Dataset Information

A new ML-based approach to enhance student engagement in online environment

ABSTRACT: The educational research is increasingly emphasizing the potential of student engagement and its impact on performance, retention and persistence. This construct has emerged as an important paradigm in the higher education field for many decades. However, evaluating and predicting the student’s engagement level in an online environment remains a challenge. The purpose of this study is to suggest an intelligent predictive system that predicts the student’s engagement level and then provides the students with feedback to enhance their motivation and dedication. Three categories of students are defined depending on their engagement level (Not Engaged, Passively Engaged, and Actively Engaged). We applied three different machine-learning algorithms, namely Decision Tree, Support Vector Machine and Artificial Neural Network, to students’ activities recorded in Learning Management System reports. The results demonstrate that machine learning algorithms could predict the student’s engagement level. In addition, according to the performance metrics of the different algorithms, the Artificial Neural Network has a greater accuracy rate (85%) compared to the Support Vector Machine (80%) and Decision Tree (75%) classification techniques. Based on these results, the intelligent predictive system sends feedback to the students and alerts the instructor once a student’s engagement level decreases. The instructor can identify the students’ difficulties during the course and motivate them through e-mail reminders, course messages, or scheduling an online meeting.

SUBMITTER: Ayouni S

PROVIDER: S-EPMC8580220 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundOnline communities and social networking sites have great potential for supporting health behavior change. However, interventions vary greatly in participants' engagement rates and, consequently, their effectiveness. Theory-based interventions in real-world contexts are needed to further increase engagement and effectiveness.MethodsWe experimentally tested whether a video intervention teaching Self-Determination-Theory-based communication strategies increases need-supportive communication strategy use over one week (Study 1, N = 76) and perceived need support, engagement, and goal attainment in a behavior change intervention supported by a forum-based online community (Study 2, N = 537). In Study 2, participants chose a goal (increasing either fruit or vegetable consumption or increasing moderate or vigorous physical activity) and joined an online community for 2 weeks. Data from both experiments were analyzed with mixed models and follow-up tests.ResultsIn Study 1, participants in the intervention but not in the control group showed an increase in the number of need-supportive communication strategies used both immediately and one week after the intervention (condition × time interaction, partial η 2 = 0.31). In Study 2, participants who watched the intervention video had a higher number of postings and reported a higher subjective forum use frequency (but not a higher number of logins) compared to participants who watched the control video. However, the effect on the subjective forum visit frequency was not robust. There were no intervention effects on perceived need support, goal attainment, or secondary outcomes. The results might be explained by low application of need-supportive communication strategies.ConclusionA brief video intervention may be a suitable, low-cost intervention to promote need-supportive communication strategy use, benefitting both engagement and behavior change. Future studies should incorporate additional means to further improve communication strategy uptake and engagement in online communities.

Project description:The COVID-19 pandemic caused unprecedented changes to educational institutions, forcing their closure and a subsequent shift to online education to cater to student learning requirements. However, successful online learning depends on several factors and may also vary between countries. As such, this cross-sectional study sought to investigate how engagement of university students, a major driver of online learning, was influenced by course content, online interaction, student acceptance, and satisfaction with online learning, as well as self-efficacy across nine countries (China, India, Iran, Italy, Malaysia, Portugal, Serbia, Turkey, and the United Arab Emirates) during the COVID-19 pandemic. Using a questionnaire-based approach, data collected from 6,489 university students showed that student engagement was strongly linked to perception of the quality of the course content and online interactions (p < .001). The current study also indicated that online interactions are a major determinant of academic efficacy but only if mediated by engagement within the online learning context. A negative correlation between student engagement and satisfaction with online learning was found, demonstrating the importance of students being engaged behaviorally, emotionally, and cognitively to feel satisfied with learning. Academic efficacy and student satisfaction were explained by course content, online interaction, and online learning acceptance, being mediated by student engagement. Student satisfaction and, to a lesser degree academic efficacy, were also associated with online learning acceptance. Overall, the structural equation model was a good fit for the data collected from all nine countries (CFI = .947, TLI = .943; RMSEA = .068; SRMR = .048), despite differences in the percentage variations explained by each factor (no invariance), likely due to differences in levels of technology use, learning management systems, and the preparedness of teachers to migrate to full online instruction. Despite limitations, the results of this study highlight the most important factors affecting online learning, providing insight into potential approaches for improving student experiences in online learning environments.

Project description:BackgroundStudent engagement can predict successful learning outcomes and academic development. The expansion of simulation-based medical and healthcare education creates challenges for educators, as they must help students engage in a simulation-based learning environment. This research provides a reference for facilitators of simulation teaching and student learning in medical and health-related majors by providing a deep understanding of student engagement in a simulation-based learning environment.MethodsWe conducted semi-structured interviews with ten medical and healthcare students to explore their learning types and characteristics in a simulation-based learning environment. Thematic analysis was used to analyse the data.ResultsThe interviews were thematically analysed to identify three types of student engagement in the simulation-based learning environment: reflective engagement, performance engagement, and interactive engagement. The analysis also identified eight sub-themes: active, persistent, and focused thinking engagement; self-directed-learning thinking engagement with the purpose of problem solving; active "voice" in class; strong emotional experience and disclosure; demonstration of professional leadership; interaction with realistic learning situations; support from teammates; and collegial facilitator-student interaction.ConclusionsThe student interview and thematic analysis methods can be used to study the richness of student engagement in simulation-based learning environments. This study finds that student engagement in a simulation-based learning environment is different from that in a traditional environment, as it places greater emphasis on performance engagement, which combines both thinking and physical engagement, as well as on interactive engagement as generated through interpersonal interactions. Therefore, we suggest expanding the learning space centring around "inquiry", as it can help strengthen reflective communication and dialogue. It also facilitates imagination, stimulates empathy, and builds an interprofessional learning community. In this way, medical and healthcare students can learn through the two-way transmission of information and cultivate and reshape interpersonal relationships to improve engagement in a simulation-based learning environment.

Project description:IntroductionThere has been a move to a "flipped classroom" (FC) in medical education. The FC promotes active learning and utilizes independent preparation prior to in-class sessions. Few studies have evaluated the effectiveness of the FC approach in medical education, specifically via virtual learning. The purpose of this study evaluates student and faculty perceptions of the FC approach and relationships between student engagement and performance.MethodThe first-year medical student psychiatry curriculum was redesigned with an FC approach and subsequently altered by COVID-19 to a virtual learning environment. A mixed-method approach was used to examine both qualitative assessment and quantitative performance data. Students and facilitators were invited to participate in surveys regarding the curriculum changes. Student performance data was collected via quizzes and examinations. Engagement was evaluated by student participation in National Board of Medical Examiners-style multiple-choice questions delivered via Top Hat®. Correlational analyses were used to evaluate associations between engagement and performance. T-tests were used to compare student satisfaction across 2019 and 2020.ResultsPerformance on in-class questions was positively associated with class rank and performance (p < 0.005). More students were either satisfied or strongly satisfied (91.5%) in 2020 compared to 85.7% in 2019 (two-tailed t-test, p = 0.04). Most students (81.3%) preferred in-class questions to lectures. In 2020, 62.6% of student comments were positive regarding the psychiatry curriculum vs 33.3% in 2019. Over 61.5% of facilitators felt positive towards the changes.ConclusionOur results demonstrate a positive relationship between engagement and class performance. Students and facilitators positively perceived the approach, with students preferring in-class questions compared to lectures. Future research should evaluate overall performance on standardized tests, third-year clerkships, and number of students matching into psychiatry.Supplementary informationThe online version contains supplementary material available at 10.1007/s40670-021-01287-x.

Project description:BackgroundThere is growing interest in using mobile apps and online tools to support postsecondary student mental health, but most of these solutions have suboptimal user engagement in real-world settings. Poor engagement can limit long-term effectiveness and usefulness of these tools. Previous literature has proposed several theories that link factors such as low usability and poor user-centered design to app disengagement. However, few studies provide direct evidence showing what factors contribute to suboptimal user engagement in the context of mobile mental health apps for postsecondary students.ObjectiveThis study focuses on understanding postsecondary students' attitudes and behaviors when using Thought Spot, a co-designed mental health app and online platform, to understand factors related to engagement and user experience.MethodsStudents who were given access to Thought Spot for 6 months during a randomized trial of the intervention were invited to participate in one-on-one semistructured interviews. The interviews explored participants' overall experiences and perceptions of the app, along with factors that affected their usage of various features. All interviews were recorded, and template analysis was used to analyze transcripts.ResultsUser satisfaction was mixed among users of Thought Spot. The degree of engagement with the app appeared to be affected by factors that can be grouped into 5 themes: (1) Students valued detailed, inclusive, and relevant content; (2) Technical glitches and a lack of integration with other apps affected the overall user experience and satisfaction with the app; (3) Using the app to support peers or family can increase engagement; (4) Crowdsourced information from peers about mental health resources drove user engagement, but was difficult to obtain; and (5) Users often turned to the app when they had an immediate need for mental health information, rather than using it to track mental health information over time.ConclusionsContent, user experience, user-centeredness, and peer support are important determinants of user engagement with mobile mental health apps among postsecondary students. In this study, participants disengaged when the app did not meet their expectations on these determinants. Future studies on user engagement should further explore the effectiveness of different features and the relative importance of various criteria for high-quality apps. Further focus on these issues may inform the creation of interventions that increase student engagement and align with their mental health needs.Trial registrationClinicalTrials.gov NCT03412461; https://clinicaltrials.gov/ct2/show/NCT03412461.International registered report identifier (irrid)RR2-10.2196/resprot.6446.

Dataset Information

A new ML-based approach to enhance student engagement in online environment

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets