Prediction of dilatory behaviour in online assignments

Imhof, Christof; Bergamin, Per; McGarrity, Stéphanie

doi:10.1016/j.lindif.2021.102014

Cited by 8 publications

(17 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, these examples involve a classification of students into clusters, rather than predictions regarding the extent of the delay itself. This research gap was one of the reasons we conducted a previous study to determine if dilatory behavior could be predicted based on a mixture of questionnaire scores and log data [14].…”

Section: B Delay-related Prediction Models In Learning Analyticsmentioning

confidence: 99%

“…Therefore, the goal of this study was to extend the findings reported in [14] by comparing and contrasting the performance of different approaches to prediction models, determining which ML algorithm delivers the best predictions for delay and for which type of predictor.…”

Section: Research Questionsmentioning

confidence: 99%

“…We used the same data set as in a prior study, which included 134 students from a distance university located in Central Europe [14]. The sample included 65 male and 69 female participants (mean age 31.61 years, sd = 7.97, min = 19, max = 61).…”

Section: A Participants and Coursesmentioning

confidence: 99%

“…• We provide a comparative analysis to determine which algorithms deliver the best predictions for which type of variables and compare the performance with Bayesian models as a baseline. For our analyses, we repurposed the same data set as in our prior study, where the prediction of dilatory behavior was investigated, specifically the effect sizes of objective and subjective predictors using Bayesian multilevel regression [14]. The three contributions detailed above also mark the differences between this study and its precursor, where we did not analyze the performance of the predictions in terms of accuracy and other measures.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Prediction of Dilatory Behavior in eLearning: A Comparison of Multiple Machine Learning Models

Imhof

Comşa

Hlosta

et al. 2023

IEEE Trans. Learning Technol.

View full text Add to dashboard Cite

Procrastination, the irrational delay of tasks, is a common occurrence in online learning. Potential negative consequences include higher risk of drop-outs, increased stress, and reduced mood. Due to the rise of learning management systems and learning analytics, indicators of such behavior can be detected, enabling predictions of future procrastination and other dilatory behavior. However, research focusing on such predictions is scarce. Moreover, studies involving different types of predictors and comparisons between the predictive performance of various methods are virtually non-existent. In this study, we aim to fill these research gaps by analyzing the performance of multiple machine learning algorithms when predicting the delayed or timely submission of online assignments in a higher education setting with two categories of predictors: subjective, questionnaire-based variables and objective, log-data based indicators extracted from a learning management system. The results show that models with objective predictors consistently outperform models with subjective predictors, and a combination of both variable types perform slightly better with an accuracy of 70%. For each of these three options, a different approach prevailed (Gradient Boosting Machines for the subjective, Bayesian multilevel models for the objective, and Random Forest for the combined predictors). We conclude that careful attention should be paid to the selection of predictors and algorithms before implementing such models in learning management systems.

show abstract

Section: B Delay-related Prediction Models In Learning Analyticsmentioning

confidence: 99%

Section: Research Questionsmentioning

confidence: 99%

Section: A Participants and Coursesmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Prediction of Dilatory Behavior in eLearning: A Comparison of Multiple Machine Learning Models

Imhof

Comşa

Hlosta

et al. 2023

IEEE Trans. Learning Technol.

View full text Add to dashboard Cite

show abstract

“…Commonly, procrastination is identified through peoples’ responses to self-report instruments. While research suggests these self-report instruments are strongly correlated with one another (e.g., Ferrari et al, 2005 ; Svartdal and Steel, 2017 ), emerging work raises questions regarding the strength of the relationship between self-reported procrastination and behavioral measures of task engagement ( Krause and Freund, 2014 ; Kim and Seo, 2015 ; Imhof et al, 2021 ) or pacing ( Vangsness and Young, 2020 ; Voss and Vangsness, 2020 ). Relatedly, recent research ( Hussey and Hughes, 2020 ) and policy ( Sackett et al, 2018 ) underscored a need to assess the psychometric properties and predictive validity of commonly used self-report instruments.…”

Section: Introductionmentioning

confidence: 99%

Self-Report Measures of Procrastination Exhibit Inconsistent Concurrent Validity, Predictive Validity, and Psychometric Properties

et al. 2022

View full text Add to dashboard Cite

Procrastination is a chronic and widespread problem; however, emerging work raises questions regarding the strength of the relationship between self-reported procrastination and behavioral measures of task engagement. This study assessed the internal reliability, concurrent validity, predictive validity, and psychometric properties of 10 self-report procrastination assessments using responses collected from 242 students. Participants’ scores on each self-report instrument were compared to each other using correlations and cluster analysis. Lasso estimation was used to test the self-report scores’ ability to predict two behavioral measures of delay (days to study completion; pacing style). The self-report instruments exhibited strong internal reliability and moderate levels of concurrent validity. Some self-report measures were predictive of days to study completion. No self-report measures were predictive of deadline action pacing, the pacing style most commonly associated with procrastination. Many of the self-report measures of procrastination exhibited poor fit. These results suggest that researchers should exercise caution in selecting self-report measures and that further study is necessary to determine the factors that drive misalignment between self-reports and behavioral measures of delay.

show abstract

A Systematic Review of Interventions to Reduce Academic Procrastination and Implications for Instructor-based Classroom Interventions

Turner,

Hodis

2023

Educ Psychol Rev

View full text Add to dashboard Cite

Prediction of dilatory behaviour in online assignments

Cited by 8 publications

References 50 publications

Prediction of Dilatory Behavior in eLearning: A Comparison of Multiple Machine Learning Models

Prediction of Dilatory Behavior in eLearning: A Comparison of Multiple Machine Learning Models

Self-Report Measures of Procrastination Exhibit Inconsistent Concurrent Validity, Predictive Validity, and Psychometric Properties

A Systematic Review of Interventions to Reduce Academic Procrastination and Implications for Instructor-based Classroom Interventions

Contact Info

Product

Resources

About