How Source Attribution Visualization Shapes User Attention and Preference: An Eye-Tracking Study of Four AI Chatbot Layouts
Journal of Eye Movement Research · 14.08.2026 · 19 (4) · 89
DOI: 10.3390/jemr19040089 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Eye Movement Research, online erschienen am 14.08.2026. Verfasst von Junho Cho und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Visual Communication Design, School of Design, Hongik University, 94 Wausan-ro, Mapo-gu, Seoul 04066, Republic of Korea. Die Arbeit nennt 85 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hongik University.
Abstract (Originalsprache)
As generative AI chatbots become a primary information channel, users increasingly accept answers without verification, and citations can raise trust even when sources are irrelevant or fabricated. How source-attribution visualization shapes the visual preconditions of verification remains unknown: users can notice, read, or compare a source without clicking. This within-subjects eye-tracking study (N = 23; 92 trials) evaluated four attribution visualizations abstracted from commercial AI chatbots and rendered as simulated screens: inline component (sentence-end chips), card list (cards above the answer), side panel (adjacent panel), and raw hyperlink (bare URLs), combining gaze metrics, surveys, and interviews. Repeated-measures ANOVAs revealed strong layout effects on source discoverability and engagement, largely robust to sensitivity checks (the panel’s discovery latency was order-sensitive): the card list was discovered almost immediately, with the raw hyperlink last. Yet no self-reported measure differed detectably. The most frequently nominated format, the inline component, attracted about half the dwell time of the stand-alone formats, whose prolonged fixations suggested citation-to-text mapping cost rather than genuine engagement. This attention–preference gap means both must be measured jointly. We contribute a four-layout gaze-based comparison, a reproducible participant-level analysis workflow, and three design principles (pre-click identifiability, sentence-level claim–source mapping, and in situ preview) within a proposed two-stage attribution architecture.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Visual Communication Design, School of Design, Hongik University, 94 Wausan-ro, Mapo-gu, Seoul 04066, Republic of Korea.
- Department of Mechanical and System Design Engineering, Hongik University, 94 Wausan-ro, Mapo-gu, Seoul 04066, Republic of Korea.
ORCID-Profile: Junho Cho, Dokshin Lim
Förderung
- Hongik University
Zitieren
APA
Cho, J., & Lim, D. (2026). How Source Attribution Visualization Shapes User Attention and Preference: An Eye-Tracking Study of Four AI Chatbot Layouts. Journal of Eye Movement Research, 19(4), 89. https://doi.org/10.3390/jemr19040089
Vancouver
Cho J, Lim D. How Source Attribution Visualization Shapes User Attention and Preference: An Eye-Tracking Study of Four AI Chatbot Layouts. Journal of Eye Movement Research. 2026;19(4):89. doi:10.3390/jemr19040089
BibTeX
@article{Cho2026,
author = {Cho, Junho and Lim, Dokshin},
title = {How Source Attribution Visualization Shapes User Attention and Preference: An Eye-Tracking Study of Four AI Chatbot Layouts},
journal = {Journal of Eye Movement Research},
year = {2026},
volume = {19},
number = {4},
pages = {89},
doi = {10.3390/jemr19040089}
}
EUVIMED