Predicting students’ performance is a popular objective of learning analytics, aimed at identifying indicators for learning success. Various data mining approaches have been applied for this purpose on student data collected from learning management systems or intelligent tutoring systems. However, the emerging social media-based learning environments have been less explored so far. Hence, in this paper we present an approach for predicting students’ performance based on their contributions on wiki, blog and microblogging tool. An innovative algorithm (Large Margin Nearest Neighbor Regression) is applied, and comparisons with other algorithms are conducted. Very good correlation coefficients are obtained, outperforming commonly used regression algorithms. Overall, results indicate that students’ active participation on social media tools is a good predictor of learning performance.
CITATION STYLE
Leon, F., & Popescu, E. (2017). Using large margin nearest neighbor regression algorithm to predict student grades based on social media traces. In Advances in Intelligent Systems and Computing (Vol. 617, pp. 12–19). Springer Verlag. https://doi.org/10.1007/978-3-319-60819-8_2
Mendeley helps you to discover research relevant for your work.