Predicting Student Dropout and Academic Success

Realinho, Valentim; Machado, Jorge; Baptista, Luís; Martins, M. V.

doi:10.3390/data7110146

Cited by 33 publications

(14 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Furthermore, these adjustments could reduce doctoral students' attrition rate since poor supervisory relationships often contribute to student dropout (Rigler et al, 2017;Young et al, 2019). Concomitantly, they could also reduce institutional costs linked to doctoral dropouts, help students secure jobs, and increase social justice and economic growth (Realinho et al, 2022). A critical review by Rigler et al (2017, p. 2) on doctoral student attrition reported doctoral programs to have "attrition rates of up to 50% for face-to-face programs and 50-70% for online doctoral programs".…”

Section: Additional Domains Of Collective Action: Organising Factors ...mentioning

confidence: 99%

Integrating and Normalising Coaching as a Routine Practice in Doctoral Supervision

Bordogna¹,

Lundgren‐Resenterra

2023

IJDS

View full text Add to dashboard Cite

Aim/Purpose: Recent research highlights the growing decline in doctoral students’ mental health and wellbeing, caused not only by the pressures, stress, and isolation of doctoral studies but also by existential issues around personal development and future prospects. Consequently, we argue that there is an urgent need to reassess the supervisory process to support doctoral students in addressing these concerns. This paper offers a potential solution to this challenge by exploring and examining how integrating coaching methods into doctoral supervision can support doctoral students’ growth and development, thereby increasing their wellbeing and human flourishing. Coaching aims to help individuals produce optimal performance and improvements in personal and professional settings by deploying a series of tools and models. Coaching is essentially a non-directive form of development, enabling people to identify goals and skills and then extracting the capacity people have within themselves to achieve their ambitions. This paper explores how coaching methods could be made a regular feature of doctoral supervision. Background: The need to reconfigure doctoral supervision as a practice to address humanistic issues regarding whole-person development, self-actualisation, and personal worth is nothing new. Over the years, researchers have produced models of doctoral supervision, highlighting the growing need for supervision to incorporate more pastoral and emancipatory elements, which facilitate personal growth instead of focusing purely on academic function and criticality. Although coaching is identified in previous studies as being a valuable addition, nothing examines how to modify existing supervision practices to accommodate more pastoral elements. Methodology: This paper offers a conceptual analysis whereby the argument primarily synthesizes existing research on doctoral supervision to understand why coaching methods may provide a solution to the evolving requirements of student welfare and emancipation. Since the commentary in this paper is not based on the findings of an empirical study, the following two conceptual research questions frame the discussion. First, are coaching methods beneficial when supervising doctoral students? Second, what are the challenges when implementing and integrating coaching methods into existing doctoral supervisory practice? The paper utilises the Normalisation Process Theory as a ‘thinking tool’ to help answer these questions. The theory evaluates phenomena in applied social research settings to help understand how complex practices are made workable and integrated into context-dependent ways. Therefore, the theory acts as an analytical tool, enabling researchers to think through implementation issues when designing complex interventions and their evaluation. Contribution: This paper contributes to knowledge by highlighting ways in which management responsible for a doctoral provision in higher education settings can modify their organisational structures and systems to encourage coaching methods to become a normalised part of doctoral supervision, thereby legitimising its practice. Findings: The Normalisation Process Theory has value because it produces a roadmap for integrating and implementing new or modified practices into existing systems of operation. It, therefore, assists by producing an output that enables a current/new practice to be dissected and categorised under specific headings. In this research context, this output assisted in understanding the operational challenges when considering the normalisation of a practice. The theory helped generate something managers tasked with managing doctoral provision could consider (i.e., institutional paradigms, policies, regulations, etc.) when thinking about what may need to be reconfigured to enable coaching methods to become an integrated and normalised part of doctoral supervision over time. Recommendations for Practitioners: It is recommended that practitioners consider the integration of coaching methods into supervision. First, once implemented, it requires monitoring to ensure the practice’s quality and consistency amongst the supervisory community. Secondly, to assess the impact of the practice on other services within the organisation, such as student services or faith services, and thirdly, to ensure training in coaching methods is made timely and relevant to assist all academics involved in doctoral supervision. Recommendation for Researchers: The authors recommend collecting empirical evidence using the Normalisation Process Theory to evaluate the integration and normalisation of a range of practices in higher education settings. Moreover, once implemented, more research is required on the long-term value of coaching methods within doctoral settings. Impact on Society: Doctoral education is increasingly significant in a world where knowledge is fundamental to generating economic growth. Identified as having the technical and professional skills needed to fuel the knowledge-based economy, student wellbeing, and mental health must be optimal to ensure they can contribute to the knowledge-based economy as effectively as possible. Future Research: More research must be conducted on how doctoral supervision can become more humanistic; for example, by focusing on student self-awareness, reflection, and reframing instead of just the traditional academic function. Consequently, improving these facets is vital in developing sustained wellbeing and life-long success.

show abstract

Section: Additional Domains Of Collective Action: Organising Factors ...mentioning

confidence: 99%

Integrating and Normalising Coaching as a Routine Practice in Doctoral Supervision

Bordogna¹,

Lundgren‐Resenterra

2023

IJDS

View full text Add to dashboard Cite

show abstract

“…Table 1 shows a complete description of a dataset. For more details about the dataset can be found in [12,16].…”

Section: Data Collectionmentioning

confidence: 99%

Student Academic Performance prognosticative Using optimized Hybrid Machine Learning Algorithms

Kannan

Abarna

Vairachilai

2023

Preprint

View full text Add to dashboard Cite

Prediction of student performance at early stage in higher education is important for academic society so that strategic decisions can be made before students are placed to keep them from dropping out of the course. Due to India's massive student population and extremely ancient educational system, there are significant difficulties in measuring and forecasting students' performance. Every institution in India has its own unique set of criteria for measuring student achievement, and there is no formal process for keeping track of and evaluating a student's progress and improvement. Over the last decade, researchers in the education domain have presented numerous types of machine learning techniques. However, there are significant obstacles to dealing with imbalanced datasets in order to predict the performance of students. In this paper, the first phase of traditional classification algorithms has been applied to the dataset, which contains the progress of 4424 students. In the second phase, novel hybrid machine learning (ML) algorithms were used to get better predictions. The outcome of the proposed model makes it easier to predict how well students will do so that early decisions can be made about the growth of higher education institutions.

show abstract

“…Realinho et al [20] utilized a combination of social community assessment and data mining techniques to predict the prospective success or failure of high school students at the outset of their education. The aim of their observation was modified to increase the accuracy of academic information inputted while considering the social community's opinion.…”

Section: Literature Reviewmentioning

confidence: 99%

Analysis of the Factors Influencing the Predictive Learning Performance Using Federated Learning

Naseem

Mahmood

et al. 2023

Preprint

View full text Add to dashboard Cite

Numerous educational institutions utilize data mining techniques to manage student records, particularly those related to academic achievements , which are essential in improving learning experiences and overall 1 Springer Nature 2021 L A T E X template outcomes. Educational Data Mining (EDM) is a thriving research field that employs data mining and machine learning methods to extract valuable insights from educational databases, primarily focused on predicting students’ academic performance. This study proposes a novel Federated Learning (FL) standard that ensures the confidentiality of the dataset and allows predicting student grades, categorized into four levels: Low, Good, Average, and Drop. To enhance model precision, optimized features are incorporated into the training process. This study evaluates the optimized dataset using five machine learning (ML) algorithms , namely Support Vector Machine (SVM), Decision Tree, Nã A¯ve Bayes, K-Nearest Neighbours, and the proposed Federated Learning Model. The models’ performance is assessed regarding accuracy, precision , recall, and F1 score, followed by a comprehensive comparative analysis. The results reveal that FL and SVM outperform the alternative models, demonstrating superior predictive performance for student grade classification. This study showcases the potential of Federated Learning in effectively utilizing educational data from various institutes while maintaining data privacy, contributing to educational data mining and machine learning advancements for student performance prediction.

show abstract

Predicting Student Dropout and Academic Success

Cited by 33 publications

References 24 publications

Integrating and Normalising Coaching as a Routine Practice in Doctoral Supervision

Integrating and Normalising Coaching as a Routine Practice in Doctoral Supervision

Student Academic Performance prognosticative Using optimized Hybrid Machine Learning Algorithms

Analysis of the Factors Influencing the Predictive Learning Performance Using Federated Learning

Contact Info

Product

Resources

About