Summary
Understanding cause and effect relationships between things can be tricky, even when you have diagrams showing these relationships. The researchers developed a tool called CoNS-Explorer to provide both direct explanations and story-like descriptions based on these diagrams. They found that stories helped people understand complex tasks better, especially when figuring out overall effects. People use diagrams for structure but turn to text when they feel uncertain, checking back and forth to make sense of the information. From these findings, the researchers created a framework explaining how people anchor understanding and manage uncertainty when interpreting causal information.
What this means in practice
- •For data analysts: Use story-based explanations alongside causal graphs to improve interpretation of complex causal effects in data analysis tasks.
- •For business intelligence teams: Combine causal diagrams with contextual stories to better communicate uncertain causal directions and mechanisms in reports and presentations.
Authors
Bowen Deng, Jiaqi Zou, Kexin Zhang, Daifeng Li
Abstract
Causal graphs represent structural relationships among variables, yet users must still interpret direction, mechanism, and adjustment conditions in relation to the task at hand. Prior work often compares explanation formats as fixed conditions and pays less attention to how users distribute reasoning across graphs, direct explanations, and stories. We developed CoNS-Explorer, which uses reviewed instructional DAGs/SCMs to maintain a shared causal-fact ledger and generate fact-matched direct explanations and contextualized stories. A controlled survey experiment ($N=240$) compared the two texts as complete presentation packages. In the primary GLMM, the Story condition had a positive but uncertain overall association with accuracy (OR $=1.55$, 95\% CI $[0.34,7.10]$, $p=.572$); a population-averaged GEE showed a significant positive effect (OR $=1.89$, 95\% CI $[1.02,3.48]$, $p=.042$). Task-type interactions localized the clearest advantage to total-effect adjustment. Story also significantly increased situational presence. In a separate system-task and interview study ($N=24$), participants freely used graphs, direct explanations, and stories across three causal models. They established structural anchors with graphs and numerical results, consulted text when direction was unclear, mechanisms were unfamiliar, or multiple paths competed, and checked their judgments against other representations or external evidence. Integrating the two studies, we develop a process framework of structural anchoring, uncertainty triggering, explanation routing, and cross-calibration, together with four testable design propositions for adaptive causal explanation.