scholarly journals Improving Students Performance in Small-Scale Online Courses - A Machine Learning-Based Intervention

2020 ◽  
Vol 2 (2) ◽  
pp. 80
Author(s):  
Sepinoud Azimi ◽  
Carmen-Gabriela Popa ◽  
Tatjana Cucić
Keyword(s):  
Machine Learning ◽  
Online Courses ◽  
Dropout Rate ◽  
Intervention Strategies ◽  
Massive Open Online Courses ◽  
Small Scale ◽  
Young Generation ◽  
Massive Open Online ◽  
Pedagogical Tool ◽  
Overall Performance

<p class="0abstract"><span lang="EN-US">The birth of massive open online courses (MOOCs) has had an undeniable effect on how teaching is being delivered. It seems that traditional in-class teaching is becoming less popular with the young generation – the generation that wants to choose when, where and at what pace they are learning. As such, many universities are moving towards taking their courses, at least partially, online. However, online courses, although very appealing to the younger generation of learners, come at a cost. For example, the dropout rate of such courses are higher than that of more traditional ones, and the reduced in-person interaction with the teachers results in less timely guidance and intervention from the educators. Machine learning (ML)-based approaches have shown phenomenal successes in other domains. The existing stigma that applying ML-based techniques requires a large amount of data seems to be a bottleneck when dealing with small-scale courses with limited amounts of produced data. In this study, we show not only that the data collected from an online learning management system could be well utilized in order to predict students’ overall performance but also that it could be used to propose timely intervention strategies to boost the students’ performance level. The results of this study indicate that effective intervention strategies could be suggested as early as the middle of the course to change the course of students’ progress for the better. We also present an assistive pedagogical tool based on the outcome of this study, to assist in identifying challenging students and in suggesting early intervention strategies.</span></p>

scholarly journals Topic Discovery of Online Course Reviews Using LDA with Leveraging Reviews Helpfulness

2019 ◽  
Vol 9 (1) ◽  
pp. 426
Author(s):  
Fetty Fitriyanti Lubis ◽  
Yusep Rosmansyah ◽  
Suhono H. Supangkat
Keyword(s):  
Topic Modeling ◽  
Online Courses ◽  
Influential Factors ◽  
Massive Open Online Courses ◽  
Online Course ◽  
Small Scale ◽  
Massive Open Online ◽  
Topic Discovery ◽  
Modeling Approach ◽  
Teaching Learning

Despite the popularity of the Massive Open Online Courses, small-scale research has been done to understand the factors that influence the teaching-learning process through the massive online platform. Using topic modeling approach, our results show terms with prior knowledge to understand e.g.: Chuck as the instructor name. So, we proposed the topic modeling approach on helpful subjective reviews. The results show five influential factors: “learn easy excellent class program”, “python learn class easy lot”, “Program learn easy python time game”, and “learn class python time game”. Also, research results showed that the proposed method improved the perplexity score on the LDA model.

scholarly journals A Bayesian CNN-LSTM Model for Sentiment Analysis in Massive Open Online Courses MOOCs

2021 ◽  
Vol 16 (23) ◽  
pp. 216-232
Author(s):  
Khaoula Mrhar ◽  
Lamia Benhiba ◽  
Samir Bourekkache ◽  
Mounia Abik
Keyword(s):  
Sentiment Analysis ◽  
Online Courses ◽  
Dropout Rate ◽  
Massive Open Online Courses ◽  
Dropping Out ◽  
Bayesian Neural Network ◽  
Massive Open Online ◽  
Collaborative Tools ◽  
Novel Approach ◽  
Analysis Task

Massive Open Online Courses (MOOCs) are increasingly used by learn-ers to acquire knowledge and develop new skills. MOOCs provide a trove of data that can be leveraged to better assist learners, including behavioral data from built-in collaborative tools such as discussion boards and course wikis. Data tracing social interactions among learners are especially inter-esting as their analyses help improve MOOCs’ effectiveness. We particular-ly perform sentiment analysis on such data to predict learners at risk of dropping out, measure the success of the MOOC, and personalize the MOOC according to a learner’s behavior and detected emotions. In this pa-per, we propose a novel approach to sentiment analysis that combines the advantages of the deep learning architectures CNN and LSTM. To avoid highly uncertain predictions, we utilize a Bayesian neural network (BNN) model to quantify uncertainty within the sentiment analysis task. Our em-pirical results indicate that: 1) The Bayesian CNN-LSTM model provides interesting performance compared to other models (CNN-LSTM, CNN, LSTM) in terms of accuracy, precision, recall, and F1-Score; and 2) there is a high correlation between the sentiment in forum posts and the dropout rate in MOOCs.

scholarly journals Identification of Affective States in MOOCs

2018 ◽  
Vol 6 (12) ◽  
pp. 39-55
Author(s):  
Napoliana Souza ◽  
Gabriela Perry
Keyword(s):  
Machine Learning ◽  
Data Analysis ◽  
Learning Analytics ◽  
Online Courses ◽  
Massive Open Online Courses ◽  
Signal Recognition ◽  
Affective States ◽  
Massive Open Online ◽  
Data Intensive ◽  
Physiological Signal

Massive Open Online Courses (MOOCs) are a type of online coursewere students have little interaction,  no instructor, and in some cases, no deadlines to finisch assignments. For this reason, a better understanding of student affection in MOOCs is importantant could have potential to open new perspectives for this type of course. The recent popularization of tools, code libraries and algorithms for intensive data analysis made possible collect data from text and interaction with the platforms, which can be used to infer correlations between affection and learning. In this context, a bibliographical review was carried out, considering the period between 2012 and 2018, with the goal of identifying which methods are being to identify affective states. Three databases were used: ACM Digital Library, IEEE Xplore and Scopus, and 46 papers were found. The articles revealed that the most common methods are related to data intensive techinques (i.e. machine learning, sentiment analysis and, more broadly, learning analytics). Methods such as physiological signal recognition andself-report were less frequent.

scholarly journals The Effect of Non-Monetary Rewards on Employee Performance in Massive Open Online Courses

2020 ◽  
Vol 15 (01) ◽  
pp. 88 ◽  
Author(s):  
Pradorn Sureephong ◽  
Winai Dahlan ◽  
Suepphong Chernbumroong ◽  
Yootthapong Tongpaeng
Keyword(s):  
Online Courses ◽  
Positive Impact ◽  
Employee Performance ◽  
Online Training ◽  
Employee Motivation ◽  
Dropout Rate ◽  
Massive Open Online Courses ◽  
Science Center ◽  
Massive Open Online ◽  
Monetary Rewards

A challenge for organizations is to increase employee performance and motivation, since the most crucial asset of every organization is manpower. Many companies and factories have started implementing online training platforms under the concept of “Massive Open Online Courses (MOOCs)” in their workplace to foster employee performance. Previously, the mobile application called “HSC MOOC” which is provided by the Halal Science Center, Chulalongkorn Univer-sity, Thailand functioned as a solution that encourages self-learning on online platforms at companies in Thailand. However, the main barrier or risk that occurs when implementing an online platform is the user’s motivation, since the dropout rate is considered as a serious issue regarding MOOCs. Thus, incentive and re-ward were added to online training programs which aimed to motivate employees. Many types of rewards were provided for employees who had met their own company’s expectations. Recently, psychology research papers have illustrated that non-monetary rewards seem to provide greater results on the side of employee’s motivation. However, not all types of non-monetary rewards provide positive impact on employee’s motivation. Therefore, the aim of this research is to present the effect of different non-monetary rewards on employee performance. Ninety volunteer employees from a food manufacturing company in Chiang Mai, Thailand participated in this research. The experiment was divided into two sections. The first section aimed to measure the motivation of employees which based on different non-monetary rewards. The questionnaire for measuring Valence, Instrumentality, and Expectancy variables (VIE theory) was deployed to test employee motivation in 3 different groups; “Tangible Non-Monetary Re-wards”, “Social Non-Monetary Rewards” and “Job Related Non-Monetary Re-wards”. The test consisted of 10 items using a 5-point Likert scale. The second experiment aimed to reveal which type of non-monetary reward is the most suitable for motivating employees in participating and completing the course in MOOCs. Participants in different groups were assigned to learn via MOOCs on their mobile device within a period of 30 days. Different types of non-monetary rewards were provided only for participants who had completed certain conditions in MOOCs. The overall results showed that the group of tangible non-monetary rewards reached the significant highest score on the VIE questionnaire and over 60% of participants exposed to tangible non-monetary rewards completed the course’s conditions in MOOCs.

scholarly journals A Grounded Theory Exploration of Language Massive Open Online Courses (LMOOCs): Understanding Students’ Viewpoints

2021 ◽  
Vol 13 (5) ◽  
pp. 2577
Author(s):  
Robert Li-Wei Hsu
Keyword(s):  
Grounded Theory ◽  
Theoretical Model ◽  
Online Courses ◽  
Internet Access ◽  
Dropout Rate ◽  
Massive Open Online Courses ◽  
English For Specific Purposes ◽  
Massive Open Online ◽  
Innovation In Education ◽  
High Dropout Rate

Massive open online courses (MOOCs) have been called the biggest innovation in education in 200 years for their unique attribute of being open and free to any individual with Internet access; however, their high dropout rate has led many people to be concerned or dubious about their effectiveness and applicability. The applicability of MOOCs in English for specific purposes (ESP) courses (in this case, hospitality English) needs more empirical evidence; the present study intends to help fill this gap and extend our current understanding of this issue. This study followed a grounded theory methodology to develop a theoretical model based on a constant dialogue between collected data and the literature. The results suggest that most participants had positive perceptions of language MOOCs (LMOOCs) in general, but some doubted their applicability. Most participants said they would continue to use LMOOCs for learning, depending on the attributes of specific courses. Based on the extracted data, a conceptual model for the applicability of LMOOCs is proposed.

scholarly journals Massive Open Online Courses (MOOCs) Dropout Rate in the World: A Systematic Review Protocol

2020 ◽  
Author(s):  
Manoosh Mehrabi ◽  
Ali Reza Safarpour ◽  
Abbas Ali Keshtkar
Keyword(s):  
Systematic Review ◽  
Online Courses ◽  
Meta Analysis ◽  
Dropout Rate ◽  
Open Science ◽  
Massive Open Online Courses ◽  
Massive Open Online ◽  
The World ◽  
Review Protocol ◽  
Science Framework

Abstract BackgroundRecently, massive open online courses (MOOCs) have received increasing popularity throughout the world. Regardless of the subject taught and the university providing the course, the dropout rate of MOOCs is one of the most important challenges ahead.Methods This systematic review will search MEDLINE/PubMed, Scopus, Web of Science (Clarivate Analytics), Embase (Embase.com), ASSIA, CINAHL, Education Research, BEI, and Eric databases systematically according to predefined criteria without language restrictions to retrieve prospective and retrospective observational studies conducted between the 1st of January 2000 and 30th of March 2020 which evaluated the frequency of leaving MOOCs throughout the world. In the absence of severe methodological heterogeneity, the data will be combined and a meta-analysis will be performed. DiscussionAs dropout rate is one of the most challenges that universities may encounter, this systematic review will help universities extend their view, save their resources or maybe design their MOOCs differently.RegistrationRegistered in Open Science Framework, available at: https://osf.io/jgyqx/

scholarly journals Dropout Time and Learners’ Performance in Computer Programming MOOCs

2021 ◽  
Vol 11 (10) ◽  
pp. 643
Author(s):  
Marili Rõõm ◽  
Marina Lepp ◽  
Piret Luik
Keyword(s):  
Quantitative Study ◽  
Computer Programming ◽  
Online Courses ◽  
Dropout Rate ◽  
Massive Open Online Courses ◽  
Dropping Out ◽  
Massive Open Online ◽  
High Dropout Rate ◽  
Different Levels

One of the problems regarding MOOCs (Massive Open Online Courses) is the high dropout rate. Although dropout periods have been studied, there is still a lack of understanding of how dropout differs for MOOCs with different levels of difficulty. A quantitative study was conducted to determine the periods with the highest dropouts in computer programming MOOCs and the performance of the dropouts on the course before dropping out. Four occurrences of three MOOCs, with different durations, difficulty of the topic, and the degree of supportive methods, were included. The results showed that dropout was highest at the beginning of all studied courses. Learners also dropped out before the project. In the easier and shorter courses, most dropouts were successful until they quit the course. In longer and more difficult courses, learners mainly dropped out in the week they started due to experiencing problems with the course activities. It is suggested to recommend that learners take courses at a level that suits them if their current course is too easy or difficult and encourage learners to use course resources for help. It would be a good idea to provide learners with example topics to assist them in starting with a project.

Sign in / Sign up

Export Citation Format

Share Document