Machine Learning Approach of Predicting Learning Outcomes of MOOCs to Increase Its Performance

Lisitsyna, Lubov S.; Oreshin, Svyatoslav A.

doi:10.1007/978-981-13-8260-4_10

Cited by 3 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our study, we demonstrated that preprocessing filter feature selection techniques also enhanced the performance of LR in achieving comparable AUC values with GLMNET and exceeded those of RF and XGBoost. While ensemble black-box techniques have been shown to enhance the performance of DMMs (Abdulazeez & Abdulwahab, 2018;Amrieh et al, 2016;Aulck et al, 2017;Beemer et al, 2018;Lisitsyna & Oreshin, 2019;Stapel et al, 2016), several EDM studies found that non-ensemble techniques performed better than ensemble models (Adekitan & Noma-Osaghae, 2019;Bucos & Drăgulescu, 2018). A limitation to these prior studies is that they neither incorporated preprocessing filter feature selection techniques nor utilized course-specific information in their analyses; rather, they focused on demographic and student academic achievements in their data pipelines.…”

Section: Discussionmentioning

confidence: 99%

“…However, the impact of LMS logins in predicting student outcomes has been mixed in EDM. Some studies found them to be valuable for accurately predicting performance in online classroom settings (Al-Shabandar et al, 2017;Lisitsyna & Oreshin, 2019;Morris et al, 2005;Tan et al, 2019); however, poorer prediction performance was achieved for blended courses incorporating online learning and in-class instruction (Conijn et al, 2016). Since the biology course studied is a lecture-based in-person course where the LMS is used for instructor/student communication and for posting lecture notes, the course delivery method may be attributed to these predictors being less of a contributing factor to retention and attrition than in other studies.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing data pipelines for forecasting student performance: integrating feature selection with cross-validation

Bertolini

Finch

Nehm

2021

Int J Educ Technol High Educ

View full text Add to dashboard Cite

Educators seek to harness knowledge from educational corpora to improve student performance outcomes. Although prior studies have compared the efficacy of data mining methods (DMMs) in pipelines for forecasting student success, less work has focused on identifying a set of relevant features prior to model development and quantifying the stability of feature selection techniques. Pinpointing a subset of pertinent features can (1) reduce the number of variables that need to be managed by stakeholders, (2) make “black-box” algorithms more interpretable, and (3) provide greater guidance for faculty to implement targeted interventions. To that end, we introduce a methodology integrating feature selection with cross-validation and rank each feature on subsets of the training corpus. This modified pipeline was applied to forecast the performance of 3225 students in a baccalaureate science course using a set of 57 features, four DMMs, and four filter feature selection techniques. Correlation Attribute Evaluation (CAE) and Fisher’s Scoring Algorithm (FSA) achieved significantly higher Area Under the Curve (AUC) values for logistic regression (LR) and elastic net regression (GLMNET), compared to when this pipeline step was omitted. Relief Attribute Evaluation (RAE) was highly unstable and produced models with the poorest prediction performance. Borda’s method identified grade point average, number of credits taken, and performance on concept inventory assessments as the primary factors impacting predictions of student performance. We discuss the benefits of this approach when developing data pipelines for predictive modeling in undergraduate settings that are more interpretable and actionable for faculty and stakeholders.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Enhancing data pipelines for forecasting student performance: integrating feature selection with cross-validation

Bertolini

Finch

Nehm

2021

Int J Educ Technol High Educ

View full text Add to dashboard Cite

show abstract

“…The inclusion of LMS data in EDM and LA models have been predominantly utilized in online, blended, or flipped classroom environments where they were deemed necessary tools for guiding administrative and pedagogical interventions (see Al-Shabandar et al, 2017;Wang, 2017;Lisitsyna and Oreshin, 2019;Shayan and van Zaanen, 2019;Louhab et al, 2020;Nieuwoudt, 2020). Our findings demonstrated that using technological resources with in-class instruction provided greater insights into student achievement.…”

Section: Discussionmentioning

confidence: 75%

An application of Bayesian inference to examine student retention and attrition in the STEM classroom

Bertolini

Finch²,

Nehm³

2023

Front. Educ.

View full text Add to dashboard Cite

IntroductionAs artificial intelligence (AI) technology becomes more widespread in the classroom environment, educators have relied on data-driven machine learning (ML) techniques and statistical frameworks to derive insights into student performance patterns. Bayesian methodologies have emerged as a more intuitive approach to frequentist methods of inference since they link prior assumptions and data together to provide a quantitative distribution of final model parameter estimates. Despite their alignment with four recent ML assessment criteria developed in the educational literature, Bayesian methodologies have received considerably less attention by academic stakeholders prompting the need to empirically discern how these techniques can be used to provide actionable insights into student performance.MethodsTo identify the factors most indicative of student retention and attrition, we apply a Bayesian framework to comparatively examine the differential impact that the amalgamation of traditional and AI-driven predictors has on student performance in an undergraduate in-person science, technology, engineering, and mathematics (STEM) course.ResultsInteraction with the course learning management system (LMS) and performance on diagnostic concept inventory (CI) assessments provided the greatest insights into final course performance. Establishing informative prior values using historical classroom data did not always appreciably enhance model fit.DiscussionWe discuss how Bayesian methodologies are a more pragmatic and interpretable way of assessing student performance and are a promising tool for use in science education research and assessment.

show abstract

“…Predictive analytics work has primarily relied upon data from traditional assessment types to build ML prediction models for in-person, hybrid, and online learning environments; no work to our knowledge has utilized CIs. Traditional assessment sources have included (1) standardized tests [e.g., SAT] (Adekitan & Noma-Osaghae (2019); Alexandro (2018); Aulck et al (2017); Beemer et al (2018); Getachew (2017); Kumar and Singh (2017)), (2) classroom/virtual assignments and examinations (Al-Shabandar et al 2017;Lisitsyna and Oreshin 2019), and (3) collaborative group and participation activities (Bucos and Drăgulescu 2018).…”

Section: Literature Reviewmentioning

confidence: 99%

Testing the Impact of Novel Assessment Sources and Machine Learning Methods on Predictive Outcome Modeling in Undergraduate Biology

2021

View full text Add to dashboard Cite

High levels of attrition characterize undergraduate science courses in the USA. Predictive analytics research seeks to build models that identify at-risk students and suggest interventions that enhance student success. This study examines whether incorporating a novel assessment type (concept inventories [CI]) and using machine learning (ML) methods (1) improves prediction quality, (2) reduces the time point of successful prediction, and (3) suggests more actionable course-level interventions. A corpus of university and course-level assessment and non-assessment variables (53 variables in total) from 3225 students (over six semesters) was gathered. Five ML methods were employed (two individuals, three ensembles) at three time points (pre-course, week 3, week 6) to quantify predictive efficacy. Inclusion of course-specific CI data along with university-specific corpora significantly improved prediction performance. Ensemble ML methods, in particular the generalized linear model with elastic net (GLMNET), yielded significantly higher area under the curve (AUC) values compared with non-ensemble techniques. Logistic regression achieved the poorest prediction performance and consistently underperformed. Surprisingly, increasing corpus size (i.e., amount of historical data) did not meaningfully impact prediction success. We discuss the roles that novel assessment types and ML techniques may play in advancing predictive learning analytics and addressing attrition in undergraduate science education.

show abstract

Machine Learning Approach of Predicting Learning Outcomes of MOOCs to Increase Its Performance

Cited by 3 publications

References 7 publications

Enhancing data pipelines for forecasting student performance: integrating feature selection with cross-validation

Enhancing data pipelines for forecasting student performance: integrating feature selection with cross-validation

An application of Bayesian inference to examine student retention and attrition in the STEM classroom

Testing the Impact of Novel Assessment Sources and Machine Learning Methods on Predictive Outcome Modeling in Undergraduate Biology

Contact Info

Product

Resources

About