the instructor. We first analytically model OEFs in a non-strategic setting using ideas from lumpable continuous time Markov chains and compute expected aggregate transient net-rewards for the instructor and the students. We next consider a strategic settingwherewe use the rewards computed above to set up a mixed-integer linear program which views an OEF as a single-leader-multiplefollowers Stackelberg game and recommends an optimal plan to the instructor for maximizing student participation. Our experimental results reveal several interesting phenomena including a striking non-monotonicity in the level of participation of students vis-a-vis the instructor’s arrival rate. Introduction With the explosive growth of the Internet, the area of education has undergone a massive transformation in terms of how students and instructors interact in a classroom. Online learning environments now constitute a very important part of any academic course. Further, online education has attracted the interest of the research community due to the immense popularity of the massive open online courses (MOOCs) offered by platforms like Coursera, edX, Udacity, etc. As of January 17, 2014, Coursera students voiced themselves in 590,000 discussion threads in the education forums for a total of 343,014,912 minutes of learning across 571 courses (Coursera 2014). However, empirical studies have repeatedly shown that the dropout rates in the online courses are very high (Fowler 2013) mainly due to a lack of sustainedmotivation among the enrolled students. An important, but often under-utilized component of an online classroom is the online educational forum (OEF) where students and instructors discuss various administrative and technical aspects of the course (Andresen 2009; Mazzolini andMaddison 2003). The objective of our work is to propose Copyright c © 2015, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. an instructor-driven approach to orchestrate the activities of OEFs by designing optimal incentives to enhance studentinstructor participation in these OEFs. Incentive design plays an important role in encouraging participation among students in these educational forums. As part of a case study, we analysed the data collected from two online educational forums which were part of the Game Theory (E1 254) in the Department of Computer Science and Automation, Indian Institute of Science, for two different terms. The primary difference between these two terms was that there were no incentives offered to students participating in the Spring 2012 term while in the Spring 2014 term, students were offered incentives (a certain percentage of marks based on the reward points accumulated by the student) to participate actively to openended (or discussion type) questions posted on the Piazza forum associated with the course. We observed an increased participation of students in the incentive-based course than when there were no incentives offered (See Figure 1) which is an indication of importance of appropriate incentives in driving up the participation levels in the course.