An official website of the United States government
Abstract Tracking students’ learning states to provide tailored learner support is a critical element of an adaptive learning system. This study explores how an automatic assessment is capable of tracking learners’ cognitive and emotional states during virtual reality (VR)‐based representational‐flexibility training. This VR‐based training program aims to promote the flexibility of adolescents with autism spectrum disorder (ASD) in interpreting, selecting and creating multimodal representations during STEM‐related design problem solving. For the automatic assessment, we used both natural language processing (NLP) and machine‐learning techniques to develop a multi‐label classification model. We then trained the model with the data from a total of audio‐ and video‐recorded 66 training sessions of four adolescents with ASD. To validate the model, we implemented both k‐fold cross‐validations and the manual evaluations by expert reviewers. The study finding suggests the feasibility of implementing the NLP and machine‐learning driven automatic assessment to track and assess the cognitive and emotional states of individuals with ASD during VR‐based flexibility training. The study finding also denotes the importance and viability of providing adaptive supports to maintain learners’ cognitive and affective engagement in a highly interactive digital learning environment.
more »
« less
How Does Augmented Observation Facilitate Multimodal Representational Thinking? Applying Deep Learning to Decode Complex Student Construct
In this paper, we demonstrate how machine learning could be used to quickly assess a student’s multimodal representational thinking. Multimodal representational thinking is the complex construct that encodes how students form conceptual, perceptual, graphical, or mathematical symbols in their mind. The augmented reality (AR) technology is adopted to diversify student’s representations. The AR technology utilized a low-cost, high-resolution thermal camera attached to a smartphone which allows students to explore the unseen world of thermodynamics. Ninth-grade students (N= 314) engaged in a prediction–observation–explanation (POE) inquiry cycle scaffolded to leverage the augmented observation provided by the aforementioned device. The objective is to investigate how machine learning could expedite the automated assessment of multimodal representational thinking of heat energy. Two automated text classification methods were adopted to decode different mental representations students used to explain their haptic perception, thermal imaging, and graph data collected in the lab. Since current automated assessment in science education rarely considers multilabel classification, we resorted to the help of the state-of-the-art deep learning technique—bidirectional encoder representations from transformers (BERT). The BERT model classified open-ended responses into appropriate categories with higher precision than the traditional machine learning method. The satisfactory accuracy of deep learning in assigning multiple labels is revolutionary in processing qualitative data. The complex student construct, such as multimodal representational thinking, is rarely mutually exclusive. The study avails a convenient technique to analyze qualitative data that does not satisfy the mutual-exclusiveness assumption. Implications and future studies are discussed.
more »
« less
- PAR ID:
- 10192388
- Date Published:
- Journal Name:
- Journal of Science Education and Technology
- ISSN:
- 1059-0145
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Augmented reality (AR) has the potential to fundamentally transform science education by making learning of abstract science ideas tangible and engaging. However, little is known about how students interacted with AR technologies and how these interactions may affect learning performance in science laboratories. This study examined high school students’ navigation patterns and science learning with a mobile AR technology, developed by the research team, in laboratory settings. The AR technology allows students to conduct hands-on laboratory experiments and interactively explore various science phenomena covering biology, chemistry, and physics concepts. In this study, seventy ninth-grade students carried out science laboratory experiments in pairs to learn thermodynamics. Our cluster analysis identified two groups of students, which differed significantly in navigation length and breadth. The two groups demonstrated unique navigation patterns that revealed students’ various ways of observing, describing, exploring, and evaluating science phenomena. These navigation patterns were associated with learning performance as measured by scores on lab reports. The results suggested the need for providing access to multiple representations and different types of interactions with these representations to support effective science learning as well as designing representations and connections between representations to cultivate scientific reasoning skills and nuanced understanding of scientific processes.more » « less
-
null (Ed.)Augmented reality (AR) applications are growing in popularity in educational settings. While the effects of AR experiences on learning have been widely studied, there is relatively less research on understanding the impact of AR on the dynamics of co-located collaborative learning, specifically in the context of novices programming robots. Educational robotics are a powerful learning context because they engage students with problem solving, critical thinking, STEM (Science, Technology, Engineering, Mathematics) concepts, and collaboration skills. However, such collaborations can suffer due to students having unequal access to resources or dominant peers. In this research we investigate how augmented reality impacts learning and collaboration while peers engage in robot programming activities. We use a mixed methods approach to measure how participants are learning, manipulating resources, and engaging in problem solving activities with peers. We investigate how these behaviors are impacted by the presence of augmented reality visualizations, and by participants? proximity to resources. We find that augmented reality improved overall group learning and collaboration. Detailed analysis shows that AR strongly helps one participant more than the other, by improving their ability to learn and contribute while remaining engaged with the robot. Furthermore, augmented reality helps both participants maintain a common ground and balance contributions during problem solving activities. We discuss the implications of these results for designing AR and non-AR collaborative interfaces.more » « less
-
Educational video games can engage students in authentic STEM practices, which often involve visual representations. In particular, because most interactions within video games are mediated through visual representations, video games provide opportunities for students to experience disciplinary practices with visual representations. Prior research on learning with visual representations in non-game contexts suggests that visual representations may confuse students if they lack prerequisite representational-competencies. However, it is unclear how this research applies to game environments. To address this gap, we investigated the role of representational-competencies for students’ learning from video games. We first conducted a single-case study of a high-performing undergraduate student playing an astronomy game as an assignment in an astronomy course. We found that this student had difficulties making sense of the visual representations in the game. We interpret these difficulties as indicating a lack of representational-competencies. Further, these difficulties seemed to lead to the student’s inability to relate the game experiences to the content covered in his astronomy course. A second study investigated whether interventions that have proven successful in structured learning environments to support representational-competencies would enhance students’ learning from visual representations in the video game. We randomly assigned 45 students enrolled in an undergraduate course to two conditions. Students either received representational-competency support while playing the astronomy game or they did not receive this support. Results showed no effects of representational-competency supports. This suggests that instructional designs that are effective for representational-competency supports in structured learning environments may not be effective for educational video games. We discuss implications for future research, for designers of educational games, and for educators.more » « less
-
Previous research has established that embodied modeling (role-playing agents in a system) can support learning about complexity. Separately, research has demonstrated that increasing the multimodal resources available to students can support sensemaking, particularly for students classified as English Learners. This study bridges these two bodies of research to consider how embodied models can strengthen an interconnected system of multimodal models created by a classroom. We explore how iteratively refining embodied modeling activities strengthened connections to other models, real-world phenomena, and multimodal representations. Through design-based research in a sixth grade classroom studying ecosystems, we refined embodied modeling activities initially conceived as supports for computational thinking and modeling. Across three iterative cycles, we illustrate how the conceptual and epistemic relationship between the computational and embodied model shifted, and we analyze how these shifts shaped opportunities for learning and participation by: (1) recognizing each student’s perspectives as critical for making sense of the model, (2) encouraging students to question and modify the “code” for the model, and (3) leveraging multimodal resources, including graphs, gestures, and student-generated language, for meaning-making. Through these shifts, the embodied model became a full-fledged component of the classroom’s model system and created more equitable opportunities for learning and participation.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1007/s10956-020-09856-2
