This paper describes the development and evaluation of an affect-aware intelligent support component that is part of a learning environment known as iTalk2Learn. The intelligent support component is able to tailor feedback according to a student's affective state, which is deduced both from speech and interaction. The affect prediction is used to determine which type of feedback is provided and how that feedback is presented (interruptive or non-interruptive). The system includes two Bayesian networks that were trained with data gathered in a series of ecologically-valid Wizard-of-Oz studies, where the effect of the type of feedback and the presentation of feedback on students' affective states was investigated. This paper reports results from an experiment that compared a version that provided affect-aware feedback (affect condition) with one that provided feedback based on performance only (non-affect condition). Results show that students who were in the affect condition were less bored and less off-task, with the latter being statically significant. Importantly, students in both conditions made learning gains that were statistically significant, while students in the affect condition had higher learning gains than those in the non-affect condition, although this result was not statistically significant in this study's sample. Taken all together, the results point to the potential and positive impact of affect-aware intelligent support.
The monitoring by teachers of collaborative, cognitive, and meta-cognitive student activities in collaborative learning is crucial for fostering beneficial student interaction. In a quasi-experimental study, we trained pre-service teachers (N = 74) to notice behavioral indicators for these three dimensions of student activities. Video clips of student interactions in collaborative learning settings served as learning opportunities in the training and as test scenarios for measuring monitoring competency in an assessment tool. Participants completed the assessment tool before and immediately after the training program. A control group (N = 33) completed the assessment tool twice but did not receive training in between. Results show that monitoring competency increased significantly in the training group but not in the control group. This provides initial evidence that a video-based training program can effectively enhance pre-service teachers’ noticing of behavioral indicators of collaborative, cognitive, and meta-cognitive student activities in a relatively short time. Our findings are of practical relevance as evaluating student interactions in a collaborative learning setting is challenging, yet also a skill much needed in teacher practice.
1 April 2022 in Educational Technology Research and Development
Educational technologies in mathematics typically focus on fostering either procedural knowledge by means of structured tasks or, less often, conceptual knowledge by means of exploratory tasks. However, both types of knowledge are needed for complete domain knowledge that persists over time and supports subsequent learning. We investigated in two quasi-experimental studies whether a combination of an exploratory learning environment, providing exploratory tasks, and an intelligent tutoring system, providing structured tasks, fosters procedural and conceptual knowledge more than the intelligent tutoring system alone. Participants were 121 students from the UK (aged 8–10 years old) and 151 students from Germany (aged 10–12 years old) who were studying equivalent fractions. Results confirmed that students learning with a combination of exploratory and structured tasks gained more conceptual knowledge and equal procedural knowledge compared to students learning with structured tasks only. This supports the use of different but complementary educational technologies, interleaving exploratory and structured tasks, to achieve a “combination effect” that fosters robust fractions knowledge.