Dropout In Higher Education Research Articles

Supporting Decision-Making Process on Higher Education Dropout by Analyzing Academic, Socioeconomic, and Equity Factors through Machine Learning and Survival Analysis Methods in the Latin American Context

The prediction of university dropout is a complex problem, given the number and diversity of variables involved. Therefore, different strategies are applied to understand this educational phenomenon, although the most outstanding derive from the joint application of statistical approaches and computational techniques based on machine learning. Student Dropout Prediction (SDP) is a challenging problem that can be addressed following various strategies. On the one hand, machine learning approaches formulate it as a classification task whose objective is to compute the probability of belonging to a class based on a specific feature vector that will help us to predict who will drop out. Alternatively, survival analysis techniques are applied in a time-varying context to predict when abandonment will occur. This work considered analytical mechanisms for supporting the decision-making process on higher education dropout. We evaluated different computational methods from both approaches for predicting who and when the dropout occurs and sought those with the most-consistent results. Moreover, our research employed a longitudinal dataset including demographic, socioeconomic, and academic information from six academic departments of a Latin American university over thirteen years. Finally, this study carried out an in-depth analysis, discusses how such variables influence estimating the level of risk of dropping out, and questions whether it occurs at the same magnitude or not according to the academic department, gender, socioeconomic group, and other variables.

The relevance of basic psychological needs and subject interest as explanatory variables for student dropout in higher education — a German case study using the example of a cooperative education program

Student dropout in higher education is a challenge for higher education systems. In recent years, there has been an increasing focus on analyzing motivational aspects in order to counteract dropout. However, the detailed impact mechanisms and processes of motivation on dropout have not been sufficiently researched. For example, there is very little research analyzing the preconditions of motivation and their influence on motivation as well as their eventual influence on dropout. From the background of self-determination theory and the person-object theory of interest, this study analyzes the effects of satisfying the three basic psychological needs on dropout via subject interest. We use data from a cross-sectional design with N = 2662 cooperative students in their first academic year. Our analysis identifies a direct effect of relatedness and subject interest on dropout. Furthermore, indirect effects of satisfying basic psychological needs, specifically, autonomy and relatedness, on dropout via subject interest are noted. We evaluate our results in the context of the current state of research and discuss implications.

Latest Algorithms in Machine and Deep Learning Methods to Predict Retention Rates and Dropout in Higher Education: A Literature Review

External factors, such as global impact, or internal factors, such as educational services or the quality of learning, can affect the Retention rate or Number of Dropouts (DO) of students in higher education. Higher education institutions must have a strategy to manage retention rates properly. They can take an initial approach by knowing the estimated retention rate or the number of DOs so they can anticipate it by determining the right strategy. Several researchers have researched retention prediction or DO using specific methods and algorithms. This literature review aims to provide an overview and analysis of the methods and algorithms used to predict retention rates or the Number of DOs of students in higher education and to know the latest trends in developing the algorithms used in predicting retention rates or DO. The method used in this research is the traditional literature review. We have identified Twenty-one articles according to the theme. From the article, there are 21 machine learning algorithms, 13 deep learning algorithms used, seven time-series algorithms, four feature selection algorithms, and three combinations of algorithms used. The review results show that deep learning algorithms provide higher accuracy values than machine learning algorithms, and the recent trend of using algorithms to predict retention levels or DO is towards using time series algorithms in deep learning methods.

Theoretical models of dropout in higher education and notes on the national context

Resumo O fenômeno da evasão se configura como uma preocupação nos cursos de graduação das universidades brasileiras, acarretando alguns problemas, dentre os quais destacamos os gastos de recursos públicos, tendo como consequência um sério comprometimento na qualificação dos nossos jovens, nas mais variadas áreas do conhecimento. As pesquisas teóricas sobre a evasão no ensino superior, principalmente as que dizem respeito à evasão no Brasil, são muito recentes, mas, apesar de recentes, são muito importantes para que possamos nos situar diante desse fenômeno e melhor compreendê-lo, visto que traz prejuízos, tanto para as instituições, quanto para o indivíduo que evade. Neste sentido, este artigo apresenta importantes modelos teóricos sobre evasão, tais como os que foram elaborados por Tinto, Bean, Coulon, Astin, e Cabrera, autores comumente utilizados como referência nos estudos sobre evasão universitária. Buscamos, portanto, fomentar e aprofundar essa discussão, contextualizando o fenômeno da evasão a partir da nossa realidade, com estudos feitos por pesquisadores brasileiros. Para que soluções possam ser pensadas, o conhecimento da realidade se mostra fundamental.

Factors Influencing the Chance of Dropout or Being at Risk of Dropout in Higher Education

The purpose of this paper is to establish what sociodemographic and institutional factors cause students to drop out, become uncertain about their intentions to obtain a degree, or confidently advance towards the fulfilment of their ambitions. Our analysis is based on the combined databases of large-sample questionnaire surveys carried out among former students who dropped out from higher education institutions in an eastern region of Hungary as well as those carried out among current students. In addition to bivariate methods, we conduct multinomial logistic regression analysis to explore how students’ gender, social background, the funding of their training, willingness to do paid work alongside their studies, and relationships with academic staff and fellow students affect the chance of dropout, the risk of dropout, and persistence. In contrast to previous studies, which have mostly identified those at risk of dropping out of higher education and have primarily focused on the deficiencies of institutional integration, our novel results show that the actual dropout rate is at least as influenced by students’ unfavourable social background as it is by institutional factors.

Educational data mining to support identification and prevention of academic retention and dropout: a case study in introductory programming

Several works in the literature emphasized data mining as efficient tools to identify factors related to retention and dropout in higher education. However, most of these works do not discuss if (or how) such factors may effectively contribute to decrease such rates. This article presents a data mining approach conceived to identify students at retention risk in a course of Intro to Computer Programming as well as guide preventive interventions to help such students to overcome this situation. Our results indicated an averaged predictive performance superior to 80% in both accuracy and F1 when identifying factors related to the retention. Moreover, during the two years of the project execution, the annual success rates in the course were the highest in comparison to the last five years.

Prediction of early dropout in higher education using the SCPQ

There is enormous concern at the international level vis-à-vis the retention of students in universities. Given that dropout rates and their social repercussions are causing great concern worldwide, researchers have been examining this issue to establish models to predict early dropout and to guide actions to support students who are at risk of dropping out. In this paper, we present a study we carried out at the University of Granada in which the risk of first-year students dropping out was analyzed by administering the College Persistence Questionnaire (CPQ v2) to 701 students who began their studies in the 2018/19 academic year. The data pertained to persisting at the institution one year later. The results indicated significant differences within the dimensions of academic and social integration, degree commitment, collegiate stress, academic advising and motivation, scholastic conscientiousness, institutional commitment, financial strain, and academic efficacy. These results align with a wide range of national and international studies.

Políticas de permanência estudantil na educação superior: reflexões de uma revisão da literatura para o contexto brasileiro

Abstract Dropout in higher education is a matter of global interest, and several policies were created to encourage students to stay in universities. This article aimed to identify patterns of evaluation of student retention policies in higher education through a systematic literature review, selecting 39 documents from Scopus, Sage Journals, Web of Science, Google academic, and CAPES Periodicals. Regarding evaluation forms, the results indicated the predominance of analyses on the effects of policies on dropout. However, some studies evaluated students’ performance and time to graduation. Research works were mostly applied in public university environments, which indicates a scarcity of scientific production about private educational institutions. As for the formats of permanence policies, the literature pointed out four types of aid with different natures: financial, assistance, based on academic merit, and by criteria of students’ need/vulnerability. Based on the research, it was proposed that the evaluation of permanence policies should be threefold, considering permanence, performance, and time until graduation. Among the gaps in the literature, comparative studies between the types of policies were highlighted.

Toward an Institutional Analytics Agenda for Addressing Student Dropout in Higher Education

Although the number of students in higher education institutions (HEIs) has increased over the past two decades, it is far from assured that all students will gain an academic degree. To that end, institutional analytics (IA) can offer insights to support strategic planning with the aim of reducing dropout and therefore of minimizing its negative impact (e.g., on students, academic stakeholders, and institutions). However, it is not clear how institutional stakeholders can integrate IA in their practice to overcome academic-related issues and to offer support to students who struggle to achieve their academic goals. To address this gap, we conducted focus groups with 13 institutional stakeholders of an Estonian university. By analyzing the focus group data, we identified three main categories of factors influencing dropout from the perspective of institutional stakeholders: (1) institutional experience, (2) educational goals, and (3) personal aspects. We discuss our findings from an institutional perspective with the aim of reflecting on institutional processes, organizational structures, and facilitatory roles in the context of dropout in higher education (HE). We argue that IA can provide insights into students’ institutional experience, educational goals, and personal aspects to further support decision-making on the institutional level. We envision our findings contributing to a participatory agenda for the design, implementation, and integration of IA solutions focusing on addressing dropout in HE.

Student Dataset from Tecnologico de Monterrey in Mexico to Predict Dropout in Higher Education

High dropout rates and delayed completion in higher education are associated with considerable personal and social costs. In Latin America, 50% of students drop out, and only 50% of the remaining ones graduate on time. Therefore, there is an urgent need to identify students at risk and understand the main factors of dropping out. Together with the emergence of efficient computational methods, the rich data accumulated in educational administrative systems have opened novel approaches to promote student persistence. In order to support research related to preventing student dropout, a dataset has been gathered and curated from Tecnologico de Monterrey students, consisting of 50 variables and 143,326 records. The dataset contains non-identifiable information of 121,584 High School and Undergraduate students belonging to the seven admission cohorts from August–December 2014 to 2020, covering two educational models. The variables included in this dataset consider factors mentioned in the literature, such as sociodemographic and academic information related to the student, as well as institution-specific variables, such as student life. This dataset provides researchers with the opportunity to test different types of models for dropout prediction, so as to inform timely interventions to support at-risk students.

Social Inequality in Dropout from Higher Education in Germany. Towards Combining the Student Integration Model and Rational Choice Theory

Students from a lower socioeconomic background have a higher risk of dropping out of higher education. The underlying mechanisms of this association between socioeconomic background and higher education dropout are not well understood. Previous research in higher education has followed Tinto’s model of academic and social integration to explain dropout but has largely neglected social inequality therein. In contrast, social stratification research draws on rational choice theory to explain social inequality in educational attainment but has rarely been applied to explain dropout from higher education. In our paper, we combine these two strands of research. Utilizing data from the National Educational Panel Study (NEPS), we draw on a largescale, representative sample of students in Germany to quantify the relative contribution of each theoretical approach for explaining social inequality in dropout from higher education. Binary logistic regression models reveal that both students’ integration and costs-benefit considerations are associated with their dropout risk net of each other. While academic and social integration appears to better predict dropout, rational choice theory accounts for a larger proportion of social inequality therein. We conclude that combining Tinto’s model and rational choice theory provides a more comprehensive perspective of dropouts from higher education and social inequality therein.

Study environment factors associated with retention in higher education

ABSTRACT There is a substantial body of research concerned with student retention in higher education. However, in regard to factors related to study environment, existing research is described as incomplete. Based on Tinto’s institutional departure model and a literature review of recent international articles on dropout in higher education, this article suggests a revised model for understanding dropout processes. The model envisages study environment as a concept consisting of overlapping domains of a social system, an academic system, and teaching. The article distinguishes between factors related to each of these three systems and discusses how they can be used to understand and prevent dropouts.

Refining the Spady–Tinto approach: the roles of individual characteristics and institutional support in students’ higher education dropout intentions in Luxembourg

ABSTRACT Based on the classic models developed by Spady and Tinto on the link between social and academic integration and dropout, we propose a refined model to explain dropout intentions – relating to dropout from higher education (HE) and dropout from a specific study programme – that more strongly emphasises individual background characteristics (e.g. gender, social origin, and immigration background). Additionally, we consider students’ satisfaction with the institutional support structures. Using Eurostudent survey data, this conceptual model was tested using structural equation modelling in the international and diverse HE context of Luxembourg. While the fitted model confirmed most of the expected associations of the conventional Spady–Tinto approach, initial study commitment was not linked to social integration (contacts with fellow students). We were able to identify satisfaction with institutional support as a key factor in explaining dropout intention, thus contributing to existing knowledge. In addition, we found that the link between socioeconomic factors and dropout intention from a study programme is not entirely mediated by the Spady–Tinto factors of commitment and integration.

Causas asociadas a la deserción escolar en educación superior. Una revisión sistemática del 2010 al 2020

The objective of this research is to make a systematic review of research carried out from 2010 to 2020 where mention is made of the causes of dropout in Higher Education. Collecting the information through a documentary review by the different authors consulted for this research. In order to identify the causes of school dropout, at the University. This review was carried out in a period from 2010 to 2020 with the keywords of school dropout, lag, failure and academic performance. The databases consulted were SciELO, national repository cti.mx, Eric, Redalyc, dialnet, academic google, where keywords were used in thesauri, related to each of the concepts to be investigated. Searches were conducted in English and Spanish, in the areas of psychology, education, and social sciences. The methodological approach is qualitative and descriptive. Resulting in 15 articles that show the relationship of each of the aforementioned concepts with attrition, out of a total of 35 articles selected from the consulted databases that showed information regarding said problems. Some of the causes of the desertion of young university students have been based on the survival model, making it known that the desertion is related to the degree in which they are studying. Pedagogical variables were also identified, in several of these investigations they concluded that the first year of university is the most complex for these young people, hence the importance of tutorials, there are also other important causes such as social origin, gender, ethnicity, nationality or the family situation

Comparison of Predictive Models with Balanced Classes Using the SMOTE Method for the Forecast of Student Dropout in Higher Education

Based on the premise that university student dropout is a social problem in the university ecosystem of any country, technological leverage is a way that allows us to build technological proposals to solve a poorly met need in university education systems. Under this scenario, the study presents and analyzes eight predictive models to forecast university dropout, based on data mining methods and techniques, using WEKA for its implementation, with a dataset of 4365 academic records of students from the National University of Moquegua (UNAM), Peru. The objective is to determine which model presents the best performance indicators to forecast and prevent student dropout. The study aims to propose and compare the accuracy of eight predictive models with balanced classes, using the SMOTE method for the generation of synthetic data. The results allow us to confirm that the predictive model based on Random Forest is the one that presents the highest accuracy and robustness. This study is of great interest to the educational community as it allows for predicting the possible dropout of a student from a university career and being able to take corrective actions both at a global and individual level. The results obtained are highly interesting for the university in which the study has been carried out, obtaining results that generally outperform the results obtained in related works.

A visão de matriculados sobre a evasão num curso de Licenciatura em Física

Abstract We aim to understand what are, in the perspective of undergraduate students in Physics Teaching degree, the causes and possible solutions to combat the dropout rate of the course. For this, we were grounded on the theoretical model of Tinto and literatur considerations on the causes and the possible action strategies against dropout in Higher Education. Thirty-three students participated in the research by answering an open-answer questionnaire. The analyses, done through Content Analysis, indicated that most participants had already thought about dropping out, especially those who entered without or with reduced levels of commitment to the course. Learning difficulties and a greater sensitivity of the teachers and the institution towards them were pointed, respectively, as the main reason for dropping out and the best way to combat it.

Inequality and Dropout in Higher Education in Colombia. A Multilevel Analysis of Regional Differences, Institutions, and Field of Study

In Colombia, the gaps of regional inequalities and social opportunities permeate people’s economic, political, and social participation. Additionally, the initial endowments of individual and socioeconomic background, barriers to financial aid, and academic and personal skills restrict decision-making about studying. In this context, the main objective is to analyze the determinants of dropout rates in Colombia and the differences between the type of institutions, field of study, and regions. We used data from three public administrative agencies for the period 2000–2012. The methodology combines multiple correspondence analysis and a lineal hierarchical model to explain the effect of variables operating at different levels. As a result, we retained four dimensions to represent the individuals’ socioeconomic and financial conditions. The findings obtained from the multilevel model suggest the variation between institutions (11%) and the interaction between institutions and the program cycle (17.8%). It confirms the influence of inequities on desertion. The student chooses between programs with differences in fees and study costs in general, such as quality, social recognition, and employment. In sum, contextual and institutional disparities in the dropout phenomenon’s behavior are explained mainly by the supply conditions in these regions and the individuals’ socioeconomic backgrounds.

Rural Population and COVID-19: A Model for Assessing the Economic Effects of Drop-Out in Higher Education

Higher education is one of the ways to overcome social inequalities in rural areas in developing countries. This has led states to develop public policies aimed at access, retention and timely graduation of students in those sectors, yet the high drop-out rates among the rural student population, which were catalysed by COVID-19, prevent the intrinsic and extrinsic benefits of obtaining a higher education degree from materialising. Thus, the study of the phenomenon of dropout before and after the pandemic has not sufficiently addressed the economic issues raised by this phenomenon for the different actors at the educational level. The purpose of this paper is to model the economic effects of rural student dropout at the higher education level for students and families, Higher Education Institutions (HEIs) and the State, based on public policies for access to higher education, in the pandemic and post-pandemic scenario. In order to delimit the operationalisation of the proposed model, a set of undergraduate training programmes in Colombia was taken as a reference. System dynamics was used as the main modelling technique. The model was based on data from the 20 training programmes with the highest number of students enrolled in rural areas for the year 2019, by running three computational simulations. The results showed the description of the dynamic model and the financial effects of dropout for the actors of the educational level with the current policies of access to higher education, the scenario in which COVID-19 would not have occurred and the consolidation of the public policy of tuition fee exemption in public HEIs as a result of the pandemic. It was concluded that the model developed is very useful for the valuation of these economic effects and for decision-making on policies to be implemented, given that the costs of dropout are characterised by high costs for students and their families as well as for HEIs, and where it was determined that current policies are inefficient in preventing and mitigating dropout.

How Does Learning Analytics Contribute to Prevent Students’ Dropout in Higher Education: A Systematic Literature Review

Retention and dropout of higher education students is a subject that must be analysed carefully. Learning analytics can be used to help prevent failure cases. The purpose of this paper is to analyse the scientific production in this area in higher education in journals indexed in Clarivate Analytics’ Web of Science and Elsevier’s Scopus. We use a bibliometric and systematic study to obtain deep knowledge of the referred scientific production. The information gathered allows us to perceive where, how, and in what ways learning analytics has been used in the latest years. By analysing studies performed all over the world, we identify what kinds of data and techniques are used to approach the subject. We propose a feature classification into several categories and subcategories, regarding student and external features. Student features can be seen as personal or academic data, while external factors include information about the university, environment, and support offered to the students. To approach the problems, authors successfully use data mining applied to the identified educational data. We also identify some other concerns, such as privacy issues, that need to be considered in the studies.

University Dropout in Engineering: Motives and Student Trajectories.

Dropout in higher education is a concern for students, families, educational institutions, and society. Tertiary education is an important mechanism for empowering people and STEM courses are vital to countries' development. The study combined quantitative and qualitative data. Step 1 was an analysis of personal and contextual variables in a comprehensive examination of dropout in a sample of 1,016 engineering students. In step 2 a short interview by telephone were conducted with 82 students who dropped out, identifying their reasons and their academic/professional situation. In step 3 in-depth interviews were conducted with six students in order to understand the dynamic process of their decisions to leave. The academic/professional situations of students who dropped out were quite varied, for example the same course or a different course at another institution, starting a job, not working or studying, or attending another level of professional training. There were three main reasons for dropping: vocational, learning process and achievement, and reconciling roles. Engineering student dropout is related to vocational and academic achievement. This should be considered in the implementation of programs to reduce the rate of dropout.