Rich Representations for Analyzing Learning Trajectories: Systematic Review on Sequential Data Analytics in Game-Based Learning Research

Abstract

This chapter focuses on sequential data analytics (SDA), which is one of the prominent behavior analysis frameworks in game-based learning (GBL) research. Although researchers have used a variety of SDA approaches in GBL, they have provided limited information that demonstrates the way they have employed those SDA approaches in different learning contexts. This study used a systematic literature review to demonstrate findings that synthesize SDA’s empirical uses in various GBL contexts. In this chapter, we recapitulate the characteristics of several SDA techniques that salient GBL studies have used first. Then, we address the underlying theoretical foundations that explain the proper uses of SDA in GBL research. Lastly, the chapter concludes with brief guidelines that illustrate the way to use SDA, as well as reveal major issues in implementing SDA.