Qualitative case narratives show the chatbot shifted stakeholders from narrow, visually driven readings toward conditional, context-aware interpretations¶

Claim · All claims
Evidence · 1 study (2 entries) · qualitative r3 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? In Case 1, a participant who initially read the visualization as direct gender bias began acknowledging data-quality factors and sample-size limitations after chatbot prompts, becoming cautious about student–professor gender interactions. → Marques 2026 q2 i? In Case 2, a participant replaced an individual-level reading of box plots with class-size and workload hypotheses after the chatbot clarified the data were course-level aggregates. → Marques 2026 (2)

Evidence¶

Marques 2026¶

Marques, F., Ortiz-Beltrán, A., Amarasinghe, I., & Hernández-Leo, D. (2026). Responsible Institutional Analytics: Interpreting Bias with AI Support. Journal of Universal Computer Science, 33(6). https://arxiv.org/abs/2610.07205 doi:10.48550/arxiv.2610.07205

q2 · i? · qualitative · r3

Illustrative narrative from the Case 1 think-aloud session (participant P7, satisfaction by professor gender, student gender, and faculty). The participant's initial reading focused on visible gender differences; chatbot prompts prompted reconsideration of "the limitations of the aggregated indicators."

"By interacting with the F ACTRIA-aware chatbot, the participant began acknowledging analytics pipeline factors—especially data quality—and, when prompted about small sample sizes, reconsidered the limitations of the aggregated indicators."

Marques 2026 (2)¶

Marques, F., Ortiz-Beltrán, A., Amarasinghe, I., & Hernández-Leo, D. (2026). Responsible Institutional Analytics: Interpreting Bias with AI Support. Journal of Universal Computer Science, 33(6). https://arxiv.org/abs/2610.07205. doi:10.48550/arxiv.2610.07205

q2 · i? · qualitative · r3

Illustrative narrative from the Case 2 session (participant P10, grades by active teaching methodology). After the chatbot clarified the visualization showed course-level aggregates, the participant incorporated "workload, learning design, and class size" as alternative explanations.

"When the F ACTRIA-aware chatbot prompted the participant to consider course-related factors—especially workload, learning design, and class size—the participant shifted again and recognized that course structure could influence satisfaction and performance indicators"

Discussion¶

Related Claims¶

• A FACTRIA-aware chatbot increases the number of biasing sub-factors stakeholders consider when interpreting institutional analytics visualizations — possibly the same claim (merge candidate)
• The FACTRIA-aware chatbot received good usability ratings (SUS 70.84) and high usefulness ratings from most of the 11 stakeholders — related
• Transition network analysis shows the chatbot's prompts and explanations structured the interaction while participants generated their own interpretations — related