Published October 31, 2023 | Version v1
Journal article Open

Moving Beyond Universal Designs: How Culturally Adaptive AI-Generated Visualizations Improve Cross-Cultural Data Understanding

Authors/Creators

Description

Artificial intelligence (AI) is transforming how we create data visualizations, but a major limitation remains—most AI tools produce generic visuals that ignore cultural differences in interpretation. Colors, symbols, layouts, and even how data is presented can mean different things across cultures, leading to misunderstandings or exclusion. Our research explores how cultural background affects how people understand AI-generated visuals and introduces a new approach to designing adaptive visual analytics systems that respect cultural diversity.

Using a combination of methods—including cross-cultural user testing, computational analysis of AI-generated visuals, and designer interviews—we uncover cultural biases in current tools (such as Western-centered color meanings or left-to-right flow assumptions). We then develop and evaluate a prototype AI model that customizes visual elements (like color schemes or legend placement) based on a user’s cultural background. Our results show that culturally adapted visuals significantly enhance comprehension and decision-making, especially for non-Western users in critical fields like public health and international business.

This paper provides three important contributions: (1) it shows that there are cultural barriers in AI visualization tools, (2) it gives a useful way to find and fix cultural bias in automated designs, and (3) it gives clear advice on how to develop AI-driven visual analytics that are more inclusive. This approach helps make sure that data is shared fairly and effectively in our globalized society by integrating AI automation with cultural understanding.

Files

EJAET-10-10-153-161.pdf

Files (330.4 kB)

Name Size Download all
md5:298ae45ed400ef649cc1f049786509ae
330.4 kB Preview Download

Additional details

References

  • [1]. Y. Wang, L. Cheng, and M. Bostock, "One Visualization Doesn't Fit All: A Survey of Cultural Bias in Automated Data Graphics," IEEE Trans. Vis. Comput. Graphics, vol. 27, no. 2, pp. 1751–1763, Feb. 2021, doi: 10.1109/TVCG.2020.2980801.
  • [2]. H. Kim and R. Patel, "When Colors Cross Cultures: How Misaligned Semantics in COVID-19 Dashboards Delayed Global Responses," Proc. ACM Hum.-Comput. Interact., vol. 4, no. CSCW2, pp. 1–24, Oct. 2020, doi: 10.1145/3415218.
  • [3]. T. Liu, E. M. Peck, and D. A. Szafir, "Color Crafting: Automating the Construction of Designer Quality Color Ramps," IEEE Trans. Vis. Comput. Graphics, vol. 25, no. 1, pp. 406–416, Jan. 2019, doi: 10.1109/TVCG.2018.2865027.
  • [4]. W. Alrashed and T. Oliveira, "Right-to-Left, Left-to-Right: How Spatial Bias Affects Cross-Cultural Visualization Comprehension," Proc. ACM Hum.-Comput. Interact., vol. 5, no. ISS, pp. 1–23, Nov. 2021, doi: 10.1145/3486955.
  • [5]. R. Chen, M. Brehmer, and K. W. Boy, "When Defaults Don't Fit: How Visualization Tools Fail Global Users," IEEE Trans. Vis. Comput. Graphics, vol. 26, no. 1, pp. 827–837, Jan. 2020, doi: 10.1109/TVCG.2019.2934810.
  • [6]. L. Zhang and G. Furnas, "Lost in Translation: How Cultural Mismatches in Automated Visual Analytics Undermine Global Teams," Proc. ACM Hum.-Comput. Interact., vol. 2, no. CSCW, pp. 1–25, Nov. 2018, doi: 10.1145/3274429.
  • [7]. H. Kim, J. Riche, and D. Moritz, "The Hidden Cost of Globalization: Measuring Visualization Localization Efforts in Multinational Corporations," IEEE Trans. Prof. Commun., vol. 64, no. 3, pp. 278–293, Sept. 2021, doi: 10.1109/TPC.2021.3064249.
  • [8]. W. Martinez, M. Dontcheva, and S. Klemmer, "Rule-Based vs. Adaptive: Evaluating Approaches to Automated Visualization Localization," Proc. ACM Hum.-Comput. Interact., vol. 4, no. CSCW2, pp. 1–26, Oct. 2020, doi: 10.1145/3415226.
  • [9]. Y. Wang and A. Satyanarayan, "Learning Visualization Preferences: Towards Adaptive and Explainable Recommendation Systems," IEEE Trans. Vis. Comput. Graphics, vol. 27, no. 2, pp. 269–279, Feb. 2021, doi: 10.1109/TVCG.2020.3028987.
  • [10]. R. Patel, S. Liu, and K. Karahalios, "Cultural Code-Switching in AI-Generated Visualizations," Proc. ACM Hum.-Comput. Interact., vol. 4, no. CSCW2, pp. 1–24, Oct. 2020, doi: 10.1145/3415219.
  • [11]. T. Li, M. Correll, and J. Heer, "The Western Gaze: How Dataset Biases Shape Global Visualization Practices," IEEE Trans. Vis. Comput. Graphics, vol. 28, no. 1, pp. 325–335, Jan. 2021, doi: 10.1109/TVCG.2021.3114836.
  • [12]. D. Nguyen, A. Diakopoulos, and M. Kay, "When Adaptations Offend: The Risks of Algorithmic Cultural Assumptions," Proc. ACM Hum.-Comput. Interact., vol. 4, no. CSCW3, pp. 1–27, Dec. 2020, doi: 10.1145/3432954.
  • [13]. Y. Liu and J. Stasko, "Cultural Variables in Visualization: Toward a Framework for Adaptive Design," IEEE Trans. Vis. Comput. Graphics, vol. 28, no. 1, pp. 112–122, Jan. 2021, doi: 10.1109/TVCG.2021.3114774.
  • [14]. H. Zhao, M. Brehmer, and E. Wu, "Culturally-Aware Visualization Adaptation: A Framework and Evaluation," Proc. ACM Hum.-Comput. Interact., vol. 6, no. CSCW1, pp. 1–30, Apr. 2022, doi: 10.1145/3491105.