Shifting the Load: a Peer Dialogue Agent that Encourages its Human Collaborator to Contribute More to Problem Solving

Find the Mistake!

Abstract. Reasoning ability has commonly been regarded as the best predictor of academic and occupational success. Due to concerns about the validity of multiple-choice (MC) formats, test security breaches, and the fact that the difficulty levels of most existing reasoning assessments target the population mean, there is a constant need for new reliable and valid test instruments that can be applied to assess fluid intelligence in advanced cognitive performance areas. We developed a novel computerized figural matrices test to assess nonverbal reasoning for university student aptitude assessment. In two studies, we generated, revised, and empirically validated the Isometric Matrices Test (IMT). Our results show that the IMT is less prone to test-wiseness strategies than existing reasoning tests. In a third study, we created and evaluated an innovative Find the Mistake (FtM) response format as an alternative to classical multiple-choice formats. Overall, both response formats revealed satisfactory psychometric quality in terms of item difficulties and discrimination, test-retest reliability, construct and criterion validity, and Rasch or two-parameter logistic (2PL) model fit, but in one MC version, the internal consistency was low due to negative discrimination indices. The MC response format turned out to be easier than the FtM format, with men slightly outperforming women in both response modes. We propose the IMT as a useful tool for assessing nonverbal reasoning ability in above-average performance areas and discuss the automatic generation of larger IMT item pools for adaptive testing in order to increase test security and reliability.

Promoting Social Engagement With a Multi-Role Dancing Robot for In-Home Autism Care

This work describes the design of real-time dance-based interaction with a humanoid robot, where the robot seeks to promote physical activity in children by taking on multiple roles as a dance partner. It acts as a leader by initiating dances but can also act as a follower by mimicking a child’s dance movements. Dances in the leader role are produced by a sequence-to-sequence (S2S) Long Short-Term Memory (LSTM) network trained on children’s music videos taken from YouTube. On the other hand, a music orchestration platform is implemented to generate background music in the follower mode as the robot mimics the child’s poses. In doing so, we also incorporated the largely unexplored paradigm of learning-by-teaching by including multiple robot roles that allow the child to both learn from and teach to the robot. Our work is among the first to implement a largely autonomous, real-time full-body dance interaction with a bipedal humanoid robot that also explores the impact of the robot roles on child engagement. Importantly, we also incorporated in our design formal constructs taken from autism therapy, such as the least-to-most prompting hierarchy, reinforcements for positive behaviors, and a time delay to make behavioral observations. We implemented a multimodal child engagement model that encompasses both affective engagement (displayed through eye gaze focus and facial expressions) as well as task engagement (determined by the level of physical activity) to determine child engagement states. We then conducted a virtual exploratory user study to evaluate the impact of mixed robot roles on user engagement and found no statistically significant difference in the children’s engagement in single-role and multiple-role interactions. While the children were observed to respond positively to both robot behaviors, they preferred the music-driven leader role over the movement-driven follower role, a result that can partly be attributed to the virtual nature of the study. Our findings support the utility of such a platform in practicing physical activity but indicate that further research is necessary to fully explore the impact of each robot role.

Artificial intelligence with fuzzy logic system for learning management evaluation in higher educational systems

In this paper, the mathematical model and algorithm based on knowledge forgetting curve are studied. Through the analysis of the current mathematical modeling and application of “knowledge forgetting curve”, the artificial intelligence method of fuzzy mathematics knowledge and differential modeling is adopted. This paper puts forward the mathematical model and algorithm design of the new “knowledge forgetting curve”, which aims to improve the intelligence of the software and bring a new learning experience for the teaching evaluation of the education system in colleges and universities. The fuzzy logic theory is applied to the teaching evaluation system of higher learning pedagogy, according to pedagogy and other related theories, combined with the current teaching evaluation indicators of colleges and universities, the teaching evaluation indicators of higher learning education are set according to certain requirements. The sample wood data is divided into two parts by using the fuzzy logic principle, and the training model is obtained by training the sample data in the evaluation system, and the training model is used to intelligently evaluate and analyze the prediction data.