scholarly journals Understanding Student Engagement in Large-Scale Open Online Courses: A Machine Learning Facilitated Analysis of Student’s Reflections in 18 Highly Rated MOOCs

2018 ◽  
Vol 19 (3) ◽  
Author(s):  
Khe Foon Hew ◽  
Chen Qiao ◽  
Ying Tang
Keyword(s):  
Machine Learning ◽  
Large Scale ◽  
Online Courses ◽  
Subject Area ◽  
Online Course ◽  
Valuable Insight ◽  
Course Quality ◽  
Learning Classifier ◽  
Quality Rating ◽  
Open Courses

Although massive open online courses (MOOCs) have attracted much worldwide attention, scholars still understand little about the specific elements that students find engaging in these large open courses. This study offers a new original contribution by using a machine learning classifier to analyze 24,612 reflective sentences posted by 5,884 students, who participated in one or more of 18 highly rated MOOCs. Highly rated MOOCs were sampled because they exemplify good practices or teaching strategies. We selected highly rated MOOCs from Coursetalk, an open user-driven aggregator and discovery website that allows students to search and review various MOOCs. We defined a highly rated MOOC as a free online course that received an overall five-star course quality rating, and received at least 50 reviews from different learners within a specific subject area. We described six specific themes found across the entire data corpus: (a) structure and pace, (b) video, (c) instructor, (d) content and resources, (e) interaction and support, and (f) assignment and assessment. The findings of this study provide valuable insight into factors that students find engaging in large-scale open online courses.

Using Gagné's Events of Instruction to Analyze Online Course Quality

2011 ◽  
pp. 2231-2238 ◽  
Author(s):  
Marc R. Robinson
Keyword(s):  
Instructional Design ◽  
Online Education ◽  
Learning Community ◽  
Student Perceptions ◽  
Course Design ◽  
Online Courses ◽  
Online Course ◽  
Design Quality ◽  
Course Quality ◽  
Events Of Instruction

Student perceptions of online courses are likely influenced by two overarching aspects of quality: instructor quality and course design quality (Ortiz-Rodriguez, Telg, Irani, Roberts & Rhoades, 2005). Both of these forces in online education may be analyzed using a well-known model of instructional design - Gagnés instructional design and cognition theory, the centerpiece of which are the nine events of instruction (Gagné, Wager, Golas, & Keller, 2004). Multiple studies positively correlate learner attitudes and perceptions of the online course to instructor quality. Early studies evaluating instructor quality attempted to correlate instructor quality with the attitude and perception of the learner, but not directly to learner success or course design quality. Researchers of online courses, such as Palloff & Pratt (2003), discussed the role of the instructor in depth while neglecting the roles of the learner, the institution, and course design. The main focus remained instructor-centered, and highlighted key instructor tasks such as understanding the virtual learner in terms of roles the learner plays, fostering team roles for the learner, designing an effective course orientation, and identifying potential legal issues the instructor might face (Palloff & Pratt, 2002, p. 16). A distant secondary focus was on effective course design. This highlighted instructor tasks in building an effective online learning community without highlighting the roles effective communication tools would play.

Understanding learner participation at scale: How and why

2020 ◽  
Vol 17 (3) ◽  
pp. 236-252
Author(s):  
Samaa Haniya ◽  
Luc Paquette
Keyword(s):  
Teaching And Learning ◽  
Large Scale ◽  
Online Courses ◽  
Massive Open Online Courses ◽  
Online Course ◽  
Massive Open Online ◽  
Learner Participation ◽  
Massive Open Online Course ◽  
Motivation For Learning ◽  
E Learning

Understanding learner participation is essential to any learning environment to enhance teaching and learning, especially in large scale digital spaces, such as massive open online courses. However, there is a lack of research to fully capture the dynamic nature of massive open online courses and the different ways learners participate in these emerging massive e-learning ecologies. To fill in the research gap, this paper attempted to investigate the relationship between how learners choose to participate in a massive open online course, their initial motivation for learning, and the barriers they faced throughout the course. This was achieved through a combination of data-driven clustering approaches—to identify patterns of learner participation—and qualitative analysis of survey data—to better understand the learners’ motivation and the barriers they faced during the course. Through this study we show how, within the context of a Coursera massive open online course offered by the University of Illinois, learners with varied patterns of participation (Advanced, Balanced, Early, Limited, and Delayed Participation) reported similar motivations and barriers, but described differences in how their participation was impacted by those factors. These findings are significant to gain insights about learners’ needs which in turn serve as the basis to innovate more adaptive and personalized learning experiences and thus advance learning in these large scale environments.

scholarly journals Trainable High Resolution Melt Curve Machine Learning Classifier for Large-Scale Reliable Genotyping of Sequence Variants

PLoS ONE ◽  
2014 ◽  
Vol 9 (10) ◽  
pp. e109094 ◽  
Author(s):  
Pornpat Athamanolap ◽  
Vishwa Parekh ◽  
Stephanie I. Fraley ◽  
Vatsal Agarwal ◽  
Dong J. Shin ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Resolution ◽  
Large Scale ◽  
Sequence Variants ◽  
High Resolution Melt ◽  
Learning Classifier

scholarly journals Quality evaluation of online courses during COVID-19 pandemic based on integrated FCE-AHP method

2021 ◽  
pp. 1-12
Author(s):  
Bin Tang ◽  
Shiwei Guo ◽  
Mathias Yeboah ◽  
Zhenhua Wang ◽  
Song Cheng
Keyword(s):  
Teaching And Learning ◽  
Online Courses ◽  
Influence Factors ◽  
Teaching Quality ◽  
University Education ◽  
Online Course ◽  
Fuzzy Evaluation ◽  
Negative Effects ◽  
Course Quality ◽  
University Campuses

After sudden outbreak of COVID-19 pandemic, the university campuses were closed and millions of university teachers and students had to shift teaching and learning activities from the classrooms to online courses in China. The COVID-19 pandemic undoubtedly brought significant negative effects to university education activities. How does COVID-19 influenced teaching quality and the degree of influences have been studied by many researches. However, the online course quality which is influences by COVID-19 pandemic was commonly evaluated qualitatively rather than quantitatively. In order to obtain quantitative evaluation results of online course quality during the pandemic period, the integrated FCE-AHP evaluation was applied. Based on real case of online courses, the influence factors of online course quality were divided into four first-level indicators and further subdivided into 14 second level indicators. The weight vectors of evaluation indicators were determined based on experts’ comments from the Teaching Affairs Committee and the fuzzy evaluation memberships were calculated based on questionnaire results of 2021 students. The evaluation results revealed that the integral performance of online courses is acceptable and the performances of students and hardware are relative weaker. Finally, some improvement measures were conducted to deal with difficulties encountered in online courses during COVID-19 pandemic period.

A BERT Fine-tuning Model for Targeted Sentiment Analysis of Chinese Online Course Reviews

2020 ◽  
Vol 29 (07n08) ◽  
pp. 2040018
Author(s):  
Huibing Zhang ◽  
Junchao Dong ◽  
Liang Min ◽  
Peng Bi
Keyword(s):  
Random Field ◽  
Sentiment Analysis ◽  
Large Scale ◽  
Conditional Random Field ◽  
Semantic Representation ◽  
Fine Tuning ◽  
Online Course ◽  
Analysis Model ◽  
Accurate Analysis ◽  
Course Quality

Accurate analysis of targeted sentiment in online course reviews helps in understanding emotional changes of learners and improving the course quality. In this paper, we propose a fine-tuned bidirectional encoder representation from transformers (BERT) model for targeted sentiment analysis of course reviews. Specifically, it consists of two parts: binding corporate rules — conditional random field (BCR-CRF) target extraction model and a binding corporate rules — double attention (BCR-DA) target sentiment analysis model. Firstly, based on a large-scale Chinese review corpus, intra-domain unsupervised training of a BERT pre-trained model (BCR) is performed. Then, a Conditional Random Field (CRF) layer is introduced to add grammatical constraints to the output sequence of the semantic representation layer in the BCR model. Finally, a BCR-DA model containing double attention layers is constructed to express the sentiment polarity of the course review targets in a classified manner. Experiments are performed on Chinese online course review datasets of China MOOC. The experimental results show that the F1 score of the BCR-CRF model reaches above 92%, and the accuracy of the BCR-DA model reaches above 72%.

scholarly journals The Validity and Instructional Value of a Rubric for Evaluating Online Course Quality: An Empirical Study

2020 ◽  
Vol 24 (1) ◽  
Author(s):  
Ji Eun Lee ◽  
Mimi Recker ◽  
Min Yuan
Keyword(s):  
Online Courses ◽  
Online Course ◽  
Analysis Model ◽  
Course Performance ◽  
Learner Engagement ◽  
Course Quality ◽  
Online Interactions ◽  
Passing Rates ◽  
Quality Ratings ◽  
Using Data

This study investigated the validity and instructional value of a rubric developed to evaluate the quality of online courses offered at a midsized public university. This rubric was adapted from an online course quality rubric widely used in higher education, the Quality Matters rubric. We first examined the reliability and preliminary construct validity of the rubric using quality ratings for 202 online courses and eliminated twelve problematic items. We then examined the instructional value of the rubric by investigating causal relationships between 1) course quality scores, 2) online interactions between students, instructors, and content, and 3) student course performance (course passing rates). A path analysis model, using data from 121 online courses enrolling 5,240 students, showed that only rubric items related to learner engagement and interaction had a significant and positive effect on online interactions, while only student-content interaction significantly and positively influenced course passing rates.

Developing an Online Presence

2019 ◽  
pp. 201-229
Author(s):  
Stein Brunvand ◽  
Ilir Miteza
Keyword(s):  
Higher Education ◽  
Online Courses ◽  
Education Institution ◽  
Educational Opportunities ◽  
Online Course ◽  
Online Support ◽  
Faculty Support ◽  
University Of Michigan ◽  
Course Quality ◽  
The University

This chapter outlines the process developed at the University of Michigan – Dearborn (UM-Dearborn) to support the development, facilitation, and evaluation of online courses and programs. In addition to the step-by-step account of initiatives and actions, this chapter centers on the guiding principles of enhancing online course quality, investing in faculty support and innovation, and providing robust online support to students. Initiatives and strategies outlined in this chapter are undergirded by these principles and provide guidance to any higher education institution that has a limited and/or disparate catalog of online offerings and is committed to finding a pathway to a more robust array of online educational opportunities.

scholarly journals Playing with machines: Using machine learning to understand automated copyright enforcement at scale

2020 ◽  
Vol 7 (1) ◽  
pp. 205395172091996
Author(s):  
Joanne E Gray ◽  
Nicolas P Suzor
Keyword(s):  
Machine Learning ◽  
Computational Methods ◽  
Large Scale ◽  
Detection System ◽  
Language Model ◽  
Levels Of Abstraction ◽  
Systematic Analysis ◽  
Learning Classifier ◽  
Large Scale Analysis ◽  
Copyright Enforcement

This article presents the results of methodological experimentation that utilises machine learning to investigate automated copyright enforcement on YouTube. Using a dataset of 76.7 million YouTube videos, we explore how digital and computational methods can be leveraged to better understand content moderation and copyright enforcement at a large scale.We used the BERT language model to train a machine learning classifier to identify videos in categories that reflect ongoing controversies in copyright takedowns. We use this to explore, in a granular way, how copyright is enforced on YouTube, using both statistical methods and qualitative analysis of our categorised dataset. We provide a large-scale systematic analysis of removals rates from Content ID’s automated detection system and the largely automated, text search based, Digital Millennium Copyright Act notice and takedown system. These are complex systems that are often difficult to analyse, and YouTube only makes available data at high levels of abstraction. Our analysis provides a comparison of different types of automation in content moderation, and we show how these different systems play out across different categories of content. We hope that this work provides a methodological base for continued experimentation with the use of digital and computational methods to enable large-scale analysis of the operation of automated systems.

Reading Between the Lines of Online Course Evaluations: Predictable Actions that Improve Student Perceptions of Teaching Effectiveness and Course Value

2012 ◽  
Vol 16 (1) ◽  
Author(s):  
Stephanie J Jones
Keyword(s):  
Student Perceptions ◽  
Teaching Effectiveness ◽  
Online Courses ◽  
Course Evaluations ◽  
Online Course ◽  
Course Quality ◽  
Evaluation Scores ◽  
Faculty Effectiveness ◽  
Perceptions Of Teaching ◽  
Course Value

Students continue to demand and enroll in online courses, but are not always satisfied with their experiences. The purpose of this study was to determine if students’ responses to evaluations for online courses could be used to predict faculty actions that could lead to improved evaluation scores in teaching effectiveness and overall course value. Controversy continues to exist over the validity of student evaluations to measure faculty effectiveness and overall course quality. Faculty seldom utilize the collected data for the improvement of teaching. Results indicate that stimulation of learning had the most effect on perceptions of teaching effectiveness and useful and relevant assignments had the highest correlation to overall course value.

Next-generation community ecology: Exploring ecological and evolutionary drivers of planktonic foraminifera diversity using the Endless Forams database and a supervised machine learning classifier

2020 ◽  
Author(s):  
Allison Hsiang ◽  
Pincelli Hull
Keyword(s):  
Machine Learning ◽  
Community Ecology ◽  
Large Scale ◽  
Morphological Evolution ◽  
Planktonic Foraminifera ◽  
Supervised Machine Learning ◽  
The North ◽  
Learning Classifier ◽  
Speed Up ◽  
The Rich

<p>The rich fossil record of planktonic foraminifera makes them an indispensable group for understanding interactions between climatic, oceanic, and biological dynamics through time and space. Over the past few years, we have been working to provide databases and informatics resources to standardize and speed up the generation of large datasets for community-scale analyses of planktonic foraminifera. Our public database Endless Forams Most Beautiful (www.endlessforams.org), which currently contains >34,000 unique images of individual planktonic foraminifera comprising 35 species, is an important new resource for taxonomic training and standardization, supervised machine learning, and large-scale analyses of community ecology and morphological evolution. Here, we present one such application using both the individuals in the Endless Forams database and an additional ~26,000 specimens from across the North Atlantic, identified using a supervised machine learning classifier trained using the Endless Foram data. We combine taxonomic information from these ~60,000 individuals with morphometric measurements extracted using our open source software AutoMorph to explore ecological and evolutionary drivers of modern planktonic foraminifera diversity and size.</p>

Sign in / Sign up

Export Citation Format

Share Document