Filters








1,269 Hits in 2.3 sec

MORF: A Framework for Predictive Modeling and Replication At Scale With Privacy-Restricted MOOC Data [article]

Josh Gardner, Christopher Brooks, Juan Miguel L. Andres, Ryan Baker
2018 arXiv   pre-print
We present a novel system for large-scale computational research, the MOOC Replication Framework (MORF), to jointly address these barriers.  ...  Big data repositories from online learning platforms such as Massive Open Online Courses (MOOCs) represent an unprecedented opportunity to advance research on education at scale and impact a global population  ...  Replication and Analysis Functionality 1) Predictive Modeling: A critical area of MOOC research to date has been the construction and analysis of predictive models of student success [8] .  ... 
arXiv:1801.05236v3 fatcat:jl47wjv5rrd2lds5uqswm6xkkq

Enabling End-To-End Machine Learning Replicability: A Case Study in Educational Data Mining [article]

Josh Gardner, Yuming Yang, Ryan Baker, Christopher Brooks
2018 arXiv   pre-print
We demonstrate the use of MORF by conducting a replication at scale, and provide a complete executable container, with unique DOIs documenting the configurations of each individual trial, for replication  ...  or future extension at https://github.com/educational-technology-collective/fy2015-replication.  ...  For example, MORF avoids the use of cross-validation for model evaluation: The prediction tasks to which most MOOC models aspire are prediction of future student performance (i.e., in an ongoing course  ... 
arXiv:1806.05208v2 fatcat:xrt7geusajbxjgoi3aqqsjsz3e

A Statistical Framework for Predictive Model Evaluation in MOOCs

Josh Gardner, Christopher Brooks
2017 Proceedings of the Fourth (2017) ACM Conference on Learning @ Scale - L@S '17  
In this paper, we present and apply a procedure for evaluating predictive models in MOOCs.  ...  in MOOCs.  ...  Recent research has provided evidence that some MOOC research may not be replicable when applied to new or different courses [1] ; at the very least, this highlights the importance of adopting reproducible  ... 
doi:10.1145/3051457.3054002 dblp:conf/lats/GardnerB17 fatcat:dprvuzhcg5cgphocoyxv6eba3q

Studying MOOC completion at scale using the MOOC replication framework

Juan Miguel L. Andres, Ryan S. Baker, Dragan Gašević, George Siemens, Scott A. Crossley, Srećko Joksimović
2018 Proceedings of the 8th International Conference on Learning Analytics and Knowledge - LAK '18  
MORF enables larger-scale analysis of MOOC research questions than previously feasible, and enables researchers around the world to conduct analyses on huge multi-MOOC data sets without having to negotiate  ...  This paper reports on the development of the MOOC Replication Framework (MORF), a framework that facilitates the replication of previously published findings across multiple data sets and the seamless  ...  While we view production rules as a highly interpretable and reasonably flexible framework, more complex prediction models are already in use to determine which students are at risk of failing to complete  ... 
doi:10.1145/3170358.3170369 dblp:conf/lak/AndresBGSCJ18 fatcat:yeh6va3r4nazxfi2sy4dxrxk4m

Learning Instructor Intervention from MOOC Forums: Early Results and Issues [article]

Muthu Kumar Chandrasekaran, Min-Yen Kan, Bernard C.Y. Tan, Kiruthika Ragupathi
2015 arXiv   pre-print
With large student enrollment, MOOC instructors face the unique challenge in deciding when to intervene in forum discussions with their limited bandwidth.  ...  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.  ...  We call for the community to seize this opportunity to make research on learning at scale more recognizable and replicable.  ... 
arXiv:1504.07206v1 fatcat:ibagvfof3vg7jccdo4s2ws7uua

Student success prediction in MOOCs

Josh Gardner, Christopher Brooks
2018 User modeling and user-adapted interaction  
In this article we review the state of the art in predictive models of student success in MOOCs and present a categorization of MOOC research according to the predictors (features), prediction (outcomes  ...  Such a review is particularly useful given the rapid expansion of predictive modeling research in MOOCs since the emergence of major MOOC platforms in 2012.  ...  Acknowledgements This work was funded in part by the Michigan Institute for Data Science (MIDAS) Holistic Modeling of Education (HOME) project, and the University of Michigan Third Century Initiative.  ... 
doi:10.1007/s11257-018-9203-z fatcat:pgrusb3jqrc7fmc4g4rutwqcne

Are MOOC Learning Analytics Results Trustworthy? With Fake Learners, They Might Not Be!

Giora Alexandron, Lisa Y. Yoo, José A. Ruipérez-Valiente, Sunbok Lee, David E. Pritchard
2019 International Journal of Artificial Intelligence in Education  
We replicate two highlycited learning analytics studies with and without fake learners data, and compare the results.  ...  The methodology for measuring the bias caused by fake learners' activity combines the ideas of Replication Research and Sensitivity Analysis.  ...  at scale, and by developing advanced verification techniques.  ... 
doi:10.1007/s40593-019-00183-1 fatcat:67ejsziyvfe2phliyp2qrjgpaa

Using Discourse Signals for Robust Instructor Intervention Prediction [article]

Muthu Kumar Chandrasekaran, Carrie Demmans Epp, Min-Yen Kan, Diane Litman
2016 arXiv   pre-print
We tackle the prediction of instructor intervention in student posts from discussion forums in Massive Open Online Courses (MOOCs).  ...  The resultant models are less dependent on domain-specific vocabulary, allowing them to better generalize to new courses.  ...  We would like to thank the University of Pittsburgh's Center for Teaching and Learning, for sharing their MOOC data.  ... 
arXiv:1612.00944v1 fatcat:pry6gq4mwraxfhweqbqmle4chq

Using Discourse Signals for Robust Instructor Intervention Prediction

Muthu Kumar Chandrasekaran, Carrie Epp, Min-Yen Kan, Diane Litman
2017 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We tackle the prediction of instructor intervention in student posts from discussion forums in Massive Open Online Courses (MOOCs).  ...  The resultant models are less dependent on domain-specific vocabulary, allowing them to better generalize to new courses.  ...  We would like to thank the University of Pittsburgh's Center for Teaching and Learning, for sharing their MOOC data.  ... 
doi:10.1609/aaai.v31i1.11015 fatcat:lhnbkjf6k5gx7co5hvcoooyjiu

Diverse Big Data and Randomized Field Experiments in MOOCs [chapter]

Rene F. Kizilcec, Christopher Brooks
2017 Handbook of Learning Analytics  
A new mechanism for delivering educational content at large scale, massive open online courses (MOOCs), has attracted millions of learners worldwide.  ...  Following a concise account of the recent history of MOOCs, this chapter focuses on their potential as a research instrument.  ...  A time series interaction analysis method for building predictive models of learners using log data.  ... 
doi:10.18608/hla17.018 fatcat:he7pfddotfdebeqe6c4dnjsghm

Towards Improving Students' Forum Posts Categorization in MOOCs and Impact on Performance Prediction

Fatima Harrak, Vanda Luengo, François Bouchet, Rémi Bachelet
2019 Proceedings of the Sixth (2019) ACM Conference on Learning @ Scale - L@S '19  
the MOOC.  ...  Going beyond mere forum posts categorization is key to understand why some students struggle and eventually fail in MOOCs.  ...  We hypothesize that analyzing more finely the content of MOOC posts would help in particular to predict students' success.  ... 
doi:10.1145/3330430.3333661 dblp:conf/lats/HarrakLBB19 fatcat:47lkc3j5hraypfi6ro6erl3khu

Fast Parallel SAME Gibbs Sampling on General Discrete Bayesian Networks [article]

Daniel Seita, Haoyu Chen, John Canny
2015 arXiv   pre-print
Gibbs sampling is one of the most accurate approaches and provides unbiased samples from the posterior but it has historically been too expensive for large models.  ...  In this paper, we present an optimized, parallel Gibbs sampler augmented with state replication (SAME or State Augmented Marginal Estimation) to decrease convergence time.  ...  In addition to measuring distance between predicted and actual parameters, we also evaluate the sampler using its accuracy at predicting missing labels.  ... 
arXiv:1511.06416v1 fatcat:hy6ljcuecvcjpmd62qamk7w5pa

The role of students' motivation and participation in predicting performance in a MOOC

P.G. de Barba, G.E. Kennedy, M.D. Ainley
2016 Journal of Computer Assisted Learning  
As with many emerging educational technologies, why and how people come to MOOCs needs to be better understood, and importantly what factors contribute to learners' MOOC performance.  ...  Research presented in this article investigated how motivation and participation influence students' performance in a MOOC, more specifically those students who persist to the end of the MOOC.  ...  Acknowledgements We would like to thank the Principles of Macroeconomics MOOC coordinator Nils Olekalns for partnering with us.  ... 
doi:10.1111/jcal.12130 fatcat:5vqvlxf4zff63krs2ikbrjyati

Towards Designing Profitable Courses: Predicting Student Purchasing Behaviour in MOOCs

Mohammad Alshehri, Ahmed Alamri, Alexandra I. Cristea, Craig D. Stewart
2021 International Journal of Artificial Intelligence in Education  
Specifically, we compare how several machine learning algorithms, namely RandomForest, GradientBoosting, AdaBoost and XGBoost can predict course purchasability using a large-scale data collection of 23  ...  Our proposed model achieved promising accuracies, between 0.82 and 0.91, using only the time spent on each step.  ...  This logistic regression classifier model was trained and tested on one run of the MOOCs under certain conditions and incentives, by the provider; therefore, it might need to be replicated, for the results  ... 
doi:10.1007/s40593-021-00246-2 fatcat:gf35plngknayrh2zw4swjvp2zm

Grit and Intention: Why Do Learners Complete MOOCs?

Yuan Wang, Ryan Baker
2018 International Review of Research in Open and Distance Learning  
<p class="3">In recent years there has been considerable interest in how many learners complete MOOCs, and what factors during usage can predict completion.  ...  We compare that relationship to the degree to which MOOC completion is predicted by other domain-general motivational factors such as grit, goal orientation, academic efficacy, and the need for cognition  ...  Acknowledgment This work was supported by the National Sciences Foundation, Award #DRL -1418378, Collaborative Research: Modeling Social Interaction and Performance in STEM Learning.  ... 
doi:10.19173/irrodl.v19i3.3393 fatcat:uavwkbo3pnbslnzzk5mqaf7jwe
« Previous Showing results 1 — 15 out of 1,269 results