In recent years, Large Language Models (LLM) have demonstrated impressive capabilities in the field of natural language processing (NLP). This paper explores the application of LLMs in negotiation transcript analysis by the Vanderbilt AI Negotiation Lab. Starting in September 2022, we applied multiple strategies using LLMs from zero shot learning to fine tuning models to in-context learning). The final strategy we developed is explained, along with how to access and use the model. This study provides a sense of both the opportunities and roadblocks for the implementation of LLMs in real life applications and offers a model for how LLMs can be applied to coding in other fields.

The rapid introduction of technological developments into healthcare systems adds another layer of complexity to the already demanding jobs of nurses, particularly for those working in perioperative care. In the present study, our primary aim is job satisfaction, whereas the secondary outcomes are psychological well-being and quality of life (QoL) ratings of perioperative nurses who take part in robotic-assisted and pure laparoscopic surgery. A total of 101 perioperative nurses in six different centers were included in the study. Fifty-one of the nurses were working in robotic-assisted laparoscopic surgery and 50 of them were working in pure laparoscopic surgery. All participants responded to Minnesota Job Satisfaction Questionnaire (MJSQ), Beck Depression Inventory (BDI) and SF-36 QoL Measurement Survey. The two groups did not differ in their total MJSQ, BDI and SF-36 QoL scores (pMJSQ:0.066, pBDI:0.329, pSF-36-QoL:0.136). In addition, there were no differences between the two groups in their intrinsic job satisfaction and extrinsic job satisfaction sub-scores (pintrinsic: 0.473, pextrinsic:0.121). Overall, 18.9% of the nurses reported having moderate to extreme depressive symptoms and most of them (87.1%) had low to moderate levels of job satisfaction. Finally, QoL ratings was generally at moderate levels. Perioperative nurses who work in robotic-assisted laparoscopic surgery do not differ from those working in pure laparoscopic surgery in terms of their job satisfaction, psychological well-being, and QoL ratings. In addition, across groups' psychological well-being, job satisfaction, and QoL ratings were not particularly high, suggesting that more attention needs to be paid to improving the work conditions of perioperative nurses.

This research examines the potential social benefits of displaying curiosity during a negotiation. Past research has found women who ask directly in distributive agentic settings can suffer negative social consequences and obtain worse objective outcomes compared to men. In three experiments (N = 600) using different negotiation contexts, we found men and women who approach negotiations with curiosity reap the same economic benefits of asking directly but without incurring a social cost. We also found that perceived warmth partially accounts for the positive effects of curiosity (vs. asking directly) on negotiators’ social outcomes. Finally, our results reveal women feel more comfortable conveying curiosity compared to using a direct approach in their negotiations. We discuss the implications of these findings in enhancing negotiation effectiveness for both women and men.

Although past research has offered important insights into how people seek to maintain their moral standing, it has generally portrayed this process as a matter of aggregating essentially static interpretations of a target's discrete acts. The present research reveals, however, that such interpretations are often far from static, and that they can change more than targets realize as new events unfold. More specifically, we find that: a) people can discount the diagnostic value of a target's initial deed if that party commits a subsequent act of the opposite valence, b) this occurs when an initial good deed is followed by a bad deed but not when the order is reversed, c) this occurs when evaluating the actions of others but not when evaluating the self, and d) this actor vs. observer difference can ultimately produce divergent beliefs about the target's overall morality, trustworthiness and subsequent trusting behaviors. We also identify a key mediating mechanism for these effects (i.e., the retrospective imputation of nefarious intent). Implications for reputation management, as well as the maintenance and repair of trust, are discussed.

We examine the lay belief that negotiators must give up value to protect their relationship; then we consider the effects of strategically conveying curiosity on relationship and outcome satisfaction. In a series of experiments (N= 1004), we show that curiosity cues help build attraction with counterparts, which in turn enhances relationship and outcome perceptions, even when the outcome is disadvantageous for counterparts, or the negotiation ends in impasse. Thus, curiosity cues introduce an emotional-motivational dimension to tried and true negotiation tactics that allows negotiators to claim the deal terms they want without jeopardizing relational outcomes.

In organizational groups, expertise and information are often distributed among group members, thus making information sharing a necessity for group success. We examine the role of mood diversity on the discussion of disconfirming information and evaluation of decision alternatives in groups. In a laboratory experiment, using a hidden profile task, we manipulated mood diversity in 36 four-person, same-sex groups. Results indicated that mood diversity (vs. homogeneity) was positively related to groups' focus on disconfirming information, which ultimately led to a more accurate evaluation of their decision alternatives. Results of the study expand our understanding of how mood composition of groups affects their discussion dynamics and decision evaluation.

Face threat sensitivity (FTS) is defined as reactive sensitivity to threats to one's social self-worth. In negotiations, such threats may come from a counterpart's competitive behavior. We developed and tested the argument that individuals high in face threat sensitivity, when negotiating with a competitive (vs. cooperative) counterpart, exhibit psychological responses that inhibit them from claiming value in distributive negotiations. Employing a face-to-face interaction paradigm, Study 1 revealed that higher counterpart competitiveness was negatively associated with high (but not low) FTS negotiators' global self-esteem, which in turn led them to be less demanding and obtain worse negotiation outcomes. In Study 2, employing a simulated on-line interaction paradigm, we manipulated counterpart's behavior (cooperative vs. competitive) to establish causality and examined specific aspects of negotiator global self-esteem that may account for the effect. We found that the effect of counterpart's competitiveness on high FTS negotiators' demand levels was mediated by their performance self-esteem, but not by their social self-esteem. In Study 3, we manipulated performance self-esteem to establish it as a causal underlying psychological mechanism. For high FTS negotiators, when performance self-esteem was low, demand levels were significantly lower with a competitive (vs. cooperative) counterpart. However, when performance self-esteem was high, there was no significant difference in demand levels depending on counterpart's behavior. This finding suggests that negotiating with a competitive (vs. cooperative) counterpart reduces high FTS negotiators' performance self-esteem, which in turn leads them to make lower demands. The implications of these findings are discussed.

Although past research has offered important insights into the ways in which people attempt to manage their moral character, that work has typically presumed that the kinds of inferences people make about a target would involve the aggregation of essentially static interpretations of that party’s discrete acts. The present research reveals, however, that such interpretations are often far from static, and that they can actually be altered far more than people realize as new events unfold. More specifically, through four empirical studies, we find that: a) people may discount the diagnosticity of an actor’s initial deed if that party commits a subsequent act of the opposite valence, b) this is more likely to occur when a prior good deed is followed by a bad deed than when a prior good deed is followed by a good deed, c) this occurs to a greater degree when evaluating the actions of others than the self, and d) this can ultimately produce divergent perceptions of the target’s overall morality, evaluations of that party’s trustworthiness, and expectations for trusting behaviors.

Verbal probability expressions are often used to communicate risk in decision making situations. We tested the argument that fear would lead to more pessimistic risk perceptions and higher risk aversion than tranquility when the verbal probability expression used to communicate risk is more (vs. less) ambiguous. In Experiment 1, using a dispute resolution context, we found that fear led to a lower impasse rate than tranquility when the probability of winning in court was described using the ambiguous probability word 'a chance' than when less ambiguous probability words were used (i.e., doubtful, probable). In Experiment 2, we replicated this effect using a risky-choice task. Participants in the fear condition were more likely to choose the safe option than those in the tranquil emotion condition when risk was communicated using the ambiguous probability word 'a chance' (vs. 'doubtful' and 'probable'). The implications of these findings for emotion, risk taking, and risk communication literatures are discussed.

People may express a variety of emotions after committing a transgression. Through 6 empirical studies and a meta-analysis, we investigate how the perceived authenticity of such emotional displays and resulting levels of trust are shaped by the transgressor's power. Past findings suggest that individuals with power tend to be more authentic because they have more freedom to act on the basis of their own personal inclinations. Yet, our findings reveal that (a) a transgressor's display of emotion is perceived to be less authentic when that party's power is high rather than low; (b) this perception of emotional authenticity, in turn, directly influences (and mediates) the level of trust in that party; and (c) perceivers ultimately exert less effort when asked to make a case for leniency toward high rather than low-power transgressors. This tendency to discount the emotional authenticity of the powerful was found to arise from power increasing the transgressor's perceived level of emotional control and strategic motivation, rather than a host of alternative mechanisms. These results were also found across different types of emotions (sadness, anger, fear, happiness, and neutral), expressive modalities, operationalizations of the transgression, and participant populations. Altogether, our findings demonstrate that besides the wealth of benefits power can afford, it also comes with a notable downside. The findings, furthermore, extend past research on perceived emotional authenticity, which has focused on how and when specific emotions are expressed, by revealing how this perception can depend on considerations that have nothing to do with the expression itself.

In the present studies, we examined the positive value of agreement and the negative value of impasse. Participants chose to give up real value and sacrifice economic efficiency in order to attain an agreement outcome and avoid an impasse outcome. A personally disadvantageous option was selected significantly more often when it was labeled Agreement rather than Option A, and a personally advantageous option was avoided significantly more often when it was labeled Impasse rather than Option B. In a face-to-face negotiation, a substantial proportion of individuals reached an agreement that was inferior to their best alternative to agreement. We showed that the appeal of agreement and the aversion to impasse both contribute to this effect, yet the aversion to impasse is the stronger of the two motivations. These findings have important implications for negotiators.

Five empirical studies investigated the implications of power for perceptions of emotional authenticity and trust after a transgression. Across different sets of emotions, different types of emotion stimuli, different operationalizations of the transgression, and different types of participants, our findings reveal that a transgressor’s display of emotion is perceived to be less authentic when that party’s power is high than low, and that this perception of emotional authenticity, in turn, directly influences (and ultimately mediates) the level of trust in that party. This tendency to discount the emotional authenticity of the powerful was, furthermore, found to arise from power increasing the transgressor’s perceived level of emotional control and strategic motivation. Finally, evidence suggests these implications are neither justified by expresser’s actual tendencies, nor factors for which expressers appeared to compensate in their displays.

Agreement bias is a tendency to reach agreement even when agreement violates at least one party’s objective interests. The current studies establish agreement bias in negotiations as a robust empirical phenomenon. In Studies 1A-1D, labeling an allocation option ‘agreement’ in a decomposed game shifts choices in favor of that option, even when it is strictly dominated by the alternative choice, and even when real money is at stake. In a free recall task (Study 2) and a vignette-based experiment (Study 3), negotiators who reach agreement consistently report experiencing more happiness, less anger, and greater subjective value related to the negotiation than those who reach impasse, even when reaching agreement did not satisfy the negotiators’ bottom-line interests. Finally, a vignette-based experiment (Study 3) shows that people predict that they would react more favorably to an agreement that doesn’t satisfy their interests than they would react to an impasse.

Experts often convey information to emotional decision makers using imprecise verbal probability expressions. We examined how the emotional state of decision makers influenced their judgment and choice through the interpretation of verbal probabilities. Study 1 revealed that fear led individuals to make more optimistic assessments about future events than anger when the likelihood of an event was characterized as “probable.” Study 2 demonstrated that fear prompted risk-averse tendencies compared to anger in the form of setting lower reservation values for the upcoming negotiation, especially when the likelihood of a favorable resolution following an impasse was characterized as “doubtful.” In a two-party, computer-mediated dispute resolution, Study 3 demonstrated that fear prompted risk-aversion compared to tranquility such that fear led to a lower impasse rate when the likelihood of a favorable resolution following an impasse was characterized as “a chance.” We discuss the implications of these findings for consumers and providers of advice.

We examined the effects of face threat sensitivity (White, Tynan, Galinsky, & Thompson, 2004) in negotiations. Study 1 revealed that counterpart’s competitive behaviors negatively affected high face threat sensitivity negotiators’ feelings about self. Further, negative feelings about self increased concession making, decreased the individual negotiation outcome, and led to negative feelings about the relationship. Study 2 examined how managing expectancies about counterparts’ anger would alleviate the deleterious effects of face threat sensitivity in negotiations. The results indicated that counterpart’s anger expressions had less of a negative effect on high face threat sensitivity negotiators’ feelings about self when the counterpart confirmed as opposed to violating expectancies. Taken together, the results demonstrated that feelings about self should be taken into account when examining the effects of face threat sensitivity on negotiators’ attitude toward the relationship, concession making, and individual outcome. Further, we showed that managing expectancies about counterparts’ anger mitigated the negative effects of face threats on high face threat sensitivity negotiators’ feelings about self. We discuss the implications of our findings for negotiation research.

We examined the role of anticipated happiness in negotiation settings. Anticipated happiness is the happiness that individuals expect to experience in the future if certain events do or do not occur. In two studies, we tested the argument that anticipated happiness initiates an approach goal, leading individuals to promote economic interests. Study 1 revealed that anticipated happiness was positively related to the propensity to initiate a negotiation, mediated by an approach goal. In Study 2, we found that anticipated happiness about reaching the target value increased the individual negotiation outcome, mediated by actual target value. Our studies provide insight into how anticipated happiness influences motivation, behavior, and ultimately individual outcomes in negotiations.