Thin slices of negotiation: Predicting outcomes from conversational dynamics within the first 5 minutes.

Abstract

In this research the authors examined whether conversational dynamics occurring within the first 5 minutes of a negotiation can predict negotiated outcomes. In a simulated employment negotiation, microcoding conducted by a computer showed that activity level, conversational engagement, prosodic emphasis, and vocal mirroring predicted 30% of the variance in individual outcomes. The conversational dynamics associated with success among high-status parties were different from those associated with success among low-status parties. Results are interpreted in light of theory and research exploring the predictive power of "thin slices" of behavior (N. Ambady & R. Rosenthal, 1992). Implications include the development of new technology to diagnose and improve negotiation processes.

A Reciprocal Influence Model of Social Power: Emerging Principles and Lines of Inquiry

“…Evidence from studies using this methodology suggests that individuals are able to judge strangers' status on the basis of brief (90 seconds) video clips of behavior with considerable accuracy (Dawson & Gilovich, 2004). Interestingly, other research indicates that negotiation outcomes can be reliably predicted from conversational dynamics within the first five minutes of a negotiation, and more importantly, that these dynamics differentially predict outcomes for high as compared to low status negotiators (Curhan & Pentland, 2007).…”

Predicting online lecture ratings based on gesturing and vocal behavior

“…In particular, domains like Affective Computing [31] and Social Signal Processing [43] adopted nonverbal behavioral cues as a physical, machine detectable evidence of emotional and social phenomena, respectively. Research efforts targeted a wide spectrum of problems, including conflict detection [28], communication dynamics [7,25], mimicry measurement [10], early detection of developmental and cognitive diseases [37], role recognition [38], prediction of negotiation outcomes [9], videosurveillance [4,5,6,8], etc. Furthermore, several works were dedicated to the automatic prediction of traits likely to be relevant in a teaching context like, in particular, personality [21,23,30] and dominance [13,27,34,35].…”

Human Behavior Understanding for Inducing Behavioral Change: Application Perspectives

“…There is encouraging evidence that computers can be made capable of exploiting thin slices of behavior to detect individual traits such as personality [35,47] and dominance [27,28,31], group properties like social roles [17], interactions' outcomes [15,36], etc. Many of these works have employed so-called 'honest signals' -social signals that, being too difficult for humans to control, can provide a reliable source of information about socially relevant aspects [58,45].…”