1,721,309 research outputs found
Training Temporal and NLP Features via Extremely Randomised Trees for Educational Level Classification
Full text linkMassive Open Online Courses (MOOCs) have become universal learning resources, and the COVID-19 pandemic is rendering these platforms even more necessary. These platforms also bring incredible diversity of learners in terms of their traits. A research area called Author Profiling (AP in general; here, Learner Profiling (LP)), is to identify such traits about learners, which is vital in MOOCs for, e.g., preventing plagiarism, or eligibility for course certification. Identifying a learner’s trait in a MOOC is notoriously hard to do from textual content alone. We argue that to predict a learner’s academic level, we need to also be using other features stemming from MOOC platforms, such as derived from learners’ actions on the platform. In this study, we specifically examine time stamps, quizzes, and discussions. Our novel approach for the task achieves a high accuracy (90% in average) even with a simple shallow classifier, irrespective of data size, outperforming the state of the art
Who likes me more? Analysing entity-centric language-specific bias in multilingual Wikipedia
No full textIn this paper we take an important step towards better understanding the existence and extent of entity-centric language-specific bias in multilingual Wikipedia and any deviation from its targeted neutral point of view. We propose a methodology using sentiment analysis techniques to systematically extract the variations in sentiments associated with real-world entities in different language editions of Wikipedia, illustrated with a case study of five Wikipedia language editions and a set of target entities from four categories
Encouraging Teacher-sourcing of Social Recommendations Through Participatory Gamification Design
Full text linkTeachers and learners who search for learning materials in open educational resources (OER) repositories greatly benefit from feedback and reviews left by peers who have activated these resources in their class. Such feedback can also fuel social-based ranking algorithms and recommendation systems. However, while educational users appreciate the recommendations made by other teachers, they are not highly motivated to provide such feedback by themselves. This situation is common in many consumer applications that rely on users’ opinions for personalisation. A possible solution that was successfully applied in several other domains to incentivise active participation is gamification. This paper describes for the first time the application of a comprehensive cutting-edge gamification taxonomy, in a user-centred participatory-design process of an OER system for Physics, PeTeL, used throughout Israel. Physics teachers were first involved in designing gamification features based on their preferences, helping shape the gamification mechanisms likely to enhance their motivation to provide reviews. The results informed directly the implementation of two gamification elements that were implemented in the learning environment, with a second experiment evaluating their actual effect on teachers’ behaviour. After a long-term, real-life pilot of two months, teachers’ response rate was measured and compared to the prior state. The results showed a statistically significant effect, with a 4X increase in the total amount of recommendations per month, even when taking into account the ‘Covid-pandemic effect’
Wide-Scale Automatic Analysis of 20 Years of ITS Research
Full text linkThe analysis of literature within a research domain can provide significant value during preliminary research. While literature reviews may provide an in-depth understanding of current studies within an area, they are limited by the number of studies which they take into account. Importantly, whilst publications in hot areas abound, it is not feasible for an individual or team to analyse a large volume of publications within a reasonable amount of time. Additionally, major publications which have gained a large number of citations are more likely to be included in a review, with recent or fringe publications receiving less inclusion. We provide thus an automatic methodology for the large-scale analysis of literature within the Intelligent Tutoring Systems (ITS) domain, with the aim of identifying trends and areas of research from a corpus of publications which is significantly larger than is typically presented in conventional literature reviews. We illustrate this by a novel analysis of 20 years of ITS research. The resulting analysis indicates a significant shift of the status quo of research in recent years with the advent of novel neural network architectures and the introduction of MOOCs
Predicting Certification in MOOCs Based on Students’ Weekly Activities
Full text linkMassive Open Online Courses (MOOCs) have been growing rapidly, offering low-cost knowledge for both learners and content providers. However, currently there is a very low level of course purchasing (less than 1% of the total number of enrolled students on a given online course opt to purchase its certificate). This can impact seriously the business model of MOOCs. Nevertheless, MOOC research on learners’ purchasing behaviour on MOOCs remains limited. Thus, the umbrella question that this work tackles is if learner’s data can predict their purchasing decision (certification). Our fine-grained analysis attempts to uncover the latent correlation between learner activities and their decision to purchase. We used a relatively large dataset of 5 courses of 23 runs obtained from the less studied MOOC platform of FutureLearn to: (1) statistically compare the activities of non-paying learners with course purchasers, (2) predict course certification using different classifiers, optimising for this naturally strongly imbalanced dataset. Our results show that learner activities are good predictors of course purchasibility; still, the main challenge was that of early prediction. Using only student number of step accesses, attempts, correct and wrong answers, our model achieve promising accuracies, ranging between 0.81 and 0.95 across the five courses. The outcomes of this study are expected to help design future courses and predict the profitability of future runs; it may also help determine what personalisation features could be provided to increase MOOC revenu
MOOCs Paid Certification Prediction Using Students Discussion Forums
Full text linkMassive Open Online Courses (MOOCs) have been suffering a very level of low course certification (less than 1% of the total number of enrolled students on a given online course opt to purchase its certificate), although MOOC platforms have been offering low-cost knowledge for both learners and content providers. While MOOCs discussion forums’ rich numeric and textual data are typically utilised to address many MOOCs challenges, e.g., high dropout rate, identifying intervention-needed learners, analysing learners’ forum discussion and interaction to predict certification remains limited. Thus, this paper investigates if MOOC discussion forum-based data can predict learners’ purchasing decisions (certification). We use a relatively large dataset of 23 runs of 5 FutureLearn MOOCs for temporal (weekly-based) prediction, achieving promising accuracies in this challenging task: 76% on average, across the five courses
Exploring Bayesian Deep Learning for Urgent Instructor Intervention Need in MOOC Forums
Full text linkMassive Open Online Courses (MOOCs) have become a popular choice for e-learning thanks to their great flexibility. However, due to large numbers of learners and their diverse backgrounds, it is taxing to offer real-time support. Learners may post their feelings of confusion and struggle in the respective MOOC forums, but with the large volume of posts and high workloads for MOOC instructors, it is unlikely that the instructors can identify all learners requiring intervention. This problem has been studied as a Natural Language Processing (NLP) problem recently, and is known to be challenging, due to the imbalance of the data and the complex nature of the task. In this paper, we explore for the first time Bayesian deep learning on learner-based text posts with two methods: Monte Carlo Dropout and Variational Inference, as a new solution to assessing the need of instructor interventions for a learner’s post. We compare models based on our proposed methods with probabilistic modelling to its baseline non-Bayesian models under similar circumstances, for different cases of applying prediction. The results suggest that Bayesian deep learning offers a critical uncertainty measure that is not supplied by traditional neural networks. This adds more explainability, trust and robustness to AI, which is crucial in education-based applications. Additionally, it can achieve similar or better performance compared to non-probabilistic neural networks, as well as grant lower variance
Urgency Analysis of Learners’ Comments: An Automated Intervention Priority Model for MOOC
Full text linkRecently, the growing number of learners in Massive Open Online Course (MOOC) environments generate a vast amount of online comments via social interactions, general discussions, expressing feelings or asking for help. Concomitantly, learner dropout, at any time during MOOC courses, is very high, whilst the number of learners completing (completers) is low. Urgent intervention and attention may alleviate this problem. Analysing and mining learner comments is a fundamental step towards understanding their need for intervention from instructors. Here, we explore a dataset from a FutureLearn MOOC course. We find that (1) learners who write many comments that need urgent intervention tend to write many comments, in general. (2) The motivation to access more steps (i.e., learning resources) is higher in learners without many comments needing intervention, than that of learners needing intervention. (3) Learners who have many comments that need intervention are less likely to complete the course (13%). Therefore, we propose a new priority model for the urgency of intervention built on learner histories – past urgency, sentiment analysis and step access
A Brief Survey of Deep Learning Approaches for Learning Analytics on MOOCs
Full text linkMassive Open Online Course (MOOC) systems have become prevalent in recent years and draw more attention, a.o., due to the coronavirus pandemic’s impact. However, there is a well-known higher chance of dropout from MOOCs than from conventional off-line courses. Researchers have implemented extensive methods to explore the reasons behind learner attrition or lack of interest to apply timely interventions. The recent success of neural networks has revolutionised extensive Learning Analytics (LA) tasks. More recently, the associated deep learning techniques are increasingly deployed to address the dropout prediction problem. This survey gives a timely and succinct overview of deep learning techniques for MOOCs’ learning analytics. We mainly analyse the trends of feature processing and the model design in dropout prediction, respectively. Moreover, the recent incremental improvements over existing deep learning techniques and the commonly used public data sets have been presented. Finally, the paper proposes three future research directions in the field: knowledge graphs with learning analytics, comprehensive social network analysis, composite behavioural analysis
Bi-directional Mechanism for Recursion Algorithms: A Case Study on Gender Identification in MOOCs
Full text linkAutomatically identifying the learner gender, which serves as this paper’s focus, can provide valuable information to personalised learners’ experiences in MOOCs. However, extracting the gender from learner-generated data (discussion forum) is a challenging task, which is understudied in literature. Using syntactic features is still the state-of-the-art for gender identification in social media. Instead we propose here a novel approach based on Recursive Neural Networks (RecNN), to learn advanced syntactic knowledge extracted from learners’ comments, as an NLP-based predictor for their gender identity. We propose a bi-directional composition function, added to NLP state-of-the-art candidate RecNN models. We evaluate different combinations of semantic level encoding and syntactic level encoding functions, exploring their performances, with respect to the task of learner gender profiling in MOOCs
- …
