AI is increasingly embedded in government, yet its meanings and implications remain contested and often misunderstood. Science fiction is an important yet underexplored source shaping public understandings of AI by generating collective imaginaries through polarized narratives. This paper introduces a typology structured along three axes: scale of governance (micro, meso, macro), type of AI (robotic, conversational, algorithmic), and narrative role (helper, subject, opponent). We apply the typology to 76 films and 68 reflective essays from university students. Findings reveal an overrepresentation of conversational, antagonistic AI at micro and meso scales in fiction whereas participants overrepresent algorithmic AI at the macro scale. The findings reveal convergences and divergences that expose forms of sociotechnical blindness in how AI in government is imagined. The study contributes to research by offering a theoretical lens to analyse fictional AI narratives, comparing representations and perceptions, and introducing cultural artefacts to study AI in government.
Lisa Dewulf, Anthony Simonofski, N. B. Rosselló et al.· EGOV-CeDEM-ePart 2026· 0 citations
AI-supported deliberation platforms increasingly support large-scale participation in public policymaking. Yet their design reflects strong rationalistic and emotion reductionist bias: while they structure arguments, cluster opinions, visualize disagreement or organize discussions, they largely ignore the emotional dynamics through which participants interpret claims, react to disagreement and sustain engagement. This blind spot is particularly problematic in discussions surrounding wicked public issues, where emotions are not peripheral but integral to how actors evaluate arguments and orient themselves toward collective consensus-oriented decisions. At the same time, recent advances in Generative Artificial Intelligence (GenAI) introduce new possibilities for interacting with emotional signals in digital communication. Beyond content processing, GenAI systems can detect, interpret, and generate context-sensitive emotional expressions; this opens the possibility of GenAI-mediated emotional support in deliberative environments. This study explores how such systems could be designed. Following an echeloned Design Science Research approach, the paper focuses on the initial stages of a broader design project aimed at developing a GenAI mediator for consensus-oriented online deliberation. The problem space is examined through an analysis of 3 existing deliberation platforms and a semisystematic literature review of 25 papers on emotional dynamics in consensus-oriented discussions. Using a three-step thematic synthesis, the study derives design knowledge, articulated through design requirements, for emotion-aware GenAI mediation. The results of this study consist of two outcomes. First, the analysis formulates a problem statement that identifies a gap in current deliberation platforms: while they organize informational exchanges, emotional dynamics remain unmodeled. Second, the study derives six design requirements that define the design space a solution must satisfy: emotional awareness, emotional regulation, emotional inclusive design, emotional stability, emotional conflict transformation, and emotional articulation. These findings contribute to an initial body of design knowledge that bridges research on emotions in deliberation with emerging capabilities of GenAI; they lay the groundwork for designing emotion-aware GenAI-mediated deliberations.
Antoine Danthine, Anthony Simonofski· EGOV-CeDEM-ePart 2026· 0 citations
