An evaluation of an adaptive learning system based on multimodal affect recognition for learners with intellectual disabilities

Artificial intelligence tools for education (AIEd) have been used to automate the provision of learning support to mainstream learners. One of the most innovative approaches in this field is the use of data and machine learning for the detection of a student’s affective state, to move them out of negative states that inhibit learning, into positive states such as engagement. In spite of their obvious potential to provide the personalisation that would give extra support for learners with intellectual disabilities, little work on AIEd systems that utilise affect recognition currently addresses this group. Our system used multimodal sensor data and machine learning to first identify three affective states linked to learning (engagement, frustration, boredom) and second determine the presentation of learning content so that the learner is maintained in an optimal affective state and rate of learning is maximised. To evaluate this adaptive learning system, 67 participants aged between 6 and 18 years acting as their own control took part in a series of sessions using the system. Sessions alternated between using the system with both affect detection and learning achievement to drive the selection of learning content (intervention) and using learning achievement alone (control) to drive the selection of learning content. Lack of boredom was the state with the strongest link to achievement, with both frustration and engagement positively related to achievement. There was significantly more engagement and less boredom in intervention than control sessions, but no significant difference in achievement. These results suggest that engagement does increase when activities are tailored to the personal needs and emotional state of the learner and that the system was promoting affective states that in turn promote learning. However, longer exposure is necessary to determine the effect on learning.     

Cultivating constructivist science internships for high school students through a community of practice with cogenerative dialogues

Working with scientists has been suggested as an effective way for high-school students to learn authentic science. However, little research has involved students’ perceptions of science learning environments in a university internship. This study drew on the theoretical framework of community of practice with cogenerative dialogues to design an internship program that aims to build a constructivist internship for students. Students who learned science in the internship program developed stronger constructivist learning perceptions than those who learned science in school. Specifically, students perceived that they had more opportunities to think independently of the instructors and other students. Three effective principles for program design are: (a) high school students conduct open-inquiry projects with the support of scientists; (b) high school students and scientists conduct cogenerative dialogues regularly to address issues and share experiences; and (c) high school students present their project proposals and scientific findings at open house events. Implications of the results are discussed.     

Short- and long-term reliability of leg extensor power measurement in middle-aged and older adults

Muscular power is important for maintaining physical functioning with aging. Proper quantification of the reliability of muscular power tests is crucial to inform monitoring of individuals and sample size planning for interventional studies. This study evaluated short- and long-term reliability of leg extensor power measurement in 72 adults (age 62.7 ± 8.6 years). Participants completed four repeat trials on the Nottingham leg extensor power rig, with a further trial twelve weeks later. Mean change, typical error, and intraclass correlation coefficients (ICC) were calculated. For short-term reliability, mean change in power output was trivial after two trials (1.2–4.8%). Typical errors were small following four trials in the dominant leg of males (10.9–5.8%), three in the non-dominant leg of males (9.9–6.2%) and the dominant leg of females (10.0–9.6%) and two in the non-dominant leg in females (8.3%). Intraclass correlation coefficients (ICCs) were very high (0.88–0.96). For long-term reliability, mean change remained trivial (1.0–2.5%), typical errors remained small (5.8–8.6%), and ICCs very high (0.94–0.96). The leg extensor power rig is a reliable method for assessing lower body muscular power, both short- and long-term, with only minimal habituation effects.     

‘So you can’t blame us then?’: gendered discourses of masculine irresponsibility as biologically determined and peer-pressured in upper-primary school contexts

In a global climate increasingly shaped by neoliberal agendas that privilege meritocratic individualism, it is apparent that society as a whole and educational policy-makers and practitioners in particular expect students to take more ‘responsibility’ for their own learning and behaviour at school. In the Australian context, as elsewhere, schools are seen as sites in which students should develop and practise responsibility for self and others in ways that are enterprising, productive, civic-minded, and in accordance with social norms. Yet, few studies have critically examined how the concept of responsibility features in the everyday, taken-for-granted, discursive practices of policy-makers, teachers and students. This paper discusses findings from an ethnographic study concerned with how the discursive constructions of responsibility in three regional Australian primary schools shape upper-primary students’ understandings and experiences of responsibility for self and others. Using the theoretical insights of Michel Foucault, Emmanuel Levinas and Judith Butler to interpret data, I argue that gendered discourses of biological determinism and peer pressure work to reinforce the misconception that violence and irresponsibility are ‘naturally’ masculine traits.