Results 1 -
8 of
8
Sentiment Analysis in MOOC Discussion Forums: What does it tell us?
"... Sentiment analysis is one of the great accomplishments of the last decade in the field of Language Technologies. In this paper, we explore mining collective sentiment from forum posts in a Massive Open Online Course (MOOC) in order to monitor students ’ trending opinions towards the course and major ..."
Abstract
-
Cited by 10 (2 self)
- Add to MetaCart
(Show Context)
Sentiment analysis is one of the great accomplishments of the last decade in the field of Language Technologies. In this paper, we explore mining collective sentiment from forum posts in a Massive Open Online Course (MOOC) in order to monitor students ’ trending opinions towards the course and major course tools, such as lecture and peer-assessment. We observe a correlation between sentiment ratio measured based on daily forum posts and number of students who drop out each day. On a user-level, we evaluate the impact of sentiment on attrition over time. A qualitative analysis clarifies the subtle differences in how these language behav-iors are used in practice across three MOOCs. Implications for research and practice are discussed.
III. Predicting Instructor’s Intervention in MOOC Forums
- In Proc. of ACL ’14 (Volume 1: Long Papers
, 2014
"... 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 designe ..."
Abstract
-
Cited by 2 (0 self)
- Add to MetaCart
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.
Learning instructor intervention from MOOC forums
- In Proceedings of the 8th International Conference on Educational Data Mining
, 2015
"... With large student enrollment, MOOC instructors face the unique challenge in deciding when to intervene in forum discussions with their limited bandwidth. We study this problem of instructor inter-vention. Using a large sample of forum data culled from 61 courses, we design a binary classifier to pr ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
With large student enrollment, MOOC instructors face the unique challenge in deciding when to intervene in forum discussions with their limited bandwidth. We study this problem of instructor inter-vention. Using a large sample of forum data culled from 61 courses, we design a binary classifier to predict whether an instructor should intervene in a discussion thread or not. By incorporating novel in-formation about a forum’s type into the classification process, we improve significantly over the previous state-of-the-art. We show how difficult this decision problem is in the real world by validating against indicative human judgment, and empirically show the problem’s sensitivity to instructors ’ intervention prefer-ences. We conclude this paper with our take on the future research issues in intervention.
Identifying At-Risk Students in Massive Open Online Courses
"... Massive Open Online Courses (MOOCs) have received widespread attention for their potential to scale higher education, with multiple platforms such as Coursera, edX and Udacity recently appearing. Despite their suc-cesses, a major problem faced by MOOCs is low com-pletion rates. In this paper, we exp ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
Massive Open Online Courses (MOOCs) have received widespread attention for their potential to scale higher education, with multiple platforms such as Coursera, edX and Udacity recently appearing. Despite their suc-cesses, a major problem faced by MOOCs is low com-pletion rates. In this paper, we explore the accurate early identification of students who are at risk of not complet-ing courses. We build predictive models weekly, over multiple offerings of a course. Furthermore, we envision student interventions that present meaningful probabil-ities of failure, enacted only for marginal students. To be effective, predicted probabilities must be both well-calibrated and smoothed across weeks. Based on logis-tic regression, we propose two transfer learning algo-rithms to trade-off smoothness and accuracy by adding a regularization term to minimize the difference of failure probabilities between consecutive weeks. Experimental results on two offerings of a Coursera MOOC establish the effectiveness of our algorithms.
Your click decides your fate: Inferring Information Processing and Attrition Behavior from MOOC Video Clickstream Interactions
- Proceedings of the 2014 Empirical Methods in Natural Language Processing Workshop on Modeling Large Scale Social Interaction in Massively Open Online Courses
, 2014
"... In this work, we explore video lec-ture interaction in Massive Open Online Courses (MOOCs), which is central to stu-dent learning experience on these educa-tional platforms. As a research contribu-tion, we operationalize video lecture click-streams of students into cognitively plau-sible higher leve ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
In this work, we explore video lec-ture interaction in Massive Open Online Courses (MOOCs), which is central to stu-dent learning experience on these educa-tional platforms. As a research contribu-tion, we operationalize video lecture click-streams of students into cognitively plau-sible higher level behaviors, and construct a quantitative information processing in-dex, which can aid instructors to better un-derstand MOOC hurdles and reason about unsatisfactory learning outcomes. Our re-sults illustrate how such a metric inspired by cognitive psychology can help answer critical questions regarding students ’ en-gagement, their future click interactions and participation trajectories that lead to in-video & course dropouts. Implications for research and practice are discussed. 1
Uncovering Hidden Engagement Patterns for Predicting Learner Performance in MOOCs
"... Maintaining and cultivating student engagement is a prereq-uisite for MOOCs to have broad educational impact. Un-derstanding student engagement as a course progresses helps characterize student learning patterns and can aid in minimiz-ing dropout rates, initiating instructor intervention. In this pa ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Maintaining and cultivating student engagement is a prereq-uisite for MOOCs to have broad educational impact. Un-derstanding student engagement as a course progresses helps characterize student learning patterns and can aid in minimiz-ing dropout rates, initiating instructor intervention. In this paper, we construct a probabilistic model connecting student behavior and class performance, formulating student engage-ment types as latent variables. We show that our model iden-tifies course success indicators that can be used by instructors to initiate interventions and assist students. Author Keywords MOOC, learner engagement, probabilistic modeling
Peer Influence on Attrition in Massive Open Online Courses
"... In this work, we investigate the role of relational bonds in keeping students engaged in online courses. Specifically, we quantify the manner in which students who demonstrate similar behavior patterns influence each other’s commitment to the course through their interaction with them either ex-plic ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
In this work, we investigate the role of relational bonds in keeping students engaged in online courses. Specifically, we quantify the manner in which students who demonstrate similar behavior patterns influence each other’s commitment to the course through their interaction with them either ex-plicitly or implicitly. To this end, we design five alternative operationalizations of relationship bonds, which together al-low us to infer a scaled measure of relationship between pairs of students. Using this, we construct three variables, name-ly number of significant bonds, number of significant bonds with people who have dropped out in the previous week, and number of such bonds with people who have dropped in the current week. Using a survival analysis, we are able to measure the prediction strength of these variables with respect to dropout at each time point. Results indicate that higher numbers of significant bonds predicts lower rates of dropout; while loss of significant bonds is associated with higher rates of dropout.
Semi-automatic annotation of MOOC forum posts
"... Abstract. Massive online open courses ’ (MOOCs’) students who use discussion forums have higher chances of finishing the course. However, little research has been conducted for understanding the underlying fac-tors. One of the reasons which hinders the analysis is the amount of manual work required ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract. Massive online open courses ’ (MOOCs’) students who use discussion forums have higher chances of finishing the course. However, little research has been conducted for understanding the underlying fac-tors. One of the reasons which hinders the analysis is the amount of manual work required for annotating posts. In this paper we use ma-chine learning techniques to extrapolate small set of annotations to the whole forum. These annotations not only allow MOOC producers to sum-marize the state of the forum, but they also allow researchers to deeper understand the role of the forum in the learning process. 1
