Capturing "attrition intensifying" structural traits from didactic interaction sequences of MOOC learners

Published on Oct 1, 2014 in EMNLP (Empirical Methods in Natural Language Processing)
· DOI :10.3115/V1/W14-4108
Tanmay Sinha12
Estimated H-index: 12
(CMU: Carnegie Mellon University),
Nan Li8
Estimated H-index: 8
(EPFL: École Polytechnique Fédérale de Lausanne)
+ 1 AuthorsPierre Dillenbourg64
Estimated H-index: 64
(EPFL: École Polytechnique Fédérale de Lausanne)
Sources
Abstract
This work is an attempt to discover hidden structural configurations in learning activity sequences of students in Massive Open Online Courses (MOOCs). Leveraging combined representations of video click- stream interactions and forum activities, we seek to fundamentally understand traits that are predictive of decreasing engagement over time. Grounded in the inter- disciplinary field of network science, we follow a graph based approach to success- fully extract indicators of active and passive MOOC participation that reflect persistence and regularity in the overall interaction footprint. Using these rich educational semantics, we focus on the problem of predicting student attrition, one of the major highlights of MOOC literature in the recent years. Our results indicate an improvement over a baseline n-gram based approach in capturing “attrition intensify- ing” features from the learning activities that MOOC learners engage in. Implications for some compelling future research are discussed.
Figures & Tables
Download
📖 Papers frequently viewed together
2014EMNLP: Empirical Methods in Natural Language Processing
4 Authors (Marius Kloft, ..., Niels Pinkwart)
2014EMNLP: Empirical Methods in Natural Language Processing
References17
Newest
Oct 1, 2014 in EMNLP (Empirical Methods in Natural Language Processing)
#1Tanmay Sinha (CMU: Carnegie Mellon University)H-Index: 12
#2Patrick Jermann (EPFL: École Polytechnique Fédérale de Lausanne)H-Index: 24
Last. Pierre Dillenbourg (EPFL: École Polytechnique Fédérale de Lausanne)H-Index: 64
view all 4 authors...
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-...
Source
Oct 1, 2014 in EMNLP (Empirical Methods in Natural Language Processing)
#1Carolyn Penstein Rosé (CMU: Carnegie Mellon University)H-Index: 54
#2George Siemens (UTA: University of Texas at Arlington)H-Index: 32
The shared task on Prediction of Dropout Over Time in MOOCs involves analysis of data from 6 MOOCs offered through Coursera. Data from one MOOC with approximately 30K students was distributed as training data and consisted of discussion forum data (in SQL) and clickstream data (in JSON format). The prediction task was Predicting Attrition Over Time. Based on behavioral data from a week’s worth of activity in a MOOC for a student, predict whether the student will cease to actively participate aft...
Source
Aug 1, 2014 in IRI (Information Reuse and Integration)
#1L.A. Rossi (SC: University of Southern California)H-Index: 7
#2Omprakash Gnawali (UH: University of Houston)H-Index: 26
In this work, we analyze the discussion threads from the forums of 60 Massive Open Online Courses (MOOCs) offered by Coursera and taught in 4 different languages. The types of interactions in such threads vary: there are discussions on close ended problems (e.g. solutions to assignments), open ended topics, course logistics, or just small talk among fellow students. We first study the evolution of the forum activities with respect to the normalized course duration. Then we investigate several la...
Source
Jul 27, 2014 in AAAI (National Conference on Artificial Intelligence)
#1Arti Ramesh (UMD: University of Maryland, College Park)H-Index: 7
#2Dan Goldwasser (UMD: University of Maryland, College Park)H-Index: 22
Last. Lise Getoor (UCSC: University of California, Santa Cruz)H-Index: 69
view all 5 authors...
Maintaining and cultivating student engagement is critical for learning. Understanding factors affecting student engagement will help in designing better courses and improving student retention. The large number of participants in massive open online courses (MOOCs) and data collected from their interaction with the MOOC open up avenues for studying student engagement at scale. In this work, we develop a framework for modeling and understanding student engagement in online courses based on stude...
#1Tanmay Sinha (CMU: Carnegie Mellon University)H-Index: 12
In this work, we explain the underlying interaction mechanisms which govern students' influence on each other in Massive Open Online Courses (MOOCs). Specifically, we outline different ways in which students can be negatively exposed to their peers on MOOC forums and discuss a simple formulation of learning network diffusion, which formalizes the essence of how such an influence spreads and can potentially lead to student attrition over time. We also view the limitations of our student modeling ...
#1Kalyan Veeramachaneni (MIT: Massachusetts Institute of Technology)H-Index: 28
#2Una-May O'ReillyH-Index: 31
Last. Colin Anthony TaylorH-Index: 26
view all 3 authors...
We examine the process of engineering features for developing models that improve our understanding of learners' online behavior in MOOCs. Because feature engineering relies so heavily on human insight, we argue that extra effort should be made to engage the crowd for feature proposals and even their operationalization. We show two approaches where we have started to engage the crowd. We also show how features can be evaluated for their relevance in predictive accuracy. When we examined crowd-so...
May 16, 2014 in ICWSM (International Conference on Weblogs and Social Media)
#1Miaomiao Wen (CMU: Carnegie Mellon University)H-Index: 16
#2Diyi Yang (CMU: Carnegie Mellon University)H-Index: 28
Last. Carolyn Penstein Rosé (CMU: Carnegie Mellon University)H-Index: 54
view all 3 authors...
While data from Massive Open Online Courses (MOOCs) offers the potential to gain new insights into the ways in which online communities can contribute to student learning, much of the richness of the data trace is still yet to be mined. In particular, very little work has attempted fine-grained content analyses of the student interactions in MOOCs. Survey research indicates the importance of student goals and intentions in keeping them involved in a MOOC over time. Automated fine-grained content...
#1Laci Mary Barbosa Manhães (UFRJ: Federal University of Rio de Janeiro)H-Index: 6
#2Sérgio Manuel Serra da Cruz (UFRRJ: Universidade Federal Rural do Rio de Janeiro)H-Index: 5
Last. Geraldo Zimbrão (UFRJ: Federal University of Rio de Janeiro)H-Index: 11
view all 3 authors...
Predicting the academic progress of student is an issue faced by many public universities in emerging countries. Although, those institutions stores large amounts of educational data, they fail to recognize the students that are in danger to leave the system. This paper presents a novel architecture that uses EDM techniques to predict and to identify those who are at dropout risk. This approach allows academic managers to monitor the progress of the students in each academic semester, identifyin...
Source
#1Carolyn Penstein Rosé (CMU: Carnegie Mellon University)H-Index: 54
#2Ryan Carlson (CMU: Carnegie Mellon University)H-Index: 5
Last. Jennifer Zoltners Sherer (University of Pittsburgh)H-Index: 7
view all 7 authors...
In this paper, we explore student dropout behavior in a Massively Open Online Course (MOOC). We use a survival model to measure the impact of three social factors that make predictions about attrition along the way for students who have participated in the course discussion forum.
Source
#1Jonathan Huang (Stanford University)H-Index: 32
#2Anirban Dasgupta (Yahoo!)H-Index: 76
Last. Marc D. Sanders (Stanford University)H-Index: 1
view all 5 authors...
Discussion forums, employed by MOOC providers as the primary mode of interaction among instructors and students, have emerged as one of the important components of online courses. We empirically study contribution behavior in these online collaborative learning forums using data from 44 MOOCs hosted on Coursera, focusing primarily on the highest-volume contributors---"superposters"---in a forum. We explore who these superposters are and study their engagement patterns across the MOOC platform, w...
Source
Cited By50
Newest
Online educational platforms increasingly allow learners to consume content at their own pace with on-demand formats, in contrast to the synchronous content of traditional education. Thus, it is im...
Source
#1Niki GitinabardH-Index: 6
#1Ahmed Ali Mubarak (Ibb University)H-Index: 3
#2Han Cao (SNNU: Shaanxi Normal University)H-Index: 3
Last. Salah A. M. Ahmed (SNNU: Shaanxi Normal University)H-Index: 1
view all 3 authors...
Analysis of learning behavior of MOOC enthusiasts has become a posed challenge in the Learning Analytics field, which is especially related to video lecture data, since most learners watch the same online lecture videos. It helps to conduct a comprehensive analysis of such behaviors and explore various learning patterns for learners and predict their performance by MOOC courses video. This paper exploits a temporal sequential classification problem by analyzing video clickstream data and predict...
Source
#1Bello Ahmad Muhammad (SNNU: Shaanxi Normal University)
#2Zhenqiang Wu (SNNU: Shaanxi Normal University)H-Index: 5
Last. Hafsa Kabir Ahmad (SNNU: Shaanxi Normal University)H-Index: 1
view all 3 authors...
Online learning has become increasingly popular in recent years. This interest in online education has provided us with many opportunities to research, the behavior of learners as it generates behavior data at large scale. By dynamically adapting learning, the automated identification of learning styles in online learning based on learner activity is a significant issue, in which many researchers have shown their interests as it improves learning output. In this paper, the collection of behavior...
Source
#1Jose Edmond Meku Fotso (University of Yaoundé)H-Index: 1
#2Bernabe Batchakui (University of Yaoundé)H-Index: 4
Last. George Okereke (UNN: University of Nigeria, Nsukka)H-Index: 1
view all 4 authors...
MOOCs (Massive Open Online Courses) are definitely one of the best approach to support the international agenda about inclusive and equitable education and lifelong learning opportunities for all (SDG4) [1]. A great deal universities and institutions offer valuable free courses to their numerous students and to people around the word through MOOC platforms. However, because of huge number of learners and data generated, learner’s behaviour in those platforms remain a kind of black box for learne...
Source
#1Qing Chen (HKUST: Hong Kong University of Science and Technology)H-Index: 7
#2Xuanwu Yue (HKUST: Hong Kong University of Science and Technology)H-Index: 3
Last. Huamin Qu (HKUST: Hong Kong University of Science and Technology)H-Index: 43
view all 7 authors...
The research on massive open online courses (MOOCs) data analytics has mushroomed recently because of the rapid development of MOOCs. The MOOC data not only contains learner profiles and learning outcomes, but also sequential information about when and which type of learning activities each learner performs, such as reviewing a lecture video before undertaking an assignment. Learning sequence analytics could help understand the correlations between learning sequences and performances, which furt...
Source
#1Byungsoo Jeon (CMU: Carnegie Mellon University)H-Index: 5
#2Namyong Park (CMU: Carnegie Mellon University)H-Index: 9
This paper addresses a key challenge in MOOC dropout prediction, namely to build meaningful representations from clickstream data. While a variety of feature extraction techniques have been explored extensively for such purposes, to our knowledge, no prior works have explored modeling of educational content (e.g. video) and their correlation with the learner's behavior (e.g. clickstream) in this context. We bridge this gap by devising a method to learn representation for videos and the correlati...
#1Byungsoo Jeon (CMU: Carnegie Mellon University)H-Index: 5
#2Namyong Park (CMU: Carnegie Mellon University)H-Index: 9
Last. Seojin Bang (CMU: Carnegie Mellon University)H-Index: 4
view all 3 authors...
Massive Open Online Courses (MOOCs) have become popular platforms for online learning. While MOOCs enable students to study at their own pace, this flexibility makes it easy for students to drop out of class. In this paper, our goal is to predict if a learner is going to drop out within the next week, given clickstream data for the current week. To this end, we present a multi-layer representation learning solution based on branch and bound (BB) algorithm, which learns from low-level clickstream...
#1SungJin NamH-Index: 5
#1Yi CuiH-Index: 7
This website uses cookies.
We use cookies to improve your online experience. By continuing to use our website we assume you agree to the placement of these cookies.
To learn more, you can find in our Privacy Policy.