Transfer Learning using Representation Learning in Massive Open Online Courses

  title={Transfer Learning using Representation Learning in Massive Open Online Courses},
  author={Mucong Ding and Yanbang Wang and Erik Hemberg and Una-May O’Reilly},
  journal={Proceedings of the 9th International Conference on Learning Analytics \& Knowledge},
In a Massive Open Online Course (MOOC), predictive models of student behavior can support multiple aspects of learning, including instructor feedback and timely intervention. Ongoing courses, when the student outcomes are yet unknown, must rely on models trained from the historical data of previously offered courses. It is possible to transfer models, but they often have poor prediction performance. One reason is features that inadequately represent predictive attributes common to both courses… Expand
Knowledge Transfer by Discriminative Pre-training for Academic Performance Prediction
  • Byungsoo Kim, Hangyeol Yu, Dongmin Shin, Youngduck Choi
  • Computer Science
  • ArXiv
  • 2021
DPA is a transfer learning framework with Discriminative Pre-training tasks for Academic performance prediction that outperforms the previous state-of-the-art generative pre-training method with a reduction of 4.05% in mean absolute error and is more robust to increased labelscarcity. Expand
Designing Intelligent Systems for Online Education: Open Challenges and Future Directions
Several areas of research in this field are identified, such as data availability and sharing, time-wise and multi-modal data modelling, generalizability, fairness, explainability, interpretability, privacy, and ethics behind models delivered for supporting education. Expand
Towards Portability of Models for Predicting Students’ Final Performance in University Courses Starting from Moodle Logs
The results obtained show that it is only feasible to directly transfer predictive models or apply them to different courses with an acceptable accuracy and without losing portability under some circumstances. Expand
Improving the portability of predicting students’ performance models by using ontologies
This paper proposes the utilization of an ontology that uses a taxonomy of actions that summarises students’ interactions with the Moodle learning management system and results indicate that the use of the proposed ontology improves the portability of the models in terms of predictive accuracy. Expand
Educational data mining and learning analytics: An updated survey
The current state of the art in data mining in education is provided by reviewing the main publications, the key milestones, the knowledge discovery cycle, the main educational environments, the specific tools, the free available datasets, the most used methods, themain objectives, and the future trends in this research area. Expand
Informing the Design of Collaborative Activities in MOOCs using Actionable Predictions
Predictive models for student participation in group discussions in MOOCs are derived using only data prior to the learning activity, and can thus provide actionable predictions, as opposed to post-hoc approaches common in the MOOC literature. Expand
Bibliometric Analysis of MOOC using Bibliometrix Package of R
As a growing academic approach, MOOCs have gained widespread attention through academic courses. There are many MOOC platforms available like Udemy, Udacity, Coursera, Swayam, Khan Academy and EdX.Expand
Assessment Modeling: Fundamental Pre-training Tasks for Interactive Educational Systems
This work proposes assessment modeling as a guiding principle for selecting proper pre- training tasks for the label-scarce educational problems, and is the first work investigating appropriate pre-training method of predicting educational features from student-system interactions. Expand


Transfer Learning for Predictive Models in Massive Open Online Courses
This article designs a set of processes that take advantage of knowledge from both previous courses and previous weeks of the same course to make real time predictions on learners behavior, and evaluates multiple transfer learning methods. Expand
Predicting MOOC Dropout over Weeks Using Machine Learning Methods
This paper presents an approach that works on click-stream data that takes the weekly history of student data into account and thus is able to notice changes in student behavior over time and be able to predict dropout significantly better than baseline methods. Expand
Towards Feature Engineering at Scale for Data from Massive Open Online Courses
Different influential features for stop out prediction that depended on whether a learner was in 1 of 4 cohorts defined by their level of engagement with the course discussion forum or wiki are identified. Expand
Student success prediction in MOOCs
This article presents a categorization of MOOC research according to the predictors, prediction, and underlying theoretical model, and critically survey work across each category, providing data on the raw data source, feature engineering, statistical model, evaluation method, prediction architecture, and other aspects of these experiments. Expand
Communication at Scale in a MOOC Using Predictive Engagement Analytics
This paper augments a MOOC platform with personalized communication affordances, allowing the instructional staff to direct communication to learners based on individual predictions of three engagement analytics, using the state-of-the-art in recurrent neural network classification. Expand
Data mining for modeling students' performance: A tutoring action plan to prevent academic dropout
The use of knowledge discovery techniques to analyse historical student course grade data in order to predict whether or not a student will drop out of a course is proposed and a tutoring action plan is designed. Expand
Replicating MOOC predictive models at scale
This work demonstrates the importance of replication of predictive modeling research in MOOCs using large and diverse datasets, illuminates the challenges of doing so, and describes the freely available, open-source software framework to overcome barriers to replication. Expand
A Survey on Transfer Learning
The relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift are discussed. Expand
A time series interaction analysis method for building predictive models of learners using log data
A novel method for converting educational log data into features suitable for building predictive models of student success, an approach that requires no input from instructional or domain experts and can be applied across courses or learning environments. Expand
A Comparative Study of Methods for Transductive Transfer Learning
A novel maximum entropy based technique, iterative feature transformation (IFT), is introduced and it is shown how simple relaxations, such as providing additional information like the proportion of positive examples in the test data, can significantly improve the performance of some of the transductive transfer learners. Expand