An official website of the United States government
As demand grows for job-ready data science professionals, there is increasing recognition that traditional training often falls short in cultivating the higher-order reasoning and real-world problem-solving skills essential to the field. A foundational step toward addressing this gap is the identification and organization of knowledge components (KCs) that underlie data science problem solving (DSPS). KCs represent conditional knowledge—knowing about appropriate actions given particular contexts or conditions—and correspond to the critical decisions data scientists must make throughout the problem-solving process. While existing taxonomies in data science education support curriculum development, they often lack the granularity and focus needed to support the assessment and development of DSPS skills. In this paper, we present a novel framework that combines the strengths of large language models (LLMs) and human expertise to identify, define, and organize KCs specific to DSPS. We treat LLMs as ``knowledge engineering assistants" capable of generating candidate KCs by drawing on their extensive training data, which includes a vast amount of domain knowledge and diverse sets of real-world DSPS cases. Our process involves prompting multiple LLMs to generate decision points, synthesizing and refining KC definitions across models, and using sentence-embedding models to infer the underlying structure of the resulting taxonomy. Human experts then review and iteratively refine the taxonomy to ensure validity. This human-AI collaborative workflow offers a scalable and efficient proof-of-concept for LLM-assisted knowledge engineering. The resulting KC taxonomy lays the groundwork for developing fine-grained assessment tools and adaptive learning systems that support deliberate practice in DSPS. Furthermore, the framework illustrates the potential of LLMs not just as content generators but as partners in structuring domain knowledge to inform instructional design. Future work will involve extending the framework by generating a directed graph of KCs based on their input-output dependencies and validating the taxonomy through expert consensus and learner studies. This approach contributes to both the practical advancement of DSPS coaching in data science education and the broader methodological toolkit for AI-supported knowledge engineering.
more »
« less
This content will become publicly available on March 1, 2026
Haptic Technology Interaction Framework in Engineering Learning: A Taxonomical Conceptualization
ABSTRACT Innovative technology helps students foster creative thinking and problem‐solving abilities by augmenting human sensing and enriching input and output information. New technology can incorporate haptic sensing features—a sensing modality for user operations. Learning with haptic sensing features promises new ways to master cognitive and motor skills and higher‐order cognitive reasoning tasks (e.g., decision‐making and problem‐solving). This study conceptualizes haptic technology within the human‐technology interaction (HTI) framework. It aims to investigate the components of haptic systems to define their impact on learning and facilitate understanding of haptic technology, including application development to ease entry barriers for educators. The research builds a haptic HTI framework based on a systematic literature review on haptic applications in engineering learning over the last two decades. The review utilizes the SALSA methodology to analyze relevant studies comprehensively. The framework outcome is a haptic HTI taxonomy to build visual representations of the explicit connection between the taxonomy components and practical educational applications (by means of heatmaps). The approach led to a robust conceptualization of HTI into a taxonomy—a structured framework encompassing categories for interaction modalities, immersive technologies, and learning methodologies in engineering education. The model assists in understanding how haptic feedback can be utilized in learning with technology experiences. Applying haptic technology in engineering education includes mastering fundamental science concepts and creating customized haptic prototypes for engineering processes. A growing trend focuses on wearable haptics, such as gloves and vests, which involve kinesthetic movement, fine motor skills, and spatial awareness—all fostering spatial and temporal cognitive abilities (the ability to effectively manage and comprehend significant amounts ofspatial(how design components or resources are related to one another in the 3D space) andtemporal(the logic in a process, such as the order, sequences, and hierarchies of the resources information). The haptic human‐technology interaction (H‐HTI) framework guides future research in developing cognitive reasoning through H‐HTI, unlocking new frontiers in engineering education.
more »
« less
- Award ID(s):
- 2044444
- PAR ID:
- 10584096
- Editor(s):
- Iskander, Magdy F
- Publisher / Repository:
- Wiley
- Date Published:
- Journal Name:
- Computer Applications in Engineering Education
- Volume:
- 33
- Issue:
- 2
- ISSN:
- 1061-3773
- Subject(s) / Keyword(s):
- engineering education haptic feedback haptics haptic‐technology human‐technology interaction
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Embodied Interaction (EI) offers unique opportunities to uncover novel ways to achieve experiential learning whilst keeping students stimulated and engaged. Spatial abilities have been repeatedly demonstrated as a success predictor for educations and professions in Science, Technology, Engineering and Mathematics. However, many researchers argue that training and assessment of this pertinent reasoning skill is vastly underrepresented in the school curriculum. This paper presents TetRotation, a PhD centred on how affordances coming from Multimodal Analytics can be coupled with EI to nurture Mental Rotation (MR) skills. The overarching objectives of the project are two fold. First, the TetRotation Interaction Design study will highlight best practices identified through the assessment of efficiency, level of engagement and learning gains achieved when using gesture based EI to solve MR tasks. Next, in the TetRotation Game study, these design practices will guide the implementation of an interactive serious game purposed to support the development of MR skills. This research relies on mixed method techniques, including data collections from users' actions, like motion sensing, EEG, gaze tracking, video-recordings, click streams, interviews and surveys.more » « less
-
null (Ed.)Spatial reasoning skills contribute to performance in many STEM fields. For example, drawing sectional views of three-dimensional objects is an essential skill for engineering students. There is considerable variation in the spatial reasoning skills of prospective engineering students, putting some at risk for compromised performance in their classes. This study takes place in a first-year engineering Spatial Visualization course to integrate recent practices in engineering design education with cognitive psychology research on the nature of spatial learning. We employed three main pedagogical strategies in the course - 1) in class instruction on sketching; 2) spatial visualization training; and 3) manipulation of physical objects (CAD/3D print creations). This course endeavors to use current technology, online accessibility, and implementation of the three pedagogical strategies to bring about student growth in spatial reasoning. This study is designed to determine the effect of adding two different spatial reasoning training apps to this environment. Over 230 students (three sections) participated in our study. In two of the three sections, students received interactive spatial visualization training using either a spatial visualization mobile touchscreen app in one section or an Augmented Reality (AR) app in the other section. Research suggests that there are benefits to using the Spatial Vis Classroom mobile app for college students.The app has been shown to increase student persistence resulting in large learning gains as measured by the Purdue assessment of spatial visualization (PSVT-R), especially for students starting with poor spatial visualization skills. The Spatial Vis Classroom app can be used in the classroom or assigned as homework. The AR app is designed to help users develop their mental rotation abilities. It is designed to support a holistic understanding of 3-dimensional objects, and research has shown that, in combination with a traditional curriculum, it increases students’ abilities also measured by the PSVT-R. Of particular interest, the data suggest that the app overcomes the advantage found by males over females in a traditional class alone focused on spatial reasoning. Both of the course sections were required to use the apps for approximately the same time in class and outside of class. Students in the control section were required to do hand sketching activities in class and outside of class, with roughly the same completion time as for the sections with the apps. Students grades were not affected by using the three different approaches as grading was based on completion only. Based on current literature, we hypothesize that overall benefits (PSVT-R gains) will be comparable across the 3 treatments but there will be different effects on attitude and engagement (confidence,enjoyment, and self-efficacy). Lastly, we hypothesize that the treatments will have different effects on male/female and ethnic categories of the study participants. The final paper will include an analysis of results and a report of the findings.more » « less
-
This research paper details a study investigating spatial visualization skills relation to design problem-solving for undergraduate engineering students. Design is outlined as one of the seven attributes that engineering students must demonstrate prior to their graduation as set out through the ABET guidelines. It is important to understand the factors that contribute to design capability to achieve this learning goal. Design problems by their nature are cognitive tasks and as such require problem solvers to draw both on learned knowledge and pertinent cognitive abilities for their solution. In the context of engineering design problem solving, spatial visualization is one such cognitive ability that likely plays a role. Previous research has demonstrated a link between spatial visualization and design. This work aims to advance on that research by exploring how spatial visualization relates to the design process enacted by undergraduate engineering students. There were two phases to data collection for this research. In the first phase, 127 undergraduate engineering students completed four spatial tests. In the second phase, 17 students returned to complete three design tasks. This paper will focus on one of these design tasks, the Ping Pong problem where individuals are asked to design a ping pong launcher to hit a target from a given distance at a specific height. A purposive sample of 9 first-year and 8 senior students were selected to engage in a think aloud protocol during the problemsolving task based on their spatial visualization skill levels (high vs. low). The think aloud protocol was used to assign pre-defined codes for design activity for each of the 17 participants. Through analysis of these codes, results indicated that there is an association between the spatial skills of students and the design processes/actions that they employ. These insights will be discussed relative to their potential influence on engineering education, specifically in developing design capability.more » « less
-
This research paper describes work performed at a large midwestern university in the U.S. examining the link between spatial skills and design performance. Spatial skills are vital to success in engineering education and their relation to efficient problem-solving is wellresearched. This study is part of a larger project focusing on understanding the link between spatial visualization skills and solving engineering design problems. In the current study, we made use of an eye-tracking device to determine the visual focus of participants while they solved an assigned design task. High and low spatial visualizers in undergraduate engineering were identified through Phase I testing. In Phase 1, students completed four widely accepted spatial ability tests. Subsequently, some students were invited to participate in a Phase 2 design problem-solving activity wearing the Tobii Pro Glasses 3 to collect eye tracking data to gain insight into the design problem-solving behaviors based on information collected about participants’ eye movement fixations (i.e. duration and location). In this paper, we report on the analysis conducted through Tobii Pro Lab research software involving 13 study participants of whom 7 (1 female, 6 male: 3 first-year, 4 senior-year) were high spatial visualizers while 6 (3 female, 3 male; 4 first-year, 2 senior-year) were low spatial visualizers. Findings from the study suggest that the solutions produced by the high visualizers were more graphical compared to low visualizers. Low visualizers focused more on the problem statement, spending more time reading it and coming back to it compared to high visualizers who remained in the problem solution area for most of the problem-solving session. Recognizing the importance of spatial abilities in design problem-solving, educators can incorporate activities and exercises aimed at developing spatial skills among students which could include spatial reasoning tasks, visualization exercises, and hands-on design projects.more » « less
