Search for: All records

Research into student affect detection has historically relied on ground truth measures of emotion that utilize one of three sources of data: (1) self-report data, (2) classroom observations, or (3) sen- sor data that is retrospectively labeled. Although a few studies have compared sensor- and observation-based approaches to student af- fective modeling, less work has explored the relationship between self-report and classroom observations. In this study, we use both recurring self-reports (SR) and classroom observation (BROMP) to measure student emotion during a study involving middle school students interacting with a game-based learning environment for microbiology education. We use supervised machine learning to develop two sets of affect detectors corresponding to SR and BROMP-based measures of student emotion, respectively. We compare the two sets of detectors in terms of their most relevant features, as well as correlations of their output with measures of student learning and interest. Results show that highly predictive features in the SR detectors are different from those selected for BROMP-based detectors. The associations with interest and moti- vation measures show that while SR detectors captured underlying motivations, the BROMP detectors seemed to capture more in-the- moment information about the student’s experience. Evidence sug- gests that there is benefit of using both sources of data to model different components of student affect. 

Although numerous programs exist in many institutions of higher education aimed at helping students from underrepresented groups achieve their goals of successfully graduating in a science, technology, mathematics, or engineering (STEM) field and moving on to the next educational level or a career, few are set up to support students across schools, from their entry into postsecondary education at the community college through the completion of their fouryear degree at a university and beyond. Furthermore, few programs are able to offer the full range of support that has been shown to be optimally effective toward promoting student success, as in, for example, the Building Engineering and Science Talent (BEST) model laid out by Chubin and Ward (2009). The reason for this is simple: rarely are the funds available from any given source to allow a program to provide all the supports students need. In this paper, we provide an example of how this problem was (at least partly) solved by the close interaction of two Louis Stokes Alliances for Minority Participation and an S-STEM program, working within the context of other support opportunities at three community colleges and one university in Northern New Jersey. The programs and the mechanisms through which they support students are described and preliminary data examining their impacts are presented.