SearcharxivSearch

arXiv subjects

Gary Bente

Publications and source records attributed to Gary Bente.

3 recordsLinked to original sources

The Moment of Capture: How the First Seconds of a Speaker's Nonverbal and Verbal Performance Shapes Audience Judgments

Why do some speakers capture a room almost instantly while others fail to connect? The real-time architecture of audience engagement remains largely a black box. Here, we used motion-captured animations to present the pure nonverbal performance of public speakers to audiences - either in silence (nonverbal-only) or paired with the verbal content (nonverbal-plus-verbal). Using continuous response measurement (CRM), we find that audience judgments solidify with remarkable speed: Moment-to-moment engagement ratings become highly predictive of subsequent evaluations within the initial 10 seconds of the performance. Most notably, this predictive relationship emerged faster and slightly stronger in the nonverbal-only condition, with predictive information being present already after less than 5 seconds. These findings elucidate the social impact a speaker's nonverbal performance has on audience impressions, even when dissociated from the verbal content of the speech. Our approach provides a high-resolution temporal map of social impression formation, pointing to an early "moment of capture" that appears to set the stage for the reception of the following message. On a broader scale, this research validates a powerful new method to isolate different communicative channels, to scientifically deconstruct rhetorical skill, and to study the pervasive impact of nonverbal behavior more broadly. It also enables us to translate the ancient art of rhetoric into a modern science of social impression formation, yielding an empirical basis that can inform human-centered feedback, develop AI-based augmentation tools, and guide the design of engaging, socially present avatars in an increasingly AI-mediated and virtual world.

cs.HC

The Art of Audience Engagement: LLM-Based Thin-Slicing of Scientific Talks

This paper examines the thin-slicing approach - the ability to make accurate judgments based on minimal information - in the context of scientific presentations. Drawing on research from nonverbal communication and personality psychology, we show that brief excerpts (thin slices) reliably predict overall presentation quality. Using a novel corpus of over one hundred real-life science talks, we employ Large Language Models (LLMs) to evaluate transcripts of full presentations and their thin slices. By correlating LLM-based evaluations of short excerpts with full-talk assessments, we determine how much information is needed for accurate predictions. Our results demonstrate that LLM-based evaluations align closely with human ratings, proving their validity, reliability, and efficiency. Critically, even very short excerpts (less than 10 percent of a talk) strongly predict overall evaluations. This suggests that the first moments of a presentation convey relevant information that is used in quality evaluations and can shape lasting impressions. The findings are robust across different LLMs and prompting strategies. This work extends thin-slicing research to public speaking and connects theories of impression formation to LLMs and current research on AI communication. We discuss implications for communication and social cognition research on message reception. Lastly, we suggest an LLM-based thin-slicing framework as a scalable feedback tool to enhance human communication.

cs.CL

Artificial social influence via human-embodied AI agent interaction in immersive virtual reality (VR): Effects of similarity-matching during health conversations

Interactions with artificial intelligence (AI) based agents can positively influence human behavior and judgment. However, studies to date focus on text-based conversational agents (CA) with limited embodiment, restricting our understanding of how social influence principles, such as similarity, apply to AI agents (i.e., artificial social influence). We address this gap by leveraging the latest advances in AI (language models) and combining them with immersive virtual reality (VR). Specifically, we built VR-ECAs, or embodied conversational agents that can naturally converse with humans about health-related topics in a virtual environment. Then we manipulated interpersonal similarity via gender matching and examined its effects on biobehavioral (i.e., gaze), social (e.g., agent likeability), and behavioral outcomes (i.e., healthy snack selection). We found an interesting interaction effect between agent and participant gender on biobehavioral outcomes: discussing health with opposite-gender agents tended to enhance gaze duration, with the effect stronger for male participants compared to their female counterparts. A similar directional pattern was observed for healthy snack selection, though it was not statistically significant. In addition, female participants liked the VR-ECAs more than their male counterparts, regardless of the gender of the VR-ECAs. Finally, participants experienced greater presence while conversing with VR-embodied agents than chatting with text-only agents. Overall, our findings highlight embodiment as a crucial factor of influence of AI on human behavior, and our paradigm enables new experimental research at the intersection of social influence, human-AI communication, and immersive virtual reality (VR).

cs.HC