Analysis of the Factors Influencing Learners’ Performance Prediction With Learning Analytics
Open Access
- 1 January 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 5264-5282
Abstract
The advancement of learning analytics has enabled the development of predictive models to forecast learners’ behaviors and outcomes (e.g., performance). However, many of these models are only applicable to specific learning environments and it is usually difficult to know which factors influence prediction results, including the predictor variables as well as the type of prediction outcome. Knowing these factors would be relevant to generalize to other contexts, compare approaches, improve the predictive models and enhance the possible interventions. In this direction, this work aims to analyze how several factors can make an influence on the prediction of students’ performance. These factors include the effect of previous grades, forum variables, variables related to exercises, clickstream data, course duration, type of assignments, data collection procedure, question format in an exam, and the prediction outcome (considering intermediate assignment grades, including the final exam, and the final grade). Results show that variables related to exercises are the best predictors, unlike variables about forum, which are useless. Clickstream data can be acceptable predictors when exercises are not available, but they do not add prediction power if variables related to exercises are present. Predictive power was also better for concept-oriented assignments and best models usually contained only the last interactions. In addition, results showed that multiple-choice questions were easier to predict than coding questions, and the final exam grade (actual knowledge at a specific moment) was harder to predict than the final grade (average knowledge in the long term), based on different assignments during the course.Keywords
Funding Information
- Ministerio de Ciencia, Innovación y Universidades (TIN2017-85179-C3-1-R)
- Comunidad de Madrid (S2018/TCS-4307)
- European structural funds
- Ministerio de Ciencia, Innovación y Universidades (FPU016/00526, EST18/00554)
- Research Grants Council, University Grants Committee (T44-707/16-N)
- Innovation and Technology Fund (ITS/388/17FP)
This publication has 31 references indexed in Scilit:
- Learning analytics should not promote one size fits all: The effects of instructional conditions in predicting academic successThe Internet and Higher Education, 2016
- Predicting students' success based on forum activities in MOOCs2015
- MOOC performance prediction via clickstream data and social learning networks2015
- Who You Are or What You Do2015
- Learning about Social Learning in MOOCs: From Statistical Analysis to Generative ModelIEEE Transactions on Learning Technologies, 2014
- Predicting MOOC Dropout over Weeks Using Machine Learning Methods2014
- Facing Imbalanced Data--Recommendations for the Use of Performance Metrics2013
- Measuring Determinants of Student Return VS. Dropout/Stopout VS. Transfer: A First-to-Second Year Analysis of New FreshmenResearch in Higher Education, 2005
- A Comparison of Sensitivity Analysis TechniquesHealth Physics, 1995
- College Persistence: Structural Equations Modeling Test of an Integrated Model of Student RetentionThe Journal of Higher Education, 1993