Predictive modeling is an important part of learning analytics, whose main objective is to estimate student success, in terms of performance, knowledge, score or grade. The data used for the predictive model can be either state-based data (e.g., demographics, psychological traits, past performance) or event-driven data (i.e., based on student activity). The latter can be derived from students’ interactions with educational systems and resources; learning management systems are a widely analyzed data source, while social media-based learning environments are scarcely explored. In this context, our objective is to predict students’ performance based on their social media traces. Data is collected from a Web Applications Design course, in which students use wiki, blog and microblogging tools, for communication and collaboration activities in a project-based learning scenario. A total of 343 students, from six consecutive course installments, are included in the study. In addition to the novel settings and performance indicators, an innovative regression algorithm is used for grade prediction. Very good correlation coefficients are obtained and 85% of predictions are within one point of the actual grade, outperforming classic regression algorithms. From a pedagogical perspective, results indicate that, as a general rule, a higher engagement with social media tools correlates with a higher final grade.

Individualizing the learning experience for each student is an important goal for educational systems and accurately modeling the learner is the first step towards attaining this goal. This chapter addresses learner modeling from the point of view of learning styles, an important factor for the efficiency and effectiveness of the learning process. A critical review of existing modeling methods is provided, outlining the specificities and limitations of current learning style based adaptive educational systems (LSAES). The controversy regarding the multitude of partially overlapping learning style models proposed in the literature is addressed, by suggesting the use of a complex of features, each with its own importance and influence (the so called Unified Learning Style Model). An implicit modeling method is introduced, based on analyzing students’ behavioral patterns. The approach is validated experimentally and good precision rates are reported.