scholarly journals Sentiment Analysis of Online Course Evaluation Based on a New Ensemble Deep Learning Mode: Evidence from Chinese

2021 ◽  
Vol 11 (23) ◽  
pp. 11313
Author(s):  
Xiaomin Pu ◽  
Guangxi Yan ◽  
Chengqing Yu ◽  
Xiwei Mi ◽  
Chengming Yu

In recent years, online course learning has gradually become the mainstream of learning. As the key data reflecting the quality of online courses, users’ comments are very important for improving the quality of online courses. The sentiment information contained in comments is the guide of course improvement. A new ensemble model is proposed for sentiment analysis. The model takes full advantage of Word2Vec and Glove in word vector representation, and utilizes the bidirectional long and short time network and convolutional neural network to achieve deep feature extraction. Moreover, the multi-objective gray wolf optimization (MOGWO) ensemble method is adopted to integrate the models mentioned above. The experimental results show that the sentiment recognition accuracy of the proposed model is higher than that of the other seven comparison models, with an F1score over 91%, and the recognition results of different emotion levels indicate the stability of the proposed ensemble model.

Author(s):  
D. Thammi Raju ◽  
G. R. K. Murthy ◽  
S. B. Khade ◽  
B. Padmaja ◽  
B. S. Yashavanth ◽  
...  

Building an effective online course requires an understanding of learning analytics. The study assumes significance in the COVID 19 pandemic situation as there is a sudden surge in online courses. Analysis of the online course using the data generated from the Moodle Learning Management System (LMS), Google Forms and Google Analytics was carried out to understand the tenants of an effective online course. About 515 learners participated in the initial pre-training needs & expectations’ survey and 472 learners gave feedback at the end, apart from the real-time data generated from LMS and Google Analytics during the course period. This case study analysed online learning behaviour and the supporting learning environment and suggest critical factors to be at the centre stage in the design and development of online courses; leads to the improved online learning experience and thus the quality of education. User needs, quality of resources and effectiveness of online courses are equally important in taking further online courses.


Author(s):  
Veronica Outlaw ◽  
Margaret L. Rice ◽  
Vivian H. Wright

The authors have personally experienced the burdens of creating online courses without the assistance of trained instructional designers. Many faculty are employed in conditions where they develop online courses without the proper knowledge and training of many essential aspects that should accompany the development of an online course (e.g., design, development, learning styles, copyright, design principles, accessibility, incorporating technology, and technical skills) (Singleton et al., 2013; Speck, 2000; Wickersham et al., 2007). The authors propose and describe the use of a detailed online course development and delivery model (Outlaw & Rice, 2015) that was created to provide distance education units with a systematic approach to course development. The proposed model nourishes the partnerships between faculty and designers to improve the quality of online courses, while providing the support faculty need to successfully create online courses. The authors discuss a model that provides consistency in efforts to create efficient workflows to develop online courses.


2020 ◽  
Vol 166 ◽  
pp. 10011
Author(s):  
Kateryna Vlasenko ◽  
Olena Chumak ◽  
Iryna Lovianova ◽  
Daria Kovalenko ◽  
Nataliia Volkova

The article looks into the issue of developing methodical requirements for the structure and content of online courses. The study is dedicated to the analysis of peculiarities of developing the content of online systems and developing methodical recommendations to educational materials for online courses of training higher school mathematics teachers. The research considers the experts’ experience in preparing, structuring and developing the content for online courses and answers to volunteers who have agreed to test the educational materials of the course. The answers given by the participants have allowed estimating the quality of the developed course and detecting its insignificant drawbacks. The article discusses general requirements to the structure and content of the online course, means for the implementation of a testing subsystem, peculiarities of developing educational video content and educational materials in PDF format, issues of implementing forum and survey subsystems, as well as means of estimating learning outcomes. We have grounds to conclude that the quality of the course is determined by the range of factors, among which we point out the course organization based on weekly planning, implementation of a testing subsystem under conditions of extended functionality, creation of abilities to organize feedback.


Author(s):  
Mohammad Khalil ◽  
Hubert Brunner ◽  
Martin Ebner

Massive Open Online Courses, shortly MOOCs, are a phenomenon nowadays. The number of courses is worldwide steadily increasing since Sebastian Thrun has offered a free online course for more than 100.000 students. Nowadays, decision makers and students as well as lecturers are asking about the quality of such courses. After a live experiment on 15 randomly chosen courses and a brief literature review, we discuss the possibility of finding an evaluation grid for xMOOCs. The finally suggested criteria can be used now for future investigations.


2014 ◽  
Vol 15 (3) ◽  
pp. 145-162 ◽  
Author(s):  
Jane E. Klobas

Purpose – The purpose of this paper is to propose measures of online open course success for non-commercial institutional providers of massive open online courses (MOOCs) and other scaleable open online courses (SOOCs). Design/methodology/approach – The measures are derived from the characteristics of open online courses, existing knowledge about open online course providers and users and their motivations, and current practice in MOOC evaluation and data analytics. Findings – Current practices for evaluation of open online courses are dominated by MOOC analytics which provide insights into user demographics and behaviour with some implications for evaluation of reach and course design but leaving many unknowns. Measures for evaluation of success at the institutional level can be derived from institutional goals for open online courses. Success from the point of view of teachers and technical teams involved in design, development and delivery of open online courses can be derived from team members’ expectations, resources and satisfaction as well as measures of cost and effort compared to budget and benchmarks. Users are classified as registrants (information seekers, window shoppers, samplers), downloaders and participants (starters, partial participants and full participants who are further divided into auditing, active and certificate takers); different measures are appropriate for each group. Practical implications – Practitioners and researchers must consider a variety of levels and indicators of success to adequately evaluate open online courses. Tables in the text propose measures, methods, timing and roles. Originality/value – This is the first published paper to take a holistic view of open online course evaluation and propose detailed measures.


2019 ◽  
Vol 6 (3) ◽  
pp. 321
Author(s):  
Nanang Fakhrur Rozi ◽  
Fandi Arianto ◽  
Dian Puspita Hapsari

<p>Tingginya minat penggunaan pesawat terbang dipengaruhi oleh tingginya tingkat mobilitas masyarakat yang menuntut perpindahan kota dalam waktu yang singkat. Meski demikian, tidak semua maskapai penerbangan mampu memberikan layanan yang memuaskan bagi konsumennya. Kualitas layanan yang diberikan oleh suatu maskapai, baik dari segi keselamatan, keamanan, maupun kenyamanan, umumnya dapat diketahui melalui opini penumpang lainnya. Banyaknya opini negatif yang didapat oleh maskapai mengindikasikan buruknya kualitas layanannya, begitu pula sebaliknya. Akan tetapi, jumlah opini yang semakin hari semakin meningkat menyebabkan sulitnya konsumen dalam menilai kualitas maskapai secara cepat. Oleh karena itu, analisis sentimen dibutuhkan guna mempercepat konsumen dalam menilai kualitas layanan maskapai. Hybrid Cuckoo Search (HCS) merupakan salah satu metode yang dapat digunakan untuk melakukan analisis tersebut. Metode ini mampu mengelompokkan informasi secara cepat. Penelitian ini bertujuan untuk mengimplementasikan HCS dalam melakukan analisis sentimen pada data opini penumpang maskapai penerbangan. Hasil uji coba menunjukkan bahwa nilai rata-rata akurasi, <em>precision</em>, dan <em>recall</em> dari data opini 7 maskapai dengan 1.000 iterasi masing-masing sebesar 69,24%; 70,88%; dan 77,57%.</p><p> </p><p><em><strong>Abstract</strong></em></p><p class="Abstract"><em>The high demands of airplanes usage are influenced by the increasing levels of people's mobility who want to trip from one city to another in a short time. However, not all airlines company could provide satisfactory services for the consumers. The quality of services provided by an airline, in terms of safety, security, and convenience, is usually known through passenger opinions. The number of negative opinions gained by airlines indicates its poor quality of service and vice versa. However, the increasing number of opinion increases the difficulty of the consumer in assessing the quality of the airline quickly. Therefore, sentiment analysis is needed to accelerate the consumer in assessing the quality of airline services. Hybrid Cuckoo Search (HCS) is a method which can be used in conducting such analysis. This method is able to group information quickly. This study aims to implement HCS in conducting sentiment analysis on airline passenger opinion data. The results show that the averaged accuracy, precision, and recall from opinion dataset of 7 airlines company at 1,000 iteration are 69.24%, 70.88%, and 77.57% respectively.</em></p><p><em><strong><br /></strong></em></p>


Author(s):  
Julia M. Matuga ◽  
Deborah Wooldridge ◽  
Sandra Poirier

This paper examines the critical issue of assuring quality online course delivery by examining four key components of online teaching and learning. The topic of course delivery is viewed as a cultural issue that permeates processes from the design of an online course to its evaluation. First, the authors examine and review key components of and tools for designing high impact online courses that support student learning. Second, in this paper, the authors provide suggestions for faculty teaching online courses to assist in creating high quality online courses that supports teaching and, consequently, facilitates opportunities for student learning. Quality online course delivery is also contingent on the support of faculty by administration. Lastly, this paper provides suggestions for conducting course evaluation and feedback loops for the continual improvement of online learning and teaching. These four components are essential elements in assuring quality online courses.


Author(s):  
Terry T. Kidd ◽  
Holim Song

This study assessed the perceptions of adult learners in online distance learning programs regarding the instructional quality of Web-based courses via WebCT. The results showed an overall positive perception regarding the instructional quality of online courses delivered via WebCT (M = 3.51, SD = 1.1362). The mean obtained for students’ perceptions regarding the instructional quality items ranged from 3.7 to 3.37. The visual appeal of Web site and appropriateness of the course materials received the highest rating (M = 3.625). Clarity and purpose in introduction to content components earned the lowest ratings (M = 3.37). These results were closely correlated to students’ responses regarding the important aspects of instructional quality of online courses. The most important aspect indicated by students was the idea of having online course content and materials relevant to the course. The results of the study also indicated other perceived aspects that affect students’ views of the instructional quality of an online course, including interaction, design, convenience, feedback, and usability.


2010 ◽  
pp. 228-248
Author(s):  
Yungwei Hao ◽  
Gary Borich

This chapter introduces a graphic approach to define quality inonline courses. The Decomposition Model (Borich & Jemelka, 1982) is used to illustrate course structure and the salient characteristics of an effective online course. The constraints that influence the success of online courses are discussed. Salient transactions (activities) that occur in online coursesare described. And the means-end continuum in the process of online learning is illustrated graphically. The chapter is expected to provide readers with a whole picture of a qualityonline course through an architectural framework.


Author(s):  
Julia M. Matuga ◽  
Deborah Wooldridge ◽  
Sandra Poirier

This paper examines the critical issue of assuring quality online course delivery by examining four key components of online teaching and learning. The topic of course delivery is viewed as a cultural issue that permeates processes from the design of an online course to its evaluation. First, the authors examine and review key components of and tools for designing high impact online courses that support student learning. Second, in this paper, the authors provide suggestions for faculty teaching online courses to assist in creating high quality online courses that supports teaching and, consequently, facilitates opportunities for student learning. Quality online course delivery is also contingent on the support of faculty by administration. Lastly, this paper provides suggestions for conducting course evaluation and feedback loops for the continual improvement of online learning and teaching. These four components are essential elements in assuring quality online courses.


Sign in / Sign up

Export Citation Format

Share Document