SPOC online video learning clustering analysis: Identifying learners' group behavior characteristics

Abstract

With the widespread of Small Private Online Courses (SPOC) in colleges and universities, course organizers who provide high-quality personalized course activities need to understand learners' learning status and characteristics, and then optimize the course teaching. However, little research has been done on different learners' group behavior characteristics, such as which indicators can reflect learner groups' behavior, and what are the typical behavior characteristics of different learner groups. In this work, we established a Python Language Foundation self-built SPOC course, and 109 undergraduates' learning behavior data were collected and analyzed. From 74-dimensional behavior log data consisting of 72 video-viewing, course video score, and comprehensive score, Principal Component Analysis was performed to reduce dimensionality. Agglomerative hierarchical clustering was used to divide learners into different categories, and the results showed that 15 groups are clustered. According to the analysis of the four indicators for group characteristics, which are the completion and viewing-stability of task-point videos, unit test excellence, and comprehensive score, it is identified into five primary types, including positive type, regular type, negative type, seminegative type, and a fluctuation type. Experiments conducted on a real data set across different academic years and courses show that the proposed approach has better clustering accuracy and practicability. It is expected that this work may be used to strengthen the personalized learning support services system in educational institutions and develop a tool that integrates exploration and analysis work onto the web platform.

The Effect of SPOC Hybrid Model on Deep Learning Effectiveness: A Systematic Literature Review

“…Among the 27 papers screened since 2018-2023, 2 articles considered SPOC as a curricular tool that can enable deep learning, exploring the difficulties and crises encountered by SPOC in deep learning practice, but without giving specific recommendations Dong & Zeng, 2020); 18 papers focused on exploring 18 articles focus on exploring suggestions and measures for SPOC to facilitate deep learning An & Qu, 2021;Yang et al, 2019;Filius, 2019;Chen & Chen, 2019;Li et al, 2023;Liu, 2020;Filius & Uijl, 2021;Gan et al al., 2022), such as the development of SPOC courses (An & Qu, 2021), or enhancing learning through peer feedback ; eight papers focused on examining the role and effectiveness of SPOC for deep learning (Bin & Ahmad, 2022;Kang & He, 2018;Zhang et al, 2019;Ning et al, 2021;Chen et al, 2021;Ma, 2021;Shang, 2022). Moreover, most studies conducted on SPOC and deep learning are empirical.…”

“…Moreover, most studies conducted on SPOC and deep learning are empirical. Among them, interview method Ma, 2021;Hadad et al, 2021); questionnaire analysis Gan & Zhang, 2020); Bin & Ahmad, 2022;Zhang et al, 2019;Li et al, 2023;Ning et al, 2021), experimental method (Yang et al, 2020), and case method Kang & He, 2018;Dong & Zeng, 2020) as the primary research methods.…”

“…Of the 27 papers, 23 were positioned in higher education An & Qu, 2021;Yang et al, 2020;Bin & Ahmad, 2022;Kang & He. 2018;Gan & Zhang, 2020;Dong & Zeng, 2020;Xianyu & Hu, 2020;Chen & Chen, 2019;Li et al, 2023;Liu, 2020;Filius & Uijl, 2021;Chen et al, 2021;Gan et al, 2019;Xiao, 2020;Yue & Jiqiong, 2020;lAgrebi, 2019;Fang et al, 2022), and 21 studies from China (An & Qu, 2021;Yang et al, 2020;Kang & He, 2018;Gan & Uijl, 2021;Gan et al, He, 2018;Gan & Zhang, 2020;Dong & Zeng, 2020;Xianyu & Hu, 2020;Dong et al, 2020;Chen et al, 2021;Ma, 2021;Gan et al, 2019;Xiao, 2020;Yue & Jiqiong, 2020;Agrebi, 2019;Fang et al, 2022;Shang, 2022). Only some studies have focused on students in other academic segments (Ning et al, 2021) or pre-service training (Ma, 2021).…”

“…Of the 27 relevant papers, 16 papers treat deep learning as a learning state, focusing on exploring how this desired learning state can be achieved or enhanced through SPOC Yang et al, 2020;Kang & He, 2018;Dong & Zeng, 2020;Xianyu & Hu, 2020;Zhang et al, 2019;Filius, 2019;Chen & Chen, 2019;Li et al, 2023;Filius & Uijl, 2021;Chen et al, 2021;Yue & Jiqiong, 2020;Shang, 2022). 11 papers deal with deep learning as an educational theory to explore the application of SPOC guided by deep learning theory and the final results that this application can achieve (An & Qu, 2021;Bin & Ahmad, 2022;Gan & Zhang, 2020;Dong et al, 2019;Ning et al, 2021;Liu, 2020;Gan et al, 2019;Xiao, 2020;Agrebi, 2019;Fang et al, 2022).…”

“…Reinforcement application, on the other hand, refers to the appropriate adaptation of the SPOC to reinforce factors that promote deeper learning (Bin & Ahmad, 2022), such as developing recommendations for the implementation of the SPOC based on CIMO logic ; or the design of a factor of the SPOC , such as enhancing peer feedback , as a way to enhance the effectiveness of SPOC for deep learning. Fifteen papers chose the model of reinforcement application Bin & Ahmad, 2022;Xianyu & Hu, 2020;Filius, 2019;Chen & Chen, 2019;Li et al, 2023;Ning et al, 2021;Liu, 2020;Filius & Uijl, 2021;Chen et al, 2021;Gan et al, 2019;Agrebi, 2019;Fang et al, 2022). In using SPOC to achieve or enhance deep learning goals, researchers have focused on designing and adapting SPOC to meet the requirements of deep learning.…”