In digital learning systems, gaming the system refers to occasions when students attempt to succeed in an educational task by systematically taking advantage of system features rather than engaging meaningfully with the content. Often viewed as a form of behavioral disengagement, gaming the system is negatively associated with short- and long-term learning outcomes. However, little research has explored this phenomenon beyond its behavioral representation, leaving questions such as whether students are cognitively disengaged or whether they engage in different self-regulated learning (SRL) strategies when gaming largely unanswered. This study employs a mixed-methods approach to examine students’ cognitive engagement and SRL processes during gaming versus non-gaming periods, using utterance length and SRL codes inferred from think-aloud protocols collected while students interacted with an intelligent tutoring system for chemistry. We found that gaming does not simply reflect a lack of cognitive effort; during gaming, students often produced longer utterances, were more likely to engage in processing information and realizing errors, but less likely to engage in planning, and exhibited reactive rather than proactive self-regulatory strategies. These findings provide empirical evidence supporting the interpretation that gaming may represent a maladaptive form of SRL. With this understanding, future work can address gaming and its negative impacts by designing systems that target maladaptive self-regulation to promote better learning.

This experience report describes a partnership between community college faculty and learning scientists to co-design Intelligent Tutoring Systems (ITSs) addressing challenges in cybersecurity workforce training. Our co-design approach combined collaborative reflection on student difficulties from prior course offerings with systematic curricular analysis to identify high-impact intervention points. We targeted two challenge areas: strengthening students' ability to contrast key cybersecurity taxonomies, and providing realistic hands-on training without costly infrastructure. The resulting ITSs include: one employing exercises that scaffold comparison of conceptual categories, and another using lightweight simulations to provide experiential learning while circumventing typical cost and time overhead. Both systems incorporate instructional principles grounded in learning science research, including evidence-based features associated with ITS efficacy such as timely hints and feedback. Through iterative classroom deployment and refinement—including adding task-loop adaptivity to offer repeated practice until mastery—we observed encouraging learning outcomes, alongside insights into mitigating ''gaming the system'' behaviors. We detail our co-design process and formative evaluations—procedures, outcomes, and cautious interpretation due to the limited number of consented learners—and share lessons learned to inform scalable ITS development for cybersecurity workforce training in resource-constrained settings.

There is currently significant demand for training in how to use metals additive manufacturing (AM) machines. Such training is important not only for the technicians who run and maintain the machines, but also for engineers and strategic decision makers who need to support AM part fabrication. Furthermore, there are a variety of AM machines, each with different details to be learned and potential hazards to overcome, and it is difficult to train more than a handful of users at one time. To address these challenges, a prototype training system has been developed, the AM Training Tutor, which uses interactive virtual reality (VR) to train users on a specific AM machine - the EOS M290. To make the training technology more widely available and expand its use across a variety of different AM machines, efforts are underway to develop a modularized and generic version of the AM Training Tutor that can be customized with relatively little effort to train users to operate other AM machines. This work-in-progress paper details the progress to-date, challenges and proposed solutions with the aim to demonstrate how standalone VR-based training systems can be redesigned for relatively easy repurposing and generalization.

How do the features of a learning environment's user interface impact learners' agency and, further, their learning? We explored this question in the context of Decimal Point, a digital learning game designed to support middle school students in learning decimals. Previous studies of the game showed that giving students the ability to choose the order and number of mini-games to play did not significantly impact their learning outcomes compared to a condition without choice. In this paper we explore whether some elements of the game's interface may have inadvertently exerted indirect control over students' choice, leading to the previous effects. We conducted a classroom study using a new version of the game that varied whether students saw a visual path connecting mini-games on the game map to modulate the level of indirect control students would experience with an implied ordering. Ultimately, we found that students in the no-line condition exercised significantly more agency but did not learn any less than the line condition. These results suggest that indirect control can be a subtle but powerful way to direct student attention in digital learning games.

When used in classrooms, personalized learning software allows students to work at their own pace, while freeing up the teacher to spend more time working one-on-one with students. Yet such personalized classrooms also pose unique challenges for teachers, who are tasked with monitoring classes working on divergent activities, and prioritizing help-giving in the face of limited time. This paper reports on the co-design, implementation, and evaluation of a wearable classroom orchestration tool for K-12 teachers: mixed-reality smart glasses that augment teachers' realtime perceptions of their students' learning, metacognition, and behavior, while students work with personalized learning software. The main contributions are: (1) the first exploration of the use of smart glasses to support orchestration of personalized classrooms, yielding design findings that may inform future work on real-time orchestration tools; (2) Replay Enactments: a new prototyping method for real-time orchestration tools; and (3) an in-lab evaluation and classroom pilot using a prototype of teacher smart glasses (Lumilo), with early findings suggesting that Lumilo can direct teachers' time to students who may need it most.

Intelligent tutoring systems (ITSs) are commonly designed to enhance student learning. However, they are not typically designed to meet the needs of teachers who use them in their classrooms. ITSs generate a wealth of analytics about student learning and behavior, opening a rich design space for real-time teacher support tools such as dashboards. Whereas real-time dashboards for teachers have become popular with many learning technologies, we are not aware of projects that have designed dashboards for ITSs based on a broad investigation of teachers' needs. We conducted design interviews with ten middle school math teachers to explore their needs for on-the-spot support during blended class sessions, as a first step in a user-centered design process of a real-time dashboard. Based on multi-methods analyses of this interview data, we identify several opportunities for ITSs to better support teachers' needs, noting that the analytics commonly generated by existing teacher support tools do not strongly align with the analytics teachers expect to be most useful. We highlight key tensions and tradeoffs in the design of such real-time supports for teachers, as revealed by "Speed Dating" possible futures with teachers. This paper has implications for our ongoing co-design of a real-time dashboard for ITSs, as well as broader implications for the design of ITSs that can effectively collaborate with teachers in classroom settings.

Classroom experiments that evaluate the effectiveness of educational technologies do not typically examine the effects of classroom contextual variables (e.g., out-of-software help-giving and external distractions). Yet these variables may influence students' instructional outcomes. In this paper, we introduce the Spatial Classroom Log Explorer (SPACLE): a prototype tool that facilitates the rapid discovery of relationships between within-software and out-of-software events. Unlike previous tools for retrospective analysis, SPACLE replays moment-by-moment analytics about student and teacher behaviors in their original spatial context. We present a data analysis workflow using SPACLE and demonstrate how this workflow can support causal discovery. We share the results of our initial replay analyses using SPACLE, which highlight the importance of considering spatial factors in the classroom when analyzing ITS log data. We also present the results of an investigation into the effects of student-teacher interactions on student learning in K-12 blended classrooms, using our workflow, which combines replay analysis with SPACLE and causal modeling. Our findings suggest that students' awareness of being monitored by their teachers may promote learning, and that "gaming the system" behaviors may extend outside of educational software use.

This study examines how accurately individual student differences in learning can be predicted from prior student learning activities. Bayesian Knowledge Tracing (BKT) predicts learner performance well and has often been employed to implement cognitive mastery. Standard BKT individualizes parameter estimates for knowledge components, but not for learners. Studies have shown that individualizing parameters for learners improves the quality of BKT fits and can lead to very different (and potentially better) practice recommendations. These studies typically derive best-fitting individualized learner parameters from learner performance in existing data logs, making the methods difficult to deploy in actual tutor use. In this work, we examine how well BKT parameters in a tutor lesson can be individualized based on learners' prior performance in reading instructional text, taking a pretest, and completing an earlier tutor lesson. We find that best-fitting individual difference estimates do not directly transfer well from one tutor lesson to another, but that predictive models incorporating variables extracted from prior reading, pretest and tutor activities perform well, when compared to a standard BKT model and a model with best-fitting individualized parameter estimates.

How much assistance should be provided to students as they learn with educational technology? Providing help allows students to proceed when struggling, yet can depress their motivation to learn independently. Assistance withholding encourages students to learn for themselves, yet can also lead to frustration. The web-based inquiry-learning program, Voyage to Galapagos (VTG), helps students “follow” the steps of Darwin through a simulation of the Galapagos Island. Students explore the islands, take pictures of animals, evaluate their characteristics and behavior, and use scientific methodology to “discover” evolution. A preliminary study with 48 middle school students examined three levels of assistance: (1) no support, (2) error flagging, text feedback on errors, and hints, and (3) pre-emptive hints with error flagging, error feedback, and hints. The results indicate that higher performing students gainfully use the program’s support more frequently than lower performing students, those who arguably have a greater need for it. We conjecture that this could be a product of the current program only providing an early phase of the learning process and also that higher performers generally are better at asking for help. Lower performers may benefit at later phases of work, which we will test in a future study.

Given a renewed interest in the field of AI and Law in more complex factual representations of legal cases in terms of narratives, techniques for representing and reasoning about temporal orderings of facts will become increasingly important. The SIROCCO (System for Intelligent Retrieval of Operationalized Cases and COdes) program employed a representation for the temporal ordering of events in ethics cases in a way that informed determinations of whether and how ethical norms were violated and if the problem and other cases were normatively analogous at a deeper level. At the same time, the program supported ordinary case enterers in translating the facts of textually described cases into a machine-processable representation. This paper presents these previously unpublished aspects of the work including a report of an empirical evaluation of the contribution of the temporal representation to the program's success in retrieving relevant norms and cases. Although the results were negative, a consideration of the reasons why is illuminating. While SIROCCO dealt with engineering ethics cases, it is clear that similar temporal considerations apply in legal cases and that the approach is likely to be useful in legal narrative representations.

This paper describes the development and evaluation of a Bayesian network model of student misconceptions in the domain of decimals. The Bayesian model supports a remote adaptation service for an intelligent t utoring system within a project focused on adaptively presenting erroneous examples to students. We have evaluated the accuracy of the student model by comparing its predictions to the outcomes of the interactions of 255 students with the software. Student s’ logs were used for retrospective training of the Bayesian network parameters. The accuracy of the student model was evaluated from three different perspectives: its ability to predict the outcome of an individual student’s answer, the correctness of the answer, and the presence of a particular misconception. The results show that the model is capable of producing predictions of high accuracy (up to 87%).

Computer-mediated environments provide an arena for learning to argue. We investigate to what extent student dyads’ online argumentation can be facilitated with collaboration scripts that (1) prompt learners to prepare individually, (2) create conflict, and (3) encourage productive collaboration and argumentation. A process analysis of the chats of the dyads showed that the scripted treatment group used significantly more words and broadened and deepened their discussions significantly more than the unscripted group. Qualitative analysis indicates that scripted learners engaged in more critical and objective argumentation than non-scripted learners.

In this paper, we discuss how Artificial Intelligence (AI) techniques might be brought to bear in automatically recognizing “creative reasoning” in student e-discussions. An AI-based graph-matching algorithm was used to find instances of deepening and widening, interactional categories that provide evidence of, respectively, explicit argumentation and creative reasoning. A deepening occurs when students provide further argumentation for an on-going perspective. A widening occurs, on the other hand, when a student (or students) attempts to diverge from the current perspective by either questioning it or presenting a new perspective or new idea. Given examples of deepening and widening from real e-discussions, the AI algorithm was able to successfully find similar events within new e-discussions and did so within realistic run-time expectations. Our ultimate aim is to provide a software tool for teachers that will support them in recognizing a range of important dialogic aspects of student e-discussions, such as deepening and widening.

In this paper, we discuss design considerations and our plans to develop a generalized framework for intelligent support in educational argumentation systems. Our goal is to develop a framework that will support the development of argumentation learning systems across a variety of domains (e.g., the law, ethics).

Supporting students in the acquisition of argumentation skills is an important goal of educational technology. However, there has not been much work done towards developing generic and reusable software architectures for collaborative argumentation that could reduce the development time for distributed argumentation learning systems. Based on a survey of more than 50 different argumentation systems, this paper presents a requirements analysis for a generic collaborative intelligent tutoring system for argumentation.

Intelligent Tutoring Systems (ITS) can both help improve student learning and serve as useful platforms for experiments in learning science [1,2]. But the difficulty of building or customizing ITSs has hindered their acceptance among educators and researchers [3]. The Cognitive Tutor Authoring Tools (CTAT) project aims to provide a suite of authoring tools that make tutor development more affordable by leveraging human-computer interaction and artificial intelligence techniques. Previous efforts on CTAT added the capability for nonprogrammers to create exampletracing tutors via a programming-by-demonstration technique that requires no coding [4]. While exampletracing tutors provide a student experience similar to that of the more general cognitive tutors, they also require that an author demonstrate and fully annotate each individual problem to be presented.

This paper describes how we used an AI model for retrieving ethics cases to investigate empirically the epistemological contributions of a decision-makers' citing cases and code provisions in justifying decisions. In practical ethics, like law, it is impossible to define abstract principles intensionally so that they may be applied deductively. After investigating hundreds of professional ethics case opinions, we hypothesized that the decision-makers' explanations extensionally defined principles over time, in effect, operationalizing them. We constructed SIROCCO, a system for retrieving principles and past ethics cases. We used this computational model to conduct an ablation experiment concerning a core set of operationalization techniques. This paper presents empirical evidence that the operationalization information supports predictions of the relevant principles and past cases more accurately than competing approaches that do not use such information.

Article Context sensitive case comparisons in practical ethics: reasoning about reasons Share on Authors: Bruce M. McLaren University of Pittsburgh, Intelligent Systems Program, Pittsburgh, Pennsylvania University of Pittsburgh, Intelligent Systems Program, Pittsburgh, PennsylvaniaView Profile , Kevin D. Ashley University of Pittsburgh, Intelligent Systems Program, Pittsburgh, Pennsylvania University of Pittsburgh, Intelligent Systems Program, Pittsburgh, PennsylvaniaView Profile Authors Info & Claims ICAIL '95: Proceedings of the 5th international conference on Artificial intelligence and lawMay 1995 Pages 316–325https://doi.org/10.1145/222092.222266Online:24 May 1995Publication History 5citation324DownloadsMetricsTotal Citations5Total Downloads324Last 12 Months3Last 6 weeks0 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access