Conference PaperPDF Available

MoocViz: A Large Scale, Open Access, Collaborative, Data Analytics Platform for MOOCs

Authors:
  • Adobe Research

Abstract and Figures

In this paper we present an open access large scale analytics platform that helps researchers analyze MOOC data from multiple platforms with out the need to share the data. It allows researchers to share scripts/effort, compare results and attempts to engage the community to achieve shared educational science goals. The platform utilizes some well known tools and packages and provides multiple levels of access to address a wide variety of needs around the data. We demonstrate the platforms capability by analyzing data from two MOOCs, one from coursera (offered by Stanford University) and one from edX (offered by MITx). This is the first time two courses from two platforms have been jointly analyzed. The analysis and the platform is made possible due to joint adoption of a data model called MoocDB.
Content may be subject to copyright.
A preview of the PDF is not available
... These results highlight the need for additional research on the high dropout rate in massive open online courses (MOOCs), a pressing problem in the field of higher education. [16]. This is due to the fact that pinpointing specific dropout variables by itself is insufficient to account for the causes of the high rate of student dropout in MOOCs [17]. ...
Article
Massive open online courses (MOOCs) are a recent e-learning programme that has received widespread acceptance among several colleges. Student dropout from MOOCs is a big worry in higher education and policy-making circles, as it occurs frequently in colleges that offer these types of courses. The majority of student dropouts are caused by causes beyond the institution’s control. Using an IF-DEMATEL (Intuitive Fuzzy Decision-making Trial and Evaluation Laboratory) approach, the primary factors and potential causal relationships for the high dropout rate were identified. The most effective aspects of massive open online courses (MOOCs) are identified using IF-DEMATEL and CIFCS. Moreover, it explains the interconnectedness of the various MOOC components. As an added measure, a number of DEMATEL techniques are used to conduct a side-by-side comparison of the results. Decisions made by the educational organisation could benefit from the findings. According to the research, there are a total of twelve indicators across four dimensions that are related to online course withdrawal amongst students. Then, experienced MOOC instructors from various higher education institutions were invited to assess the level of influence of these characteristics on each other. Academic skills and talents, prior experience, course design, feedback, social presence, and social support were identified as six primary characteristics that directly influenced student dropout in MOOCs. Interaction, course difficulty and length, dedication, motivation, and family/work circumstances have all been found to play a secondary part in student dropout in massive open online courses (MOOCs). The causal connections between the major and secondary factors were traced and discussed. The results of this study can help college professors and administrators come up with and implement effective ways to reduce the high number of students who drop out of massive open online courses (MOOCs).
... MOOCviz, a platform for visualizing data from edX and analyzing log data from Coursera, contains databases with information on students, including their activity and feedback. MOOCviz designers employed cohort and statistical analysis and used various heuristics to identify cohorts of students in MOOC courses based on resource use, country, etc. [Dernoncourt et al. 2013]. Other examples of MOOC analytical tools include Perspec-tivesX, a collaborative learning tool designed to support content and learner curation using topic modelling and deep learning techniques, and MessageLens, a visual analytics system to explore MOOC forum discussions [Bakharia 2017;Wong, Zhang 2018]. ...
Article
Full-text available
In this paper, math anxiety descriptions are extracted from Massive Open Online Course (MOOC) reviews using text mining techniques. Learners’ emotional states associated with math phobia represent substantial barriers to learning mathematics and acquiring basic mathematical knowledge required for future career success. MOOC platforms accumulate big sets of educational data, learners’ feedback being of particular research interest. Thirty-eight math MOOCs on Udemy and 1,898 learners’ reviews are investigated in this study. VADER sentiment analysis, k-means clustering of content with negative sentiment, and sentence embedding based on the Bidirectional Encoder Representations from Transformers (BERT) language model allow identifying a few clusters containing descriptions of various negative emotions related to bad math experiences in the past, a cluster with descriptions of regrets about missed opportunities due to negative attitudes towards math in the past, and a cluster describing gradual overcoming of math anxiety while progressing through a math MOOC. The constructed knowledge graph makes it possible to visualize some regularities pertaining to different negative emotions experienced by math MOOC learners.
... The emergence of MOOC big data stipulates analytics researchers to develop methods for leveraging it in education analysis. Dernoncourt et al. (2013) presented MoocViz, an open-access large scale analytics that enables analysts in analyzing MOOC data. MoocViz enables the community of education analysts to share and compare MOOC analysis findings. ...
Article
Full-text available
Malaysia and many other developing countries progressively adopting massively open online course (MOOC) in their national higher education approach. We have observed an increasing need for facilitating MOOC monitoring that is associated with the rising adoption of MOOCs. Our observation suggests that recent adoption cases led analyst and instructors to focus on monitoring enrolment and learning activities. Visual analytics in MOOC support education analysts in analyzing MOOC data via interactive visualization. Existing literature on MOOC visualization focuses on enabling visual analysis on MOOC data from forum and course material. We found limited studies that investigate and characterize domain problems or design requirements of visual analytics for MOOC. This paper aims to present the empirical problem characterization and abstraction for visual analytics in MOOC learner's support monitoring. Detailed characterization and abstraction of the domain problem help visualization designer to derive design requirements in generating appropriate visualization solution. We examined the literature and conducted a case study to elicit a problem abstraction based on data, users, and tasks. We interviewed five Malaysian MOOC experts from three higher education institutes using semi-structured questions. Our case study reveals the priority of enabling MOOC analysis on learner's progression and course completion. There is an association between design and analysis priority with the pedagogical type of implemented MOOC and users. The characterized domain problems and requirements offer a design foundation for visual analytics in MOOC monitoring analysis.
... Much research on clickstream visualization covered many directions in MOOCs. Some studies targeted learners' online activities [15,16,5,60], while others focused on the interaction of learners with videos [29,47]. Some visualization systems and tools were proposed. ...
Article
The big data stored in massive open online course (MOOC) platforms have become a posed challenge in the Learning Analytics field to analyze the learning behavior of learners, and predict their respective performance, related especially to video lecture data, since most learners view the same online lecture videos. This helps to conduct a comprehensive analysis of such behaviors and explore various learning patterns in MOOC video interactions. This paper aims at presenting a visual analysis, which enables course instructors and education experts to analyze clickstream data that were generated by learner interaction with course videos. It also aims at predicting learner performance , which is a vital decision-making problem, by addressing their issues and improving the educational process. This paper uses a long short-term memory network (LSTM) on implicit features extracted from video-clickstreams data to predict learners' performance and enable instructors to make measures for timely intervention. Results show that the accuracy rate of the proposed model is 89%-95% throughout course weeks. The proposed LSTM model outperforms baseline Deep learning (GRU) and simple recurrent neural network by accuracy of 90.30% in the "Mining of Massive Datasets" course, and the "Automata Theory" accuracy is 89%.
... The examples from the literature referred here indicate the effort of applying learning analytics into massive scale data in a single domain or platform. There is also an attempt for open access collaborative data analytics platform to visualise MOOC data without sharing the data (Dernoncourt et al., 2013). They propose a unified data modelling for three partner MOOC platforms and enable the statistical analysis and data visualisation using open tools such as the 6 1st International Conference on Learning Analytics and Knowledge, Banff, Alberta, February 27 -March 1, 2011, https://tekri.athabascau.ca/analytics. ...
Conference Paper
Full-text available
The availability of open educational resources is growing at an increasingly fast pace since its first promotion by UNESCO in 2002. Today, large variability of opportunities for free and online educational resources are available and accessible by everyone from all around the world who has access to the Internet. An Internet user may exploit numbers of different platforms to find what they are looking for, where one platform may fit their study goal while another platform suits their learning approach. Finding the appropriate content and platform could be like searching for a needle in the haystack where users desperately need help from personalised recommendations. Many platforms aim to transform to a more personalised learning environment, mostly by recommending a content or a peer to study with, providing timely feedback, or a gamified learning environment within the platform. We expect that in the next decade it will be necessary to provide user guidance to the Open Educational Resources not only in a single domain but in cross-domain, cross-site, and cross-cultural nature of the Internet. In this paper, we investigate the users’ learning behaviour by analysing their clickstream data across different learning platforms. The results indicate that most of the users tend to stay on a website for a short duration. Also, the design of materials on different websites affect the number of clicks and the pattern of engagement.
Article
Full-text available
Education and education research are experiencing increased digitization and datafication, partly thanks to the rise in popularity of massively open online courses (MOOCs). The infrastructures that collect, store and analyse the resulting big data have received critical scrutiny from sociological, epistemological, ethical and analytical perspectives. These critiques tend to highlight concerns and/or warnings about the lack of the infrastructures' and builders' understanding of various nontechnical aspects of big data research (eg seeing data as neutral rather than as products of social processes). These critiques have primarily come from outside of the builder community, rendering the conversation largely one‐sided and devoid of the voices of the builders themselves. The purpose of this paper is to re‐balance the conversation by reporting the results of interviews with 11 data infrastructure builders in higher education institutions. The interviews reveal that builders engage deeply with the issues the critiques outline, not only thinking about them, but also developing practices to address them. The paper focuses the findings on three themes: designing a productive science, navigating ubiquitous ethics and achieving real human impact. Researchers, policymakers and infrastructure builders can use these accounts to better understand the building process and experience.
Conference Paper
Full-text available
As MOOCs grow in popularity, the relatively low completion rates of learners has been a central criticism. This focus on completion rates, however, reflects a monolithic view of disengagement that does not allow MOOC designers to target interventions or develop adaptive course features for particular subpopulations of learners. To address this, we present a simple, scalable, and informative classification method that identifies a small number of longitudinal engagement trajectories in MOOCs. Learners are classified based on their patterns of interaction with video lectures and assessments, the primary features of most MOOCs to date. In an analysis of three computer science MOOCs, the classifier consistently identifies four prototypical trajectories of engagement. The most notable of these is the learners who stay engaged through the course without taking assessments. These trajectories are also a useful framework for the comparison of learner engagement between different course structures or instructional approaches. We compare learners in each trajectory and course across demographics, forum participation, video access, and reports of overall experience. These results inform a discussion of future interventions, research, and design directions for MOOCs. Potential improvements to the classification mechanism are also discussed, including the introduction of more fine-grained analytics.
Article
Full-text available
The intent of this article is to enable development of data standards for MOOCs and build enabling technology.
Article
Full-text available
“Circuits and Electronics” (6.002x), which began in March 2012, was the first MOOC developed by edX, the consortium led by MIT and Harvard. Over 155,000 students initially registered for 6.002x, which was composed of video lectures, interactive problems, online laboratories, and a discussion forum. As the course ended in June 2012, researchers began to analyze the rich sources of data it generated. This article describes both the first stage of this research, which examined the students’ use of resources by time spent on each, and a second stage that is producing an in-depth picture of who the 6.002x students were, how their own background and capabilities related to their achievement and persistence, and how their interactions with 6.002x’s curricular and pedagogical components contributed to their level of success in the course.
Conference Paper
Full-text available
This paper is focused on user modeling and adaptation in distributed E- Learning systems. We describe here CUMULATE, a generic student modeling server developed for a distributed E-Learning architecture, KnowledgeTree. We also introduce a specific, topic-based knowledge modeling approach which has been implemented as an inference agent in CUMULATE and used in QuizGuide, an adaptive system that helps students select the most relevant self-assessment quizzes. We also discuss our attempts to evaluate this multi-level student modeling.
Article
The paper reviews the development of generic user modeling systems over the past twenty years. It describes their purposes, their services within user-adaptive systems, and the different design requirements for research prototypes and commercially deployed servers. It discusses the architectures that have been explored so far, namely shell systems that form part ofthe application, central server systems that communicate with several applications, and possible future user modeling agents that physically follow the user. Several implemented research prototypes and commercial systems are briefly described.
US -113120 4533 -5271
  • Br Vs
BR vs.US -113120 4533 -5271.2 3201 -16114 -2993.5 -53044 -18485
Statistical methods in education and psychology
  • G V Glass
  • K D Hopkins
G. V. Glass and K. D. Hopkins. Statistical methods in education and psychology. Prentice-Hall Englewood Cliffs, NJ, 1970.
Moocdb: Developing data standards for mooc data science
  • K Veeramachaneni
  • F Dernoncourt
  • C Taylor
  • Z Pardos
  • U.-M Oõreilly
K. Veeramachaneni, F. Dernoncourt, C. Taylor, Z. Pardos, and U.-M. OÕReilly. Moocdb: Developing data standards for mooc data science. In AIED 2013 Workshops Proceedings Volume, page 17, 2013. BR vs.DE -35405 138970 -2563.1 9993.1 -7198.3 12247 -37926