This study compared student learning engagement from two UK departments exploring their participation in face-to-face and synchronous online learning environments. Overall, 446 undergraduate students from Psychology (soft/non-Science, Technology, Engineering, and Mathematics (STEM) discipline) and Electrical Engineering and Electronics (EEE) (hard/STEM discipline) completed an online questionnaire over the second semester of the 2020–2021 academic year, where the teaching was mainly online. The questionnaire included validated scales regarding teaching and students’ characteristics and an open-ended question regarding the role of learning environments. There was a significant difference between the two learning environments in both departments, with most of the students believing that they were better engaged with their learning process in face-to-face environments (quantitative analysis). Additionally, the thematic analysis of student qualitative responses revealed that online student engagement was influenced by (1) Behaviour, (2) Affective, and (3) Cognitive challenges (i.e., additional workload, lack of communication and distractions in the home environment) and opportunities (i.e., the effective use of study time and online content through interactive learning environments). This study could assist academics, university policymakers, and researchers to understand student engagement alongside learning environments, reconsidering the opportunities and challenges that were gained from online learning due to the COVID-19 pandemic.
This study aims to explore and improve ways of handling a continuous variable dataset, in order to predict student dropout in MOOCs, by implementing various models, including the ones most successful across various domains, such as recurrent neural network (RNN), and tree-based algorithms. Unlike existing studies, we arguably fairly compare each algorithm with the dataset that it can perform best with, thus 'like for like'. I.e., we use a time-series dataset 'as is' with algorithms suited for time-series, as well as a conversion of the time-series into a discrete-variables dataset, through feature engineering, with algorithms handling well discrete variables. We show that these much lighter discrete models outperform the time-series models. Our work additionally shows the importance of handing the uncertainty in the data, via these 'compressed' models.
As the largest distance learning university in the UK, the Open University has more than 250,000 students enrolled, making it also the largest academic institute in the UK. However, many students end up failing or withdrawing from online courses, which makes it extremely crucial to identify those "at risk" students and inject necessary interventions to prevent them from dropping out. This study thus aims at exploring an efficient predictive model, using both behavioural and demographical data extracted from the anonymised Open University Learning Analytics Dataset (OULAD). The predictive model was implemented through machine learning methods that included BART. The analytics indicates that the proposed model could predict the final result of the course at a finer granularity, i.e., classifying the students into Withdrawn, Fail, Pass, and Distinction, rather than only Completers and Non-completers (two categories) as proposed in existing studies. Our model's prediction accuracy was at 80% or above for predicting which students would withdraw, fail and get a distinction. This information could be used to provide more accurate personalised interventions. Importantly, unlike existing similar studies, our model predicts the final result at the very beginning of a course, i.e., using the first assignment mark, among others, which could help reduce the dropout rate before it was too late.
Along with the exponential increase of students enrolling in MOOCs [26] arises the problem of a high student dropout rate. Researchers worldwide are interested in predicting whether students will drop out of MOOCs to prevent it. This study explores and improves ways of handling notoriously challenging continuous variables datasets, to predict dropout. Importantly, we propose a fair comparison methodology: unlike prior studies and, for the first time, when comparing various models, we use algorithms with the dataset they are intended for, thus 'like for like.' We use a time-series dataset with algorithms suited for time-series, and a converted discrete-variables dataset, through feature engineering, with algorithms known to handle discrete variables well. Moreover, in terms of predictive ability, we examine the importance of finding the optimal hyperparameters for our algorithms, in combination with the most effective pre-processing techniques for the data. We show that these much lighter discrete models outperform the time-series models, enabling faster training and testing. This result also holds over fine-tuning of pre-processing and hyperparameter optimisation.
Decision trees are highly famous in machine learning and usually acquire state-of-the-art performance. Despite that, well-known variants like CART, ID3, random forest, and boosted trees miss a probabilistic version that encodes prior assumptions about tree structures and shares statistical strength between node parameters. Existing work on Bayesian decision trees depend on Markov Chain Monte Carlo (MCMC), which can be computationally slow, especially on high dimensional data and expensive proposals. In this study, we propose a method to parallelise a single MCMC decision tree chain on an average laptop or personal computer that enables us to reduce its run-time through multi-core processing while the results are statistically identical to conventional sequential implementation. We also calculate the theoretical and practical reduction in run time, which can be obtained utilising our method on multi-processor architectures. Experiments showed that we could achieve 18 times faster running time provided that the serial and the parallel implementation are statistically identical.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.