Bachelor Thesis Analytics: Using Machine Learning to Predict Dropout and Identify Performance Factors

Nouri, Jalal; Larsson, Ken; Saqr, Mohammed

doi:10.3991/ijai.v1i1.11065

Cited by 8 publications

(11 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By dispositions, we mean behavioral and cognitive factors such as motivation (to write a master thesis, for instance), engagement, self-regulation skills, strategies and attitudes [43,44]. Such an approach would most likely increase the probability of finding additional factors that influence the master thesis process and increase accuracy, replicability and transferability of prediction models [27,45,46].…”

Section: Discussionmentioning

confidence: 99%

Identifying Factors for Master Thesis Completion and Non-completion Through Learning Analytics and Machine Learning

Nouri¹,

Larsson²,

Saqr³

2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

The master thesis is the last formal step in most universities around the world. However, all students do not finish their master thesis. Thus, it is reasonable to assume that the non-completion of the master thesis should be viewed as a substantial problem that requires serious attention and proactive planning. This learning analytics study aims to understand better factors that influence completion and non-completion of master thesis projects. More specifically, we ask: which student and supervisor factors influence completion and non-completion of master thesis? Can we predict completion and noncompletion of master thesis using such variables in order to optimise the matching of supervisors and students? To answer the research questions, we extracted data about supervisors and students from two thesis management systems which record large amounts of data related to the thesis process. The sample used was 755 master thesis projects supervised by 109 teachers. By applying traditional statistical methods (descriptive statistics, correlation tests and independent sample t-tests), as well as machine learning algorithms, we identify five central factors that can accurately predict master thesis completion and non-completion. Besides the identified predictors that explain master thesis completion and non-completion, this study contributes to demonstrating how educational data and learning analytics can produce actionable data-driven insights. In this case, insights that can be utilised to inform and optimise how supervisors and students are matched and to stimulate targeted training and capacity building of supervisors.

show abstract

Section: Discussionmentioning

confidence: 99%

Identifying Factors for Master Thesis Completion and Non-completion Through Learning Analytics and Machine Learning

Nouri¹,

Larsson²,

Saqr³

2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Most of the studies on online engagement have looked into a course or two while the longitudinal online engagement remains an uncharted territory especially in higher education settings [18,23]. Very few exceptions can be mentioned here.…”

Section: Trajectories Of Engagementmentioning

confidence: 99%

The trajectory of early disengagement: A longitudinal learning analytics study over a full program

Saqr

López-Pernas

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Research on online engagement is abundant. However, most of the available studies have focused on a single course. Therefore, little is known about how students’ online engagement evolves over time. Previous research in face-to-face settings has shown that early disengagement has negative consequences on students’ academic achievement and graduation rates. This study examines the longitudinal trajectory of students’ online engagement throughout a complete college degree. The study followed 99 students over 4 years of college education including all their course data (15 courses and 1383 course enrollments). Students’ engagement states for each course enrollment were identified through Latent Class Analysis (LCA). Students who were not engaged at least one course in the first term were labeled as “Early Disengagement”, whereas the remaining students were labeled as “Early Engagement”. The two groups of students were analyzed using sequence pattern mining methods. The stability (persistence of the engagement state), transition (ascending to a higher engagement state or descending to a lower state), and typology of each group trajectory of engagement are described in this study. Our results show that early disengagement is associated with higher rates of dropout, lower scores and lower graduation rates whereas early engagement is relatively stable. Our findings indicate that it is critical to proactively address early disengagement during a program, watch the alarming signs such as presence of disengagement during the first courses, declining engagement along the program or history of frequent disengagement states.

show abstract

“…writing, it is hoped that students will develop competencies for developing critical thinking, empirical research literacy and synthesis of knowledge and assessment of the truth of information (Nouri et al, 2019). Very little literature regarding the Bachelor's thesis is available.…”

Section: Thesis Examiner Performancementioning

confidence: 99%

“…In higher education, the thesis has been a central element as well as a formal requirement of undergraduate programs for more than a century (Rennie and Brewer, 1987;Wong, 2010). In most universities around the world, a bachelor thesis is a compulsory final step toward graduation in higher education and, thus, is the main key for further study as well as jobs requiring a higher education degree (Nouri et al, 2019). As with many higher education institutions in the world, almost all tertiary education institutions in Indonesia also make thesis preparation a requirement for graduation from the undergraduate level.…”

Section: Introductionmentioning

confidence: 99%

Student satisfaction on the implementation of the online undergraduate thesis examination: a PLS-SEM analysis

Astuti¹,

Rukmana²

2021

QAE

View full text Add to dashboard Cite

Purpose The covid-19 pandemic that hit the world has caused several changes in the higher education service sector, including the implementation of the undergraduate thesis examination, where direct interaction between students and examiners is avoided and replacing it with an online bachelor thesis exam. This study aims to develop a conceptual model regarding the variables that can affect student satisfaction with the quality of the implementation of online undergraduate thesis examinations in higher education. Design/methodology/approach The research instrument consisted of 22 survey questions distributed to 583 students taking the thesis trial examination in the even semester of 2019/2020 who came from 12 different study programs. Factor analysis and structural equation modeling (SEM) were conducted to analyze the validity of the instrument and test the hypothesis. The results of the analysis show that the 22 instrument items used have been determined by sufficient variables to check the structure of each. Findings SEM analysis results show that the three hypothesized variables (study program service, examiner performance and quality of video conference applications) positively and significantly affect the level of student satisfaction with the online undergraduate thesis examination 0.187, 0.177 and 0.177, respectively. The total effect of these three factors is 0.737. Research limitations/implications This finding is a reference for those who want to improve the quality of the online undergraduate thesis examination in higher education. Originality/value As the online thesis examination was implemented in higher education in Indonesia as a result of the implementation of the study and work at home policy by the Indonesian Ministry of Education, it is important to conduct research on the implementation of online thesis exams in Indonesia, especially to study the conceptual model of variables affect student satisfaction with the implementation of the online thesis exam. Because even though the implementation of online thesis exams on a large scale is new to some higher education in Indonesia.

show abstract

Bachelor Thesis Analytics: Using Machine Learning to Predict Dropout and Identify Performance Factors

Cited by 8 publications

References 35 publications

Identifying Factors for Master Thesis Completion and Non-completion Through Learning Analytics and Machine Learning

Identifying Factors for Master Thesis Completion and Non-completion Through Learning Analytics and Machine Learning

The trajectory of early disengagement: A longitudinal learning analytics study over a full program

Student satisfaction on the implementation of the online undergraduate thesis examination: a PLS-SEM analysis

Contact Info

Product

Resources

About