Search results

This study aimed to use enrollment information including demographic, family background and financial status, which can be gathered before the first semester starts, to construct early prediction models (EPMs) and extract crucial factors associated with first-year student dropout probability.

The real-world samples comprised the enrolled records of 2,412 first-year students of a private university (UNI) in Taiwan. This work utilized decision trees (DT), multilayer perceptron (MLP) and logistic regression (LR) algorithms for constructing EPMs; under-sampling, random oversampling and synthetic minority over sampling technique (SMOTE) methods for solving data imbalance problems; accuracy, precision, recall, F1-score, receiver operator characteristic (ROC) curve and area under ROC curve (AUC) for evaluating constructed EPMs.

DT outperformed MLP and LR with accuracy (97.59%), precision (98%), recall (97%), F1_score (97%), and ROC-AUC (98%). The top-ranking factors comprised “student loan,” “dad occupations,” “mom educational level,” “department,” “mom occupations,” “admission type,” “school fee waiver” and “main sources of living.”

This work only used enrollment information to identify dropout students and crucial factors associated with dropout probability as soon as students enter universities. The extracted rules could be utilized to enhance student retention.

Although first-year student dropouts have gained non-stop attention from researchers in educational practices and theories worldwide, diverse previous studies utilized while-and/or post-semester factors, and/or questionnaires for predicting. These methods failed to offer universities early warning systems (EWS) and/or assist them in providing in-time assistance to dropouts, who face economic difficulties. This work provided universities with an EWS and extracted rules for early dropout prevention and intervention.

Adolescent pregnancy stands as a societal challenge, compelling young individuals to prematurely discontinue their education. Conversely, an expansion of high school education can potentially diminish rates of adolescent pregnancy, given that educational attainment stands as the foremost risk factor influencing sexual initiation, the use of contraceptive methods during initial sexual encounters and fertility. The aim of this paper is to analyze the impact of the implementation of the public educational policy introducing full-time schools (FTS) for high schools in the state of Ceará, Brazil, on early pregnancy rates.

Using the difference-in-differences method with multiple time periods, we measured the average effect of this staggered treatment on the treated municipalities.

The main result indicates a reduction of 0.849 percentage points in the teenage pregnancy rate. Concerning dynamic effects, the establishment of FTS in treated municipalities results in a 1.183–1.953 percentage point decrease in teenage pregnancy rates, depending on the timing of exposure. We explored heterogeneous effects within socioeconomically vulnerable municipalities, yet discerned no impact on this group. Rigorous tests confirm the robustness of the results.

This paper aims to contribute to: (1) the consolidation of research on the subject, given the absence of such research in Brazil to the best of our knowledge; (2) the advancement and analysis of evidence-based public policy and (3) the utilization of novel longitudinal data and methodology to evaluate adolescent pregnancy rates.

Automation of detecting cracked surfaces on buildings or in any industrially manufactured products is emerging nowadays. Detection of the cracked surface is a challenging task for inspectors. Image-based automatic inspection of cracks can be very effective when compared to human eye inspection. With the advancement in deep learning techniques, by utilizing these methods the authors can create automation of work in a particular sector of various industries.

In this study, an upgraded convolutional neural network-based crack detection method has been proposed. The dataset consists of 3,886 images which include cracked and non-cracked images. Further, these data have been split into training and validation data. To inspect the cracks more accurately, data augmentation was performed on the dataset, and regularization techniques have been utilized to reduce the overfitting problems. In this work, VGG19, Xception and Inception V3, along with Resnet50 V2 CNN architectures to train the data.

A comparison between the trained models has been performed and from the obtained results, Xception performs better than other algorithms with 99.54% test accuracy. The results show detecting cracked regions and firm non-cracked regions is very efficient by the Xception algorithm.

The proposed method can be way better back to an automatic inspection of cracks in buildings with different design patterns such as decorated historical monuments.

The transition to college presents significant challenges for many students as they navigate new academic and social experiences. In the USA, 30% of first-year students drop out before their second year. Research indicates that mentoring programs help students achieve social integration and likely have a positive effect on their transition to college. This research study was conducted with education students to better understand the potential impacts of peer mentorship.

Student mentors and mentees were matched by attributes such as their concentration within the education major, gender, sports they played and whether they were first-generation matriculants. Data collection utilized two surveys one before the peer mentoring process and one after the process.

The findings suggest that peer mentoring improved first-generation students' sense of belonging to both their major and the college. Peer mentors also experienced increased belongingness. The transfer rate among participants of 2% was a significant drop from previous years.

The success of the peer mentoring experience was possibly due to the intentional matching process based on certain attributes. Additionally, taking a leadership role increased a sense of belonging in the peer mentors.

The study aims to determine the outcomes of mentorship in an online game system, as well as the characteristics of good mentors.

A combination of anonymized survey measures and in-game behavioral measures were used to power longitudinal analysis over an 11-month period in which protégés and non-mentored new players could be compared for their performance, social connections and retention.

Successful people were more likely to mentor others, and mentors increased protégés' skill. Protégés had significantly better retention, were more active and much more successful as players than non-protégés. Contrary to expectations, younger, less wealthy and educated people were more likely to be mentors and mentors did not transfer their longevity. Many of the qualities of the mentor remain largely irrelevant—what mattered most was the time spent together.

This is a study of an online game, which has unknown generalizability to other games and to offline settings.

The results show that getting mentors to spend dedicated time with protégés matters more than their characteristics.

Good mentorship does not require age or resources to provide real benefits.

This is the first study of mentorship to use survey and objective outcome measures together, over time, online.

E-learning has become a polarizing issue. Some say that it enhances accessibility to education and some say that it hinders it. While the literature on the subject underscores the effectiveness of the pedagogical frameworks, strategies and distance learning technologies, the firsthand accounts of students, parents and practitioners challenge the validity of experts’ assessments. There is a gap between theory and practice and between the perceptions of providers and consumers of online learning. Following a period of lockdowns and a transition to online learning during the recent pandemic, the prevailing sentiment toward a distance mode of instruction became one of strong skepticism and negative bias. The aim of the study was to examine why e-learning has struggled to meet stakeholder expectations. Specifically, the study posed two research questions: 1. What are the reasons for dissatisfaction with online learning? 2. What are the implications for future research and practice?

The study used a mixed methods approach to examine the reasons behind negative perceptions of online learning by comparing the firsthand accounts posted on social media with the literature. To this end, n = 62,874 social media comments of secondary and postsecondary students, as well as parents, teachings staff and working professionals, covering the span of over 14 years (2008–2022), were collected and analyzed.

The study identified 28 themes that explain the stakeholder’s discontent with the online learning process and highlighted the importance of user-centric design. The analysis revealed that the perceived ineffectiveness of distance education stems from the failure to identify and address stakeholders’ needs and, more particularly, from the incongruence of instructional strategies, blindness to the cost of decisions related to instructional design, technology selection and insufficient levels of support. The findings also highlight the importance of user-centric design.

To address dissatisfaction with e-learning, it is imperative to remove barriers to learning and ensure alignment between technology and learners’ needs. In other words, the learning experience should be personalized to account for individual differences. Despite its cost-effectiveness, the one-size-fits-all approach hinders the learning process and experience and is likely to be met with resistance.

Drawing from the extensive literature, the study offers an explanation for stakeholders’ discontent with e-learning. Unlike survey research that is prone to social desirability bias, the sample provides a rare opportunity to observe and measure the visceral reactions that provide a more authentic sense of stakeholders’ perceptions toward online learning. The authors offer recommendations and identify areas for future research.

This study analyzed the impact on the persistence of Chilean university students who had received a government-guaranteed loan (CAE).

Using academic and administrative data from 2016 to 2019, provided by 11 Chilean universities, a discrete-time survival model was constructed. The model was based on data of 5,276 students in the 2016 cohort and included sociodemographic variables, academic background prior to entering university and academic performance once in university. As a robustness check of our results to observable confounding, the analysis was repeated using a control group constructed using propensity score matching (PSM).

The results reveal that students who receive a bank loan (CAE) were more likely to remain in undergraduate studies for at least the first two years of university, as opposed to their peers who did not receive financial aid. In addition, they show the importance of academic performance in retention.

The article advances in the identification of the impact of bank loans on permanence. Although previous research has evaluated the impact of the CAE, it has been conducted on small samples of students. These studies also lacked student records associated with their academic performance at the university. The present research overcomes both weaknesses, allowing us to estimate the impact of the CAE on a larger population of students that is representative of the system.

The purpose of this study is to identify the main perspectives and trends in educational data mining (EDM) in the e-learning environment from a managerial perspective.

This paper proposes a systematic literature review to identify the main perspectives and trends in EDM in the e-learning environment from a managerial perspective. The study domain of this review is restricted by the educational concepts of e-learning and management. The search for bibliographic material considered articles published in journals and papers published in conferences from 1994 to 2023, totaling 30 years of research in EDM.

From this review, it was observed that managers have been concerned about the effectiveness of the platform used by students as it contains the entire learning process and all the interactions performed, which enable the generation of information. From the data collected on these platforms, there are improvements and inferences that can be made about the actions of educators and human tutors (or automatic tutoring systems), curricular optimization or changes related to course content, proposal of evaluation criteria and also increase the understanding of different learning styles.

This review was conducted from the perspective of the manager, who is responsible for the direction of an institution of higher education, to assist the administration in creating strategies for the use of data mining to improve the learning process. To the best of the authors’ knowledge, this review is original because other contributions do not focus on the manager.

This study aims to analyze to what extent distance education is feasible and efficient with the limited technological infrastructure in Egypt. The study answers this question from the perspective of households' preparedness level regarding possessing information and communication technologies (ICTs). In addition, it assesses whether the pattern of students' ICT ownership is influenced by disability- and socioeconomic-based inequality in education and whether the pattern of ICT ownership exacerbates such biases.

A three-stage probit model with double sample selection (PMDSS) was applied to estimate the factors likely to influence ICT possession, considering the selection process for school enrollment and education continuation. The authors utilized nationally representative data from the Egypt Labor Market Panel Survey 2018.

About 40% of students aged 12–25 did not have ICTs. Most socioeconomically poor households, particularly those living in Upper Egypt, were the least likely to obtain ICTs and rely on distance education. In addition, female students, particularly those with disabilities, had the lowest chance of benefitting from distance learning.

The persistent structural deprivation of school enrollment and educational progression has led to the positive selection of well-off children in education, which is extended to ICT possession and internet use. Without addressing these structural biases, the study suggests that distance education will likely exacerbate educational inequalities.

The study analyzed the extent to which Egyptian families were prepared in 2018 regarding ICT possessions for distance education for their children, particularly those with disabilities. Furthermore, it investigated whether access to distance learning was influenced by disability- and socioeconomic-based inequalities in education.