KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/kmitl/1

Browse

Settings

Subject: search.filters.subject.e-learning

Search Results

Now showing 1 - 4 of 4
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Predicting the Risk of Ultimate Low Ratings in Online Courses Using Machine Learning: Analyzing Engagement and Complexity for AI-Driven Early Instructional Communication Interventions
    (2026-01-01)
    Kraishan, Obada
    ;
    Jitkajornwanich, Kulsawasd
    ;
    Vijaranakul, Nattadet
    ;
    Kee, Kerk
    Online asynchronous courses have become a common way of learning, especially after the COVID-19 epidemic. Despite their convenience and flexibility, these courses often suffer from low engagement and/or poor course quality, ultimately reflected by a low rating. A low rating is often noted at the end of a course, by when it is often too late to intervene or improve the course. The goal of this study is twofold. First, we aim to identify key factors influencing the ultimate ratings for online asynchronous courses. Second, we then build an AI model to predict the risk of ultimate low ratings before a course is fully completed. Inspired by Moore’s model of interaction, which includes two main factors: learner-content and learner-instructor interactions, we derived two features from the dataset: course complexity and course engagement. We used a dataset of 191,849 Udemy courses collected from May 2024 to August 2024. To predict the ultimate low ratings in advance so mid-course interventions are possible, we applied machine learning models, including Logistic Regression, Random Forest, and XGBoost. In our experiments, the XGBoost model achieved the highest performance with 71% accuracy, with course complexity and the number of reviews left by learners being the two most influential factors in predicting a low course rating. Constantly monitoring course complexity and the number of course reviews can help with early detection. The findings can provide valuable, actionable insights and guidance for online education platforms, especially for instructors to adjust their courses before the courses are complete.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    RSQLG: The Reverse SQL Question Generation Algorithm
    (2019-05-14)
    Julavanich, Thanakrit
    ;
    Nalintippayawong, Srinual
    ;
    Atchariyachanvanich, Kanokwan
    Nowadays, the people who learn and teach SQL commands require to get a hand-on practice with real environment to make the learning effective. The creating SQL exercise is a time-consuming task for instructors. As a result, students might not get enough questions to meet their demands. The reverse SQL question generation algorithm (RSQLG) is developed to solve this problem. The RSQLG has ability to automatically generate SQL exercise for students. The RSQLG can reverse the manual question creation process which starts from creating question to start creating query answer first instead. The RSQLG considers the existing data and database structure by using various constraints. The instructors also can specify the language, format and explanation of the questions. The RSQLG supports DML commands-SELECT, INSERT, UPDATE and DELETE-and support data retrieval from multiple tables which perform by JOIN and subquery operations. The algorithm has ability to generate bulk questions with less effort. The instructor is not required to writing requirements and validating the queries. The RSQLG can be implemented in e-learning to enhance sustainable practices and improve learning outcome for students.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    The effect of the “Prediction-observation-quiz-explanation” inquiry-based e-learning model on flow experience in green energy learning
    (2019-05-01)
    Hong, Jon Chao
    ;
    Tsai, Chi Ruei
    ;
    Hsiao, Hsien Sheng
    ;
    Chen, Po Hsi
    ;
    Chu, Kuan Cheng
    There are several models of inquiry-based learning, some of which may be practiced in experimental classroom teaching, and some of which may be used in online teaching. This study proposes the “prediction-observation-quiz-explanation” (POQE) model to design a green energy generation learning program (i.e., how solar, wind, and water can produce energy) and to test how participants' cognitive-affective factors affect their interest in using this model. A total of 396 technical high school students participated in this experimental study, and 375 valid data were collected and subjected to confirmatory factor analysis with structural equation modelling. The results indicated that incremental belief of intelligence was negatively related to cognitive load, but positively related to green energy learning self-efficacy (GELSE) in practicing POQE. Cognitive load was negatively related to flow experience, while GELSE was positively related to flow experience. Finally, flow experience was positively related to the intention to continue online learning with the POQE model. The implications of this study are that e-learning designers can use this POQE model to develop more educational content for students to learn various concepts.
      1
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Examining the motivation level of students in e-learning in higher education institution in Thailand: A case study
    (2018-11-01)
    Kew, Si Na
    ;
    Petsangsri, Sirirat
    ;
    Ratanaolarn, Thanin
    ;
    Tasir, Zaidatun
    The rapid growth of Internet technology has resulted in the development of e-learning in higher education institution with the purpose of enhancing students’ performance in their learning practice. In this regard, motivation is one of the important predictors of intention to use e-learning that can in turn make impact on students’ learning practice. By knowing the motivation level of students, instructors can provide suitable teaching materials in e-learning for students to make them more engaged in e-learning activities. Nonetheless, based on the recent review studies result, there is limited research on investigating motivation level of students in e-learning in higher education institution in Thailand. Hence, this study aims to explore the motivation level of students in e-learning in higher education institutions in Thailand, using the Instructional Materials Motivation Survey and interview as the research instruments. A total of 174 students from higher education institutions in Thailand were involved in this study. SPSS software was used to analyse the data to investigate the motivation level of students, and also to compare the different motivation level of students between gender, degree level of study, branch of study and year of study. The result shows that most of the students had upper medium level of motivation level in e-learning, and there was a statistically significant difference in motivation level between the different degree levels of students. Also, the ways to enhance motivation suggested by the respondents were also discussed in this paper as a reference for the future use.
      1