Intelligent tutoring systems (ITSs) aim to support student learning through comprehensive adaptive features, making for costly development times—about 200–300 hours of development time per hour of instruction. This proposal outlines plans to overcome several technical challenges toward building authoring tools whereby a non-programmer can build ITSs by interactively teaching simulated students. I propose both interaction design considerations and machine-learning innovations. These include a multi-modal natural language processing mechanism that mimics student learning from narrated tutorial instruction, and an active-learning mechanism that identifies training examples likely to eliminate inaccuracies in the simulated student’s induced production rules. I propose to evaluate these features over 3 user studies and evaluate the generality of this authoring method in a final open-ended authoring study. This work aims to democratize ITS authoring by opening new authoring opportunities to non-programmers by making authoring as time-efficient and natural as human-to-human tutoring. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

In this study, we developed machine learning algorithms to automatically score students' written arguments and then applied the cognitive diagnostic modeling (CDM) approach to examine students' cognitive patterns of scientific argumentation. We abstracted three types of skills (i.e., attributes) critical for successful argumentation practice: making claims, using evidence, and providing warrants. We developed 19 constructed response items, with each item requiring multiple cognitive skills. We collected responses from 932 students in Grades 5 to 8 and developed machine learning algorithmic models to automatically score their responses. We then applied CDM to analyze their cognitive patterns. Results indicate that machine scoring achieved the average machine-human agreements of Cohen's kappa = 0.73, SD= 0.09. We found that students were clustered in 21 groups based on their argumentation performance, each revealing a different cognitive pattern. Within each group, students showed different abilities regarding making claims, using evidence, and providing warrants to justify how the evidence supports a claim. The 9 most frequent groups accounted for more than 70% of the students in the study. Our in-depth analysis of individual students suggests that students with the same total ability score might vary in the specific cognitive skills required to accomplish argumentation. This result illustrates the advantage of CDM in assessing the fine-grained cognition of students during argumentation practices in science and other scientific practices.

In the proposed research, we investigated whether the standardized neuropsychological tests commonly used to assess attention can be used to measure students’ engagement in online learning settings. Accordingly, we employed 73 students in three clinically relevant neuropsychological tests to assess three types of attention. Students’ engagement performance, as evidenced by their facial video, was also annotated by three independent annotators. The manual annotations observed a high level of inter-annotator reliability (Krippendorffs’ Alpha of 0.864). Further, by obtaining a correlation value of 0.673 (Spearmans’ Rank Correlation) between manual annotation and neuropsychological tests score, our results show construct validity to prove neuropsychological test scores’ significance as a latent variable for measuring students’ engagement. Finally, using non-intrusive behavioral cues, including facial action unit and eye gaze data collected via webcam, we propose a machine learning method for engagement analysis in online learning settings, achieving a low mean squared error value (0.022). The findings suggest a neuropsychological test-based machine learning technique could effectively assess students’ engagement in online education. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Nurturing a sense of belonging in a classroom can positively impact student attrition, especially for underrepresented groups. In this work, we develop and study the effectiveness of a recommendation system that aims to foster belonging by sharing challenges and possible solutions that other students have had while taking the same course. Our system uses sentence transformers and calculates the similarity between students’ reflections. We measure participating students’ sense of belonging before and after they view the top 5 challenges and solutions received from other students. Using a significance level of 0.05, we found a p-value of 0.0145, indicating that there is a significant increase in overall belonging values. Students also rated 61% of the solutions as useful. This work allows future students to also benefit from the experiences of those before them. By showing students that those before them also had similar challenges and overcame them, we can show students that they do, in fact, belong among their peers. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

While race and gender academic disparities have often been categorized via differences in final grade performance, the day-to-day experiences of minoritized student populations may not be accounted for when only concentrating on final grade outcomes. However, more fine-grained information on student behavior analyzed using AI and machine learning techniques may help to highlight the differences in day-to-day experiences. This study explores how linguistic features related to exclusion and social dynamics vary across discussion forum structures and how the variation depends on race and gender. We applied linear mixed-effect analysis to discussion posts across six semesters to investigate the effect of discussion forum structure, race, and gender on linguistic features. These results can be used to suggest design changes to instructors’ online discussion forums that will support students in feeling included. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Psychomotor learning is an emerging research direction in the AIED (Artificial Intelligence in Education) field. This topic was introduced in the AIED research agenda back in 2016 in a contribution at the International Journal of AIED, where the SMDD (Sensing-Modelling-Designing-Delivering) process model to develop AIED psychomotor systems was introduced. Recently, a systematic review of the state of the art on this topic has also been published in the novel Handbook of AIED. In this context, the aim of the IPAIEDS tutorial is to motivate the AIED community to research on intelligent psychomotor systems and give tools to design, build and evaluate this kind of systems. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Analyzing instructional videos via computer vision and machine learning holds promise for several tasks, such as assessing teacher performance and classroom climate, evaluating student engagement, and identifying racial bias in instruction. The traditional way of evaluating instructional videos depends on manual observation with human raters, which is time-consuming and requires a trained labor force. Therefore, this paper tests several deep network architectures in the automation of instruc- tional video analysis, where the networks are tailored to recognize classroom activity. Our experimental setup includes a set of 250 hours of primary and middle school videos that are annotated by expert human raters. We present several strategies to handle varying length of instructional activities, a major challenge in the detection of instructional activity. Based on the proposed strategies, we enhance and compare different deep networks for detecting instructional activity.

Faith-based organizations provide a variety of supplemental programs to address social, economic, and political issues that negatively impact marginalized communities. In this experience report, we engage Black women employed at a faith-based organization, as experts and collaborators, in creating an equitable learning environment to accommodate the computing education needs of Black students who live in an under-resourced rural community. Leveraging Black feminist thought, we afford these Black women, who are new to computing education, an opportunity to develop their block style programming skills using Scratch. Combining our areas of expertise, we develop learning materials that affirm the racial identity of Black elementary students, contributing to the development of the faith-based organization's informal computing education program. © 2023 IEEE.

Engagement is critical to satisfaction and performance in a number of domains but is challenging to measure and sustain. Thus, there is considerable interest in developing affective computing technologies to automatically measure and enhance engagement, especially in the wild and at scale. This article provides an accessible introduction to affective computing research on engagement detection and enhancement using educational applications as an application domain. We begin with defining engagement as a multicomponential construct (i.e., a conceptual entity) situated within a context and bounded by time and review how the past six years of research has conceptualized it. Next, we examine traditional and affective computing methods for measuring engagement and discuss their relative strengths and limitations. Then, we move to a review of proactive and reactive approaches to enhancing engagement toward improving the learning experience and outcomes. We underscore key concerns in engagement measurement and enhancement, especially in digitally enhanced learning contexts, and conclude with several open questions and promising opportunities for future work. © 1963-2012 IEEE.

Background: Storybooks are an effective tool for teaching complex scientific mechanisms to young children when presented in child-friendly, joint-attentional contexts like read-aloud sessions. However, static storybooks are limited in their ability to convey change across time and, relative to animated storybooks, are harder to disseminate to a wide audience. This study examined second graders’ abilities to learn the deeply counterintuitive concepts of adaptation and speciation from multi-day interventions centered around two storybooks about natural selection that were either read-aloud (static) or watched on a screen (animated). The storybook sequence was progressive and first explained—in counter-essentialist and non-teleological terms—how the relative distribution of a terrestrial mammal’s trait changed over time due to behavioral shifts in their primary food resource (adaptation, book 1). It then explained how–after a sub-population of this species became geographically isolated–they evolved into an entirely different aquatic species over many generations via selection on multiple foraging-relevant traits (speciation, book 2). The animated and static versions of the storybooks used the same text and illustrations, but while the animations lacked joint-attentional context, they more dynamically depicted successive reproductive generations. Storybook and animation presentations were interspersed with five parallel talk-aloud assessment interviews over three days. Results: Findings revealed substantial learning from the read-aloud static storybook sequence. They also revealed substantial learning from the animation condition with patterns suggesting that the dynamic representations of change over time particularly scaffolded acquisition of the deeply counterintuitive idea that a species can evolve into an entirely different category of species by natural selection. Conclusions: The results provide much-needed optimism in a context of increasing demands for scalable solutions to promote effective learning: animated storybooks are just as good (and may even be better) than static storybooks. © 2023, The Author(s).