AI-Powered Early Detection and Prevention System for Student Dropout Risk

Objective: Internet addiction among university undergraduates may deeply impact their academic lives. This study investigated the association between academic fatigue, academic engagement, academic performance, gender, and internet addiction and how the variables jointly and relatively predict internet addiction among undergraduates in southwestern universities in Nigeria. Method: The correlational research type of the non-experimental research design was adopted for this study. A multi-stage sampling procedure was used to select 1,157 students. The main variables were the Internet Addiction Test (<em>r </em>= 0.82) and the Academic Fatigue Questionnaire (<em>r </em>= 0.85; both adapted), as well as the Academic Engagement Scale (<em>r</em> = 0.93; researcher developed) and cumulative grade point average. We analyzed the data using frequency, percentages, correlation, and multiple regression. Results: Undergraduate males are significantly more addicted to the internet than females. Academic fatigue, academic engagement, male gender, and internet addiction had a positive significant relationship, while academic performance did not. The multiple association among academic fatigue, engagement, male gender, and internet addiction was 0.6, while the variance accounted for by the predictors on internet addiction was 35.2%. Further, academic fatigue (β = 0.346, <em>t</em> = 14.042, <em>p</em> t = 15.741, <em>p</em>t = 7.609, <em>p</em> Conclusion: Academic fatigue, academic engagement, and gender (specifically male) are leading causes of increased internet addiction among undergraduates. This study contributes to the extant literature by providing evidence that academic performance or success does not necessarily predict internet addiction among university students. Nevertheless, undergraduates should be helped to moderate internet usage.

IntroductionEducation plays a crucial role in improving individual well-being and socioeconomic development. Poor academic performance is often associated with adverse socioeconomic and psychosocial outcomes. Numerous studies have highlighted the effects of sociodemographic, socioeconomic, and nutritional factors on academic performance. However, these studies have been limited to school students only, leaving university students understudied.ObjectiveTo predict academic performance through sociodemographic, socioeconomic, and nutritional factors among female undergraduate medical and health sciences students.Materials and methodsThis cross-sectional study was conducted on 400 female undergraduate medical and health sciences students selected using stratified systematic random sampling. Data were collected through a self-administered questionnaire. Nutritional status was assessed with body mass index (BMI), and academic performance was assessed with mean aggregate marks. Chi-square test was used to assess the associations. Binary logistic regression was used to estimate odds ratios (OR) with 95% confidence intervals (CI). Variables showing significance in binary logistic regression were included in multiple logistic regression model, and adjusted odds ratios (AOR) and their 95% CI were reported.ResultsThe mean age of participants was 21.5±1.5 years. Fifty percent students had normal weight with a mean BMI of 21.8±5.7 kg/m² and 76.8% students demonstrated good academic performance. On bivariate analysis academic performance was significantly higher among Bachelor of Medicine, Bachelor of Surgery (MBBS) students (OR=6.23, 95% CI: 3-13.03), and Bachelor of Science in Public Health (BSPH) students (OR=2.91, 95% CI: 1.21-7.27), as well as the fourth (OR=2.84, 95% CI: 1.54-5.37) and fifth year students (OR=7.15, 95% CI: 2.9-21.7). Performance was also significantly associated with upper-middle-class, mixed diet, three or more meals per day, and daily breakfast. In the multivariate model, field and year of study emerged as key predictors. The model revealed 79.3% accuracy with a positive predictive value of 80.8%.ConclusionAcademic performance is a multifaceted outcome influenced by academic-related factors, particularly academic progression and field of study. Nutritional and socioeconomic factors had a limited independent effect.

Recent years have seen a significant increase in study interest in the areas of predicting student performance, avoiding failure, and identifying the variables affecting student dropout. One important indicator in online and open distance learning courses is the student dropout rate. We purpose the naive bayes classification method to construct the student dropout prediction using naive bayes. This work examines the critical topic of forecasting student dropout rates in higher education using machine learning approaches, with a particular emphasis on the random forest algorithm and the naive bayes algorithm. The study's goal is to properly anticipate dropout rates using data mining methods and machine learning algorithms after conducting a thorough evaluation of existing literature and approaches. The systematic method consists of data collection from a Kaggle dataset, data preparation to solve class imbalance via SMOTE oversampling, and algorithm selection. Random forest and naive Bayes approaches outperform other machine learning algorithms in terms of accuracy, sensitivity, specificity, and precision. The study underscores the importance of considering diverse factors such as demographic data, socioeconomic factors, and academic performance in dropout prediction models. The implications of this research extend beyond academia, with the potential to inform proactive interventions and support systems, ultimately leading to improved student outcomes and institutional effectiveness. According to this paper, the paper outputs that for the binary classification on the data set used in this project has best performed with Naive Bayes and Random Forest Algorithm with SMOTE oversampling. Keywords- SMOTE oversampling, machine learning, Random forest, naive bayes.

Research on the factors contributing to low academic performance of first-generation students studying occupational therapy is limited, and how these factors affect the students' academic performance is insufficiently described. To explore how first-generation students in occupational therapy perceive their academic self-efficacy, academic engagement, and social integration. Explanatory sequential mixed-methods design. Occupational therapy program on the East Coast of the United States. The total sample included 18 first-generation students in occupational therapy through purposeful sampling. Eighteen participants completed the survey, and 5 participants participated in the interview. Measures included a demographic questionnaire, the Self-Efficacy for Learning Form-Abridged, the Survey of Student Engagement, the Social Integration Scale, and semistructured interviews. Participants reported a low level of academic self-efficacy, academic engagement, and social integration. This study fills the gap in research regarding factors contributing to low academic performance of first-generation students in occupational therapy and how the identified barriers of academic self-efficacy, academic engagement, and social integration can be addressed for these students. Plain-Language Summary: This study explored how first-generation occupational therapy students think about their academic performance, engagement, and social integration. Students reported a low level of academic performance, engagement, and social integration. Identifying and understanding the factors that affect the academic performance of first-generation students can improve the support and services provided by occupational therapy programs to first-generation students. Positionality Statement: Positionality is described as the location of the researcher in their research (Milner, 2007). It influences the researcher's assumptions, findings, and interpretations (Banks, 2015). As a first-generation doctoral student, I identify with the unique challenges faced by many first-generation students. As Milner (2007) suggested, it is important to be introspective during research and acknowledge any internal biases to maintain objectivity during the research process. I aimed to be reflexive by taking notes about my thoughts throughout the study to actively reflect on my understanding of how my positionality may affect my data collection and analysis.

Purpose: The study aims to examine the impact of socioeconomic status the academic performance of undergraduates in private universities in Chittagong, Bangladesh. It aims to understand the impact of family financial background on students'' academic goals, results, and activities, as well as the role of family, social, and institutional issues in students'' choices and decisions. The study also aims to test students'' understanding and identification of social challenges.
 Methodology: A mixed-method study in Chittagong City, Bangladesh, examined students'' attitudes on the socioeconomic background’s impact on academic aspirations and performance. The study with mixed method strategy collected data from 206 undergrad students at private universities, focusing on academic performance, engagement, and personal lives.
 Findings: The study found that socioeconomic factors impact students'' academic performance at private universities, with middle-class students from Bangladesh enrolling to complete their education. However, tuition costs and family influences can lead to part-time employment, starting businesses, or discontinuing studies. Institutions and students'' personal desires can help improve academic performance. While some students use the financial crisis of family as inspiration, they lack the necessary tools to manage difficulties and participate in university activities Family socioeconomic background significantly impacts students'' academic performance and extra-curricular engagement, especially in private universities. Poor students face financial constraints and struggle to navigate academic environments. Institutional environments, personal life, and part-time jobs can hinder motivation.
 Recommendations: The study suggests addressing psychological issues among socioeconomically weak private university students, involving parents, personal lives and studying public-private university challenges. It also recommends interviewing scholarship recipients and training higher education teachers to provide personal guidance and consultancy for students facing mental stress. Soft Hands from families, teachers, peers, and an appropriate institutional environment can improve performance.

Objectives This study aimed to investigate the impact of Chinese high school students’ perceived interparental conflict on their academic engagement, with a focus on the mediating roles of positive and negative academic emotions and the moderating role of emotional intelligence. Background In China, parents often suppress interparental conflicts until after their children’s college entrance exams to avoid disrupting the latter’s academic performance. However, unresolved interparental conflict may impair adolescents’ psychological wellbeing and academic engagement. Grounded in the Cognitive-Contextual Theory and the Emotional Security Theory, this research explored how perceived interparental conflict influences academic engagement through academic emotions, and how emotional intelligence buffers these adverse effects. Methods The study used data from 257 high school students in City G, Province S of China. Hierarchical regression analysis was employed to test the proposed mediating and moderating hypotheses. Results Perceived interparental conflict had a significant negative impact on academic engagement; both positive and negative academic emotions partially mediated the relationship between perceived interparental conflict and academic engagement; emotional intelligence weakened the negative impact of perceived interparental conflict on positive academic emotions, and mitigated the positive impact of the former on negative academic emotions. Conclusion This study confirmed the negative impact of perceived interparental conflict on high school students’ academic engagement, revealed the mechanism by which interparental conflict in the family environment influences academic engagement, and proposed targeted measures and practical suggestions to prioritize students’ academic emotional regulation and enhance their emotional intelligence in both school and family contexts.

This study explores the correlation of parental involvement on the academic engagement and performance of Grade 11 students in Seventh-day Adventist (SDA) academies within the Western Visayas region. Using a descriptive-correlational survey approach, the research examines the relationship between various aspects of parental involvement such as support with homework, school event participation, and parent-teacher meeting attendance and students’ academic outcomes. It considers how factors like parental gender, profession, student demographics, and educational background influence these dynamics. Data collection was conducted through a self-developed questionnaire and verified academic records, with statistical analysis using Pearson correlation, t-tests, ANOVA, and moderation analysis. Findings reveal a “moderately high” level of parental involvement, particularly among non-SDA parents, fathers, and professional parents, with financial support (e.g., for school supplies) rated highest. Academic performance showed an outstanding mean GPA of 90.38, with top scores observed among students from SDA Junior High Schools and female students. Results indicate that female students benefit more from parental involvement, and socioeconomic status, educational background, and school environment significantly shape both engagement levels and academic success. The study highlights the importance of gender-sensitive and inclusive strategies to enhance parental involvement, particularly for male students and students from non-professional backgrounds. It proposes collaborative training programs to foster parent-school partnerships, aligning with SDA educational principles to support holistic student development. Recommendations encourage deeper investigation into the impact of socioeconomic and community factors on academic outcomes in faith-based schools.

Nursing students frequently encounter the challenge of balancing their studies with the demanding requirements of hands-on practice and this can greatly affect their mental wellbeing. This study aimed to investigate the impact of sleep and psychological well-being on the academic and clinical performance of nursing students in Saudi Arabia. This study used a cross-sectional approach with 218 student nurses selected through convenience sampling from King Khalid University, Abha, Saudi Arabia. The sleep quality, psychological wellbeing, academic performance and clinical performance questionnaires were adopted to measure the variables. The Google Forms survey was used to gather the data, which were collected in August through October 2023. t-test and chi-square were used to analyze the data. The sleep quality was higher with good/very good performers (p < 0.001). There was a significant difference with academic performance on positive relations (p < 0.007) and purpose in life (p < 0.004). Additionally, there was a significant difference in autonomy (p < 0.01), environmental mastery (p < 0.026), positive relations (p < 0.001), and purpose in life (p < 0.001) with clinical performance. Among students with good academic performance, those who were older than 25 years of age (p < 0.043) and level 3 students (p < 0.001) were found to have a significant correlation. Furthermore, those who were 25 years of age (p < 0.012) and level 3 students (p < 0.001) were also found to have a significant correlation with clinical performance. The sleep quality, positive relations, purpose in life, autonomy, and environmental mastery are all important factors for academic and clinical success. Moreover, older students and level 3 students may be more likely to have the skills and knowledge necessary to succeed in these areas. Further research exploring factors influencing academic and clinical success must be conducted.

Predicting student dropout risk and mental fatigue has become a critical challenge for educational institutions aiming to improve retention and overall academic success. Traditional models primarily based on academic performance often fail to capture the complex psychological factors that significantly influence student outcomes. This chapter presents an integrated approach to dropout prediction by combining academic data with psychological insights through advanced predictive analytics. The proposed model incorporates academic performance metrics, including grades and attendance, alongside psychological factors such as stress, anxiety, and mental fatigue. By integrating machine learning algorithms with multidimensional data, a more accurate and holistic prediction framework is developed, enabling early identification of at-risk students. This integrated approach not only improves prediction accuracy but also facilitates timely interventions, thereby reducing dropout rates and enhancing student well-being. The chapter explores various machine learning techniques, evaluates their effectiveness, and discusses the challenges and ethical considerations in implementing such models. The findings underscore the importance of addressing both academic engagement and mental health in predictive analytics for higher education. Ultimately, this approach offers a comprehensive framework for fostering student success and retention through data-driven interventions.

The role of conscious self-regulation in determining students' psychological well-being and academic performance is considered in the context of the fundamental problem of the regularities of young adolescents' development. To reveal the role of meta-resources of conscious self-regulation in determining young adolescents' psychological well-being and academic performance. Sample: 500 students in 4th- to 6th grade (10-12) in general schools, 149 of whom participated in a three-year longitudinal study. The Self-Regulation Profile of Learning Activity and the Well-Being Manifestation scales were used. Conscious self-regulation and academic performance increase significantly in fifth grade and decrease in sixth grade. On the contrary, psychological well-being is characterized by a systemic positive dynamic. A typological analysis identified the levels of psychological well-being of students growing, stable, and declining during the transition period. It was found that the general level of conscious self-regulation made a significant positive contribution and is a universal resource for students' psychological well-being and academic performance. Special regulatory resources for academic performance are described, depending on the trajectory of changes in psychological well-being. Increased well-being is determined by the regulatory competencies of Planning and Evaluation of results and its stability by Planning, Modelling, Flexibility, and Responsibility. The general level of self-regulation, regulatory competencies, Planning, Programming and Responsibility mediate in the relationship between student psychological well-being and academic performance. A longitudinal study found that self-regulation has a long-term positive effect on student psychological well-being and academic performance. Conscious self-regulation is a meta-resource that makes a significant contribution to both the psychological well-being and academic performance. Mediator and prognostic effects of self-regulation on these properties create a psychological basis for practical work.

Students' mental health have a greatest impact on wellbeing and academic performance, also is often affected adaptation to the university life. This study examines the proportion of students with a positive and negative affect balance, and the relationship between affective wellbeing and academic self-efficacy and performance. It also analyzes how psychological wellbeing and academic self-efficacy predict affective wellbeing and academic performance. In a sample of 200 undergraduate students (M=19.07years), it was found that positive affect decreased and negative affect increased during the second academic year. The majority had a positive affect balance (AB). Psychological wellbeing predicts positive emotions and its achievement dimension predicts academic performance. 53% of participating students maintained a positive AB, 14% maintained a negative AB and 21% went from a negative to a positive AB one. The change from a positive to a negative AB (10%) is associated with an increase in psychological wellbeing, suggesting a process of post-stress growth in relation to the challenges of university life.

This study explores how academic pressure affects middle school students' mathematical academic achievement, focusing on the mediating roles of academic self-concept and academic engagement. A survey of 454 students from two schools in Yunnan province collected data on academic pressure, self-concept, engagement, and achievement. Mediation analysis was performed using Model 6 in the SPSS PROCESS macro. Results showed a significant negative correlation between academic pressure and mathematical academic achievement. Academic self-concept partially mediated this relationship, while a chain mediation effect involving both academic self-concept and engagement was also found. These findings suggest that reducing academic pressure, while strengthening students' academic self-concept and engagement, can improve mathematical academic achievement. The study provides empirical support for educational strategies aimed at enhancing students' academic performance in mathematics.

In recent years, there has been a growing interest in scholars and practitioners to explore the factors that lead to an improvement in Students’ psychological wellbeing. Due to the tough challenges faced by students during their academic life, severe issues of stress, anxiety, and other mental health issues emerge, which affect their academic performance and have a long-lasting impact on their future careers. The pandemic accelerates the stress levels, anxiety, and mental issues of students. The main purpose of this study was to explore how music education impacts on Students’ psychological wellbeing and academic performance. This study also investigates the mediating effect of self-esteem and self-efficacy. To the best of our knowledge, there has been little to no study exploring the relationship of music education on the psychological wellbeing and performance of students, especially from the perspective of Asian countries. This study was conducted in undergraduate and graduate institutions of China. This study was quantitative in nature and data were collected from 319 respondents. The structural equation modeling (SEM) technique was employed for data analysis. Results reveal that music education has a significant positive impact on psychological wellbeing, which improves Students’ academic performance. Moreover, psychological wellbeing also has a significant and positive impact on Students’ academic performance. Self-efficacy and self-esteem significantly mediate the relationship between music education and psychological wellbeing. The findings of this study open new avenues for future research in music education and psychological wellbeing. This study suggests that the policymakers and practitioners should make such policies that encourage educational institutes to adopt music education to improve the psychological wellbeing of students.

BackgroundSocial anxiety has been shown to affect college students’ academic performance. However, the role of social media addiction and academic engagement in this association is unclear.MethodsA total 2661 college students completed a self-report questionnaire including Liebowitz Social Anxiety Scale, the Bergen Social Media Addiction Scale, the Utrecht Student Work Engagement Scale for Students, and the grade point average. Hayes’ PROCESS macro for SPSS was employed to test the serial mediation effect.ResultsResults indicated that social anxiety was negatively related to academic performance, only academic engagement played a single mediating role in the relationship between social anxiety and academic performance, meanwhile social media addiction and academic engagement acted as serial mediators between social anxiety on academic performance.ConclusionsSocial media addiction and academic engagement can explain the potential mechanisms of the association between social anxiety and academic performance, which have implications for devising intervention strategies to enhance the mental health and academic outcomes of college students.

Background This study aimed to investigate the relationship between personality traits, academic burnout, and academic engagement among dental students with emotion regulation as a mediating role. It sought to identify personality predictors within the HEXACO model and compare how these traits directly and indirectly affect students’ academic engagement and burnout. Methods The participants were 228 dental students from School of Dentistry. Data were collected using the HEXACO personality inventory, the Emotion Regulation Questionnaire (ERQ), the Maslach Burnout Inventory-Student Survey (MBI-SS), and the Korean Academic Engagement Inventory (KAEI). The study employed structural equation modeling to explore the direct and mediated relationships between personality traits, emotion regulation, academic burnout, and academic engagement. Results The findings indicated that specific personality traits, notably Extraversion, directly and indirectly influence both academic burnout and engagement, with emotion regulation serving as a mediating factor. Extraversion affected engagement directly and indirectly through cognitive reappraisal. Moreover, the burnout model revealed that, besides Extraversion, Agreeableness and Openness to experience also had a direct impact on burnout, suggesting a broader range of personality traits influencing burnout compared to engagement. Conclusions The study underscores the significant role of personality traits, particularly Extraversion, in determining academic burnout and engagement, with emotion regulation often playing a mediating role. The findings of this study indicate that personality traits can be approached in a distinct manner when developing strategies to mitigate burnout and increase engagement among dental students. These insights could inform targeted interventions aimed at improving academic engagement and performance.