Transfer Learning using Representation Learning in Massive Open Online Courses

Abstract

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. We present an automated transductive transfer learning approach that addresses this issue. It relies on problem-agnostic, temporal organization of the MOOC clickstream data, where, for each student, for multiple courses, a set of specific MOOC event types is expressed for each time unit. It consists of two alternative transfer methods based on representation learning with auto-encoders: a passive approach using transductive principal component analysis and an active approach that uses a correlation alignment loss term. With these methods, we investigate the transferability of dropout prediction across similar and dissimilar MOOCs and compare with known methods. Results show improved model transferability and suggest that the methods are capable of automatically learning a feature representation that expresses common predictive characteristics of MOOCs.

Transfer Learning from Deep Neural Networks for Predicting Student Performance

“…Ding et al investigated the transferability of dropout prediction across Massive Online Open Courses (MOOCs) [9]. Therefore, they presented two variations of transfer learning based on autoencoders: (a) using the transductive principal component analysis, and (b) adding a correlation alignment loss term.…”

“…Boyer and Veeramachaneni observe that courses (a) might evolve over time in a dissimilar way, even if they are not much different in terms of context and structure, (b) are populated with different students and instructors, and (c) might have features that cannot be transferred (e.g., a feature defined on a specific learning resource which is not available on another course) [8]. In addition, the complexity of LMSs as well as the course design have a significant impact on the course progress during the semester [9]. Therefore, there may be problems where transfer learning might not reflect the anticipating results, showing some uncertainty about the predictive accuracy of the newly created learning model [10].…”

On the Influence of Grades on Learning Behavior of Students in MOOCs

“…For all model types, we take the power set of our predictor variables and create models with each of those power sets. Additionally, for neural networks, we adjust the width and depth of the network to be some value m ∈ [5, 50] and n ∈ [5,50]. Across all tests, the overwhelmingly most significant variable was "assignment number" suggesting that student grades follow a pattern specific to that class.…”

“…After the identification of relevant features, MOOC data can be used to build relevant predictive models. Due to the multitude of possible features, neural networks are often used as the base model in dropout prediction[18][5]. Fei et al[7] used a recurrent neural network to capture time series data relationships.…”

Informing the Design of Collaborative Activities in MOOCs using Actionable Predictions

“…Two alternative techniques to post-hoc approaches are transfer across courses (which involves the use of a model trained with past course data to make predictions in an ongoing course), and insitu learning (in which student engagement in a past activity is used to generate proxy labels for training in the same course). So far, the research has noted promising results regarding the use of transfer learning for producing accurate predictions that are actionable for real-world use [5,14,2]. However, to the best of our knowledge, there are no previous studies on producing actionable information for supporting the design of collaborative learning in MOOCs.…”