More Like this

1. DesignWeaver: Dimensional Scaffolding for Text-to-Image Product Design

   https://doi.org/10.1145/3706598.3714211  

   Tao, Sirui; Liang, Ivan; Peng, Cindy; Wang, Zhiqing; Palani, Srishti; Dow, Steven P (April 2025, ACM)

   Generative AI has enabled novice designers to quickly create professional-looking visual representations for product concepts. However, novices have limited domain knowledge that could constrain their ability to write prompts that effectively explore a product design space. To understand how experts explore and communicate about design spaces, we conducted a formative study with 12 experienced product designers and found that experts — and their less-versed clients — often use visual references to guide co-design discussions rather than written descriptions. These insights inspired DesignWeaver, an interface that helps novices generate prompts for a text-to-image model by surfacing key product design dimensions from generated images into a palette for quick selection. In a study with 52 novices, DesignWeaver enabled participants to craft longer prompts with more domain-specific vocabularies, resulting in more diverse, innovative product designs. However, the nuanced prompts heightened participants’ expectations beyond what current text-to-image models could deliver. We discuss implications for AI-based product design support tools. 

   more » « less
2. Characterizing Variability in Shared Meaning through Millions of Sketches

   https://doi.org/10.31234/osf.io/p4s7d  

   Lewis, M.; Balamurugan, A.; Zheng, B.; & Lupyan, G. (July 2021, Proceedings of the Annual Meeting of the Cognitive Science Society)

   null (Ed.)

   The study of mental representations of concepts has histori- cally focused on the representations of the “average” person. Here, we shift away from this aggregate view and examine the principles of variability across people in conceptual rep- resentations. Using a database of millions of sketches by peo- ple worldwide, we ask what predicts whether people converge or diverge in their representations of a specific concept, and which kinds of concepts tend to be more or less variable. We find that larger and more dense populations tend to have less variable representations, and concepts high in valence and arousal tend to be less variable across people. Further, two countries tend to have people with more similar conceptual representations when they are linguistically, geographically, and culturally similar. Our work provides the first characteri- zation of the principles of variability in shared meaning across a large, diverse sample of participants. 

   more » « less
3. Enhancing conceptual knowledge in early algebra through scaffolding diagrammatic self-explanation

   Nagashima, T. (January 2020, 14th International Conference of the Learning Sciences (ICLS) 2020)

   Many studies have shown that visual representations can enhance student understanding of STEM concepts. However, prior research suggests that visual representations alone are not necessarily effective across a broad range of students. To address this problem, we created a novel, scaffolded form of diagrammatic self-explanation in which students explain their problem-solving steps in the form of diagrams. We used contrasting cases to support students’ sense-making between algebraic equations and diagrams in the self-explanation activity. We conducted a classroom experiment with 41 students in grades 5 and 6 to test the effectiveness of this strategy when embedded in an Intelligent Tutoring System for algebra. We found that scaffolded diagrammatic self-explanation enhanced conceptual knowledge for students who did not have prior knowledge of formal equation-solving strategies. The study is the first experimental study showing that visual representations can enhance conceptual knowledge in early algebra. 

   more » « less
4. Enhancing Conceptual Knowledge in Early Algebra Through Scaffolding Diagrammatic Self-explanation

   Nagashima, T; Bartel, A.; Silla, E.; Vest, N.; Alibali, M.; Aleven, V. (January 2020, The Interdisciplinarity of the Learning Sciences, 14th International Conference of the Learning Sciences (ICLS) 2020)

   Gresalfi, M.; Horn, I. S. (Ed.)

   Many studies have shown that visual representations can enhance student understanding of STEM concepts. However, prior research suggests that visual representations alone are not necessarily effective across a broad range of students. To address this problem, we created a novel, scaffolded form of diagrammatic self-explanation in which students explain their problem-solving steps in the form of diagrams. We used contrasting cases to support students’ sense-making between algebraic equations and diagrams in the self-explanation activity. We conducted a classroom experiment with 41 students in grades 5 and 6 to test the effectiveness of this strategy when embedded in an Intelligent Tutoring System for algebra. We found that scaffolded diagrammatic self-explanation enhanced conceptual knowledge for students who did not have prior knowledge of formal equation-solving strategies. The study is the first experimental study showing that visual representations can enhance conceptual knowledge in early algebra. 

   more » « less
5. Quantifying the qualitative: exploring epistemic network analysis as a method to study work system interactions

   https://doi.org/10.1080/00140139.2022.2051609  

   Weiler, Dustin T.; Lingg, Aloysius J.; Eagan, Brendan R.; Shaffer, David W.; Werner, Nicole E. (January 2022, Ergonomics)

   Studying interactions faces methodological challenges and existing methods, such as configural diagramming, have limitations. This work demonstrates Epistemic Network Analysis (ENA) as an analytical method to construct configural diagrams. We demonstrated ENA as an analytical tool by applying this method to study dementia caregiver work systems. We conducted 20 semistructured interviews with caregivers to collect caregiving experiences. Guided by the Patient Work System model, we conducted a directed content analysis to identify work system components and used ENA to study interactions between components. By using ENA to create configural diagrams, we identified five frequently occurring interactions, compared work system configurations of caregivers providing care at home and away from home. Although we were underpowered to determine statistically significant differences, we identified visual and qualitative differences. Our results demonstrate the capability of ENA as 

   more » « less