Predicting achievement and providing support before STEM majors begin to fail. (December 2020)

• Record Type: Journal Article
• Authors: Bernacki, Matthew L.; Chavez, Michelle M.; Uesbeck, P. Merlin
• Is Part Of: Computers & education. Volume 158(2020)
• Publication Date: 2020-12
• Subjects: Learning management systems -- Early warning systems -- Learning analytics -- Prediction modeling -- STEM learning; Education -- Data processing -- Periodicals; Education -- Periodicals; Computers -- Periodicals; Computer-Assisted Instruction -- Periodicals; Éducation -- Informatique -- Périodiques; Electronic journals; 370.285
• DOI: 10.1016/j.compedu.2020.103999
• Languages: English
• ISSNs: 0360-1315

Abstract

Abstract: Prediction models that underlie "early warning systems" need improvement. Some predict outcomes using entrenched, unchangeable characteristics (e.g., socioeconomic status) and others rely on performance on early assignments to predict the final grades to which they contribute. Behavioral predictors of learning outcomes often accrue slowly, to the point that time needed to produce accurate predictions leaves little time for intervention. We aimed to improve on these methods by testing whether we could predict performance in a large lecture course using only students' digital behaviors in weeks prior to the first exam. Early prediction based only on malleable behaviors provides time and opportunity to advise students on ways to alter study and improve performance. Thereafter, we took the not-yet-common step of applying this model and testing whether providing digital learning support to those predicted to perform poorly can improve their achievement. Using learning management system log data, we tested models composed of theory-aligned behaviors using multiple algorithms and obtained a model that accurately predicted poor grades. Our algorithm correctly identified 75% of students who failed to earn the grade of B or better needed to advance to the next course. We applied this model the next semester to predict achievement levels and provided a digital learning strategy intervention to students predicted to perform poorly. Those who accessed advice outperformed classmates on subsequent exams, and more students who accessed the advice achieved the B needed to move forward in their major than those who did not access advice. Highlights: Students' early digital learning behaviors informed models predicting course grades. Modeling tested predictive accuracy of multiple algorithms. Models achieved high accuracy using only behaviors (no demographics, performances). The applied model identified 75% of the 190 students who failed to earn Bs. Students who accessed learning support outperformed others on future course exams.