Predicting Instructor's Intervention in MOOC forums

Abstract

Instructor intervention in student discussion forums is a vital component in Massive Open Online Courses (MOOCs), where personalized interaction is limited. This paper introduces the problem of predicting instructor interventions in MOOC forums. We propose several prediction models designed to capture unique aspects of MOOCs, combining course information, forum structure and posts content. Our models abstract contents of individual posts of threads using latent categories, learned jointly with the binary intervention prediction problem. Experiments over data from two Coursera MOOCs demonstrate that incorporating the structure of threads into the learning problem leads to better predictive performance.

Prediction Method based DRSA to Improve the Individual Knowledge Appropriation in a Collaborative Learning Environment: Case of MOOCs

“…Finally, we cite the work of Chaturvedi et al [5] that proposes a model to identify the situation when the MOOC instructor has to intervene in the forum threads. The purpose is to help students get an answer from the instructor in order to provide them with the effective knowledge they need.…”

Participation Prediction and Opinion Formation in MOOC Discussion Forum

“…Their results show that instructors' active participation can increase the discussion volume but cannot mitigate the participation decline [18]. Chaturvedi et al employed latent categories to abstract contents of posts, and utilized event chain based model to predict the instructors' intervention in MOOC discussion forum [6]. Skrypnyk et al conducted social network analysis on Twitter-based interactions and confirmed that the teachers preserved a high level of influence over the flow of information [7].…”

“…Recently, the interaction behaviour in the forum, as a data source of learning analysis, is getting more and more attention. These topics not only include correlation between the forum participation and final gains [2]- [5], but also include the instructors' role and intervention in the forum [6]- [8].…”

Learning Effect Analysis Based on Association Rules in Online Education

“…The "China Basic Education Big Data Development Blue Book (2015)" Conference and Education Big Data Summit Forum held in Beijing Normal University in 2016 [2]. In addition, according to the statistics, Coursera, edX, and Udacity which are three pioneer MOOC platforms provide thousands of courses and draw more than 100,000 registrants each course [5,6]. And Tsinghua University also officially launched the first Chinese version of the MOOC platform -"xuetangX" [4,8].…”

“…Understanding the learning process can significantly design better courses and improve the learning effect. Despite several relevant studies at present, such as, learning behavior analysis [3], student classification and engagement analysis [6,7], there are few systematical studies on the factors of affecting learning effects in online learning. More specifically, how to use the existing learning theory and data mining to observe which factors are related to students learning efficiency?…”