Every model has a story, every story has a model
TEAMING AND INCLUSIVE MODELING
Stories are conveyed through dialogue, models, and collaborations. Collaborations are crucial for establishing trust and evaluating the compatibility of different viewpoints. Our research relies on collaborations with social scientists, scholars in the humanities, computer scientists, and other relevant experts. Moreover, we focus on creating inclusive approaches and tools that facilitate effective communication not only among academics but also among students and neurodiverse individuals.
Research Areas' Focus
1
Human-AI Teaming
Studies how humans and AI systems jointly perform tasks, make decisions, and enhance team performance.
-
Designs AI teammates that adapt to human reasoning and preferences.
-
Investigates trust, coordination, and shared situational awareness between humans and AI.
2
Inclusive Modeling Approaches
Builds models that integrate diverse knowledge, experiences, and viewpoints for more equitable outcomes.
-
Incorporates social, cultural, and contextual factors into modeling frameworks.
-
Ensures accessibility and representation of underrepresented groups in data and analysis.
3
Interdisciplinary Team Collaboration
Examines how experts from different fields work together, bridging disciplinary gaps to solve complex problems.
-
Studies communication dynamics across disciplines.
-
Develops frameworks to align differing methodologies, assumptions, and terminologies.
Research Papers and Blogs
Model Co-creation from a Modeler’s Perspective: Lessons Learned from the Collaboration Between Ethnographers and Modelers
Insights:
-
The paper describes a model co-creation process that integrates qualitative and quantitative methods, epistemologies, and ontologies to collaboratively develop an ethnographic simulation model of the refugee situation in Lesbos, Greece.
-
The co-created model served as a tool for ethnographers to reflect on field observations, refine research questions, and adjust the modeling scope, while also highlighting the challenges of translating complex field data into simulation models.
Citation:
Padilla, J.J., Frydenlund, E., Wallewik, H., Haaland, H. (2018). Model Co-creation from a Modeler’s Perspective: Lessons Learned from the Collaboration Between Ethnographers and Modelers. In: Thomson, R., Dancy, C., Hyder, A., Bisgin, H. (eds) Social, Cultural, and Behavioral Modeling. SBP-BRiMS 2018. Lecture Notes in Computer Science(), vol 10899. Springer, Cham. https://doi.org/10.1007/978-3-319-93372-6_8
The use of artificial intelligence to detect students' sentimentsand emotions in gross anatomy reflections
Insights:
-
This study applies natural language processing (NLP) and sentiment analysis to examine health professional students' reflective writings in gross anatomy, aiming to efficiently analyze the complex emotions embedded in student reflections about themselves and their anatomical donors.
-
Analysis of 1,365 reflections revealed predominantly positive sentiments, with trust, joy, and anticipation being the most frequent emotions across various body regions; NLP allowed the detection of shared emotional patterns between self-reflections and donor reflections, offering insights into students' person-centered perspectives.
Citation:
Rechowicz, K. J., & Elzie, C. A. (2023). The use of artificial intelligence to detect students' sentiments and emotions in gross anatomy reflections. Anatomical Sciences Education, 16(4), 729–740. https://doi.org/10.1002/ase.2273
Cloud-based simulators: Making simulations accessible to non-experts and experts alike
Insights:
-
The paper introduces ClouDES, a cloud-based discrete-event simulation platform designed to make simulations more accessible to both experts and non-experts by leveraging cloud computing’s scalability, broad access, and ease of use.
-
ClouDES enables non-expert users, such as middle and high school students, to engage with STEM concepts like probability and queuing using familiar technologies (e.g., mobile devices), demonstrating how cloud-based simulation can broaden participation in modeling and simulation education.
Citation:
Padilla, J. J., Diallo, S. Y., Barraco, A., Lynch, C. J., & Kavak, H. (2014). Cloud-based simulators: Making simulations accessible to non-experts and experts alike. In Proceedings of the 2014 Winter Simulation Conference (pp. 3630–3640). IEEE. https://doi.org/10.1109/WSC.2014.7020192
Adapting and validating a survey to assess host communities support for migration
Insights:
-
This study aimed to adapt and validate a new instrument—the Support for Migration Assessment (SMA)—to measure how host communities perceive and support incoming migration, applying Social Exchange Theory (SET) to the context of migration.
-
Using data from 333 participants in Barranquilla, Colombia, the SMA showed strong internal consistency and good construct validity across multiple factors (trust in institutions, community satisfaction, infrastructure impact), providing a reliable tool to assess host community support for migration.
Citation:
Botello, J. G., Palacio, K., Frydenlund, E., Llinás, H., & Padilla, J. J. (2024). Adapting and validating a survey to assess host communities support for migration. Social Indicators Research, 174(697–720). https://doi.org/10.1007/s11205-024-03397-6