Personalized E-learning system with self-regulated learning assisted mechanisms for promoting learning performance
Introduction
In recent years, learning modes have experienced a revolution due to the rapid growth of Internet technologies. In conventional classroom learning, learners typically play a passive role as teachers are used to conveying knowledge and experiences to learners. Since learners rely highly on teacher instruction to acquire knowledge during learning processes, most learners could lose lifelong learning abilities due to their lack of autonomous learning and self-reflection abilities (Shih, Chang, Chen, & Wang, 2005). In modern education, learners have a primary role in learning; teachers teach knowledge and convey experiences to learners, and direct learners to construct knowledge based on learner self-analysis, self-examination, and autonomous exploration abilities. Notably, the Internet can overcome the limitations of time and space to establish a convenient learning environment; that is, learners use a web-based learning environment to acquire knowledge at any time and any place via the Internet. Undoubtedly, web-based learning environments, which satisfy the requirement that learners are a central role in learning, are becoming increasingly popular. The most urgent issue in web-based learning is to identify the abilities learners should cultivate. Many studies have identified a significant positive correlation between academic achievement and self-regulated learning ability among students at different stages of academic development (Dabbagh and Kitsantas, 2005, Kumar et al., 2005, Narciss et al., 2007, Schunk and Zimmerman, 1994). Many studies have indicated that students with poor self-regulating ability are not as academically successful as those with good abilities (Zimmerman & Schunk, 1989). In other words, good learners typically have good self-regulating learning abilities. Therefore, the most important task for instructional designers and teachers is to develop effective strategies that encourage and guide learners in actively processing learning actions. Particularly, learners must frequently encounter web-based learning systems alone, without a teacher to oversee their learning attitudes and behavior; consequently, the self-regulated learning ability of individual learners is an important factor affecting learning performance in web-based learning environments. This study focused primarily on developing self-regulated learning assisted mechanisms for web-based learning systems that assist learners in monitoring their own self-learning situations and direct their learning motivation toward to good self-regulated learning abilities, thereby enhancing the learning performance of individual learners.
Currently, self-regulated learning (SRL) has received considerable interest in the education and psychology fields. The SRL model developed by Zimmerman mainly examined learning characteristics in active learning from the perspectives of meta-cognition, motivation, and behavior (Zimmerman et al., 1996, Zimmerman and Schunk, 2001). Self-regulated learning was defined by Zimmerman as the degree to which learners are metacognitively, motivationally and behaviorally active participants in their own learning (Zimmerman, 1986a, Zimmerman, 1986b). That is, self-regulated learning refers to a learning situation in which learners set their learning goals, plan, and then regulate and evaluate the learning process independently (Narciss et al., 2007). The goal of SRL for learners is to learn to be their own teachers (Schunk and Zimmerman, 1998, Torrano Montalvo and Gonzalez Torres, 2004). That is, good achievement via SRL requires a strong will to learn and excellent learning skills (Torrano & González, 2004).
Recently, many studies have developed web-based learning systems with SRL mechanisms that promote learning effectiveness. For example, Shih et al. (2005) proposed a SRL system with a scaffold support that assists learners in developing a learning schedule and process management of learners, to promote learning performance for self-regulated m/e-learning. Joo, Bong, and Choi (2000) employed a self-efficacy scale in a motivated strategies for learning questionnaire (MSLQ) to investigate self-efficacy for SRL, academic self-efficacy, and Internet self-efficacy. Their survey results indicated that student self-efficacy for SRL positively correlated with academic self-efficacy, strategy use, and Internet self-efficacy. Moreover, Chang (2005) investigated the effect of SRL strategies on learner perceptions of motivation for web-based instruction. The self-regulated learning strategies were intended to assist students to self-observe and self-evaluate learning effectiveness. The research results obtained by Chang revealed that student learning within a web-based environment with self-regulated learning strategies was responsible for student learning. Additionally, Niemi, Nevgi, and Virtanen (2003) focused on guiding students to cultivate self-reflection and self-evaluation using the IQ Learn tool, thereby helping students develop self-regulatory skills in web-based learning environments.
Based on surveys mentioned-above, this study develops effective SRL-assisted mechanisms for a personalized e-learning system (PELS) to enhance learner self-regulated learning abilities and learning performance. In the proposed SRL strategies, four SRL competence indexes are proposed to assess SRL behavior of individual learners. Two learning performance indexes are proposed to assess the learning performance of individual learners in the PELS assisted by the SRL-assistive mechanisms. Additionally, we believe that a heteronomy mechanism comes from teacher assistance can transform learners with poor SRL abilities into autonomous self-regulated learners in a web-based learning environment. In summary, this study presents SRL-assisted mechanisms in the PELS that can cultivate learners’ self-regulated learning abilities using the proposed SRL assessment mechanism with immediate feedback response to learners and a heteronomy mechanism comes from teacher’s reminding. Experimental results indicated that the proposed self-regulated learning mechanisms change passive learners with poor SRL abilities into active learners with spontaneous learning abilities, thereby improving learning achievement in a web-based learning environment.
Section snippets
Self-regulated learning
This section first discusses the SRL theory developed by Zimmerman’s and used in this study, and then the proposed SRL model is presented.
The proposed self-regulated learning assisted mechanisms in the personalized E-learning system
This section presents the system design, system architecture and system components of the proposed PELS with SRL-assisted mechanisms. An overview of system design is presented in Section 3.1. Sections 3.2 System architecture, 3.3 System components of the proposed self-regulated learning mechanisms, 3.4 The implemented personalized E-learning system with self-regulated learning assisted mechanisms then describe the system architecture, system components and the proposed self-regulated learning
Experimental analyses
The personalized e-learning system with self-regulated learning assisted mechanisms (SRL-PELS) was published on the web site http://irt7.dlll.nccu.edu.tw/ to provide personalized e-learning services and enable the learning performance promotion by the proposed self-regulated learning assisted mechanism in recommending personalized course material to be evaluated. The experimental environment and results are analyzed and described as follows.
Conclusion
This study presents a personalized e-learning system with SRL-assistive mechanisms that promote SRL abilities of individual learners. The proposed mechanisms efficiently help learners in self-evaluating their learning goals and performance by immediately displaying a self-regulated learning radar plot with five-dimension self-regulated learning indicators during learning processes. Furthermore, the interactive teaching agent, which contains hint message and immediate Q&A modules were designed
References (23)
- et al.
Personalized E-learning system using item response theory
Journal of Computer and Education
(2005) - et al.
Personalized curriculum sequencing using modified item response theory for web-based instruction
Expert Systems with Applications
(2006) - et al.
Promoting self-regulated learning in web-based learning environments
Computers in Human Behavior
(2007) Development of self-regulated learning: Which are the key subprocesses?
Contemporary Educational Psychology
(1986)Item response theory: Parameter estimation techniques
(1992)- et al.
Feedback and self-regulated learning: A theoretical synthesis
Review of Education Research
(1995) Applying self-regulated learning strategies in a web-based instruction – an investigation of motivation perception
Computer Assisted Language Learning
(2005)- Chen, C. M., Liu, M. C., & Hsu, S. H. (2005). Applying interactive mobile teaching agent to support E-learning platform...
- et al.
Using web-based pedagogical tools as scaffolds for self-regulated learning
Instructional Science
(2005) - et al.
Self-efficacy for self-regulated learning, academic self-efficacy, and internet self-efficacy in web-based instruction
Educational Technology Research and Development
(2000)
Cited by (127)
The use of a personalized learning approach to implementing self-regulated online learning
2022, Computers and Education: Artificial IntelligenceCitation Excerpt :Table 1 shows that the students who followed the self-regulated online learning guided by the personalized learning approach outperformed and gained more knowledge than those who followed the conventional self-regulated online learning activities after finishing the learning process. These results comply with the previous studies mentioning that the online learning system incorporated individual characteristics, especially conceptual learning problems, and personal preferences fostered the improvement of online learning environment quality, leading students to enhance learning (Chen, 2009; Hwang et al., 2012; Kochmar et al., 2021; McCarthy, Liu, & Schauer, 2020; McCarthy et al., 2020, 2020; Romero et al., 2019). These results led this study to focus on an optimal goal of examining the factors influencing the students’ behavioral intention to use the self-regulated online learning guided by the personalized learning approach in their future learning.
Informing the Implementation of Personalized Learning in the Middle Grades through a School-wide Genius Hour
2024, Dialogues in Middle Level Education Research Volume 3: Insights from the AMLE New Directions 2022 Roundtable DiscussionsHOW TO SUPPORT STUDENTS' SELF-REGULATED LEARNING IN TIMES OF CRISIS: AN EMBEDDED TECHNOLOGY-BASED INTERVENTION IN BLENDED LEARNING PEDAGOGIES
2023, Academy of Management Learning and Education