Tweets Reveal More Than You Know: A Learning Style Analysis on Twitter

Abstract

Adaptation and personalization of e-learning and technology-enhanced learning (TEL) systems in general, have become a tremendous key factor for the learning success with such systems. In order to provide adaptation, the system needs to have access to relevant data about the learner. This paper describes a preliminary study with the goal to infer a learner's learning style from her Twitter stream. We selected the Felder-Silverman Learning Style Model (FSLSM) due to its validity and widespread use and collected ground truth data from 51 study participants based on self-reports on the Index of Learning Style questionnaire and tweets posted on Twitter. We extracted 29 features from each subject's Twitter stream and used them to classify each subject as belonging to one of the two poles for each of the four dimensions of the FSLSM. We found a more than by chance agreement only for a single dimension: active/reflective. Further implications and an outlook are presented.