An official website of the United States government
Written memoranda of conversations, or memcons, provide a near‐contemporaneous record of what was said in conversation, and offer important insights into the activities of high‐profile individuals. We assess the impact of writing a memcon on memory for conversation. Pairs of participants engaged in conversation and were asked to recall the contents of that conversation 1 week later. One participant in each pair memorialized the content of the interaction in a memcon shortly after the conversation. Participants who generated memcons recalled more details of the conversations than participants who did not, but the content of recall was equally and largely accurate for both participants. Remarkably, only 4.7% of the details of the conversation were recalled by both of the partners after a week delay. Contemporaneous note‐taking appears to enhance memory for conversation by increasing the amount of information remembered but not the accuracy of that information. These findings have implications for evaluating the testimony of participants on conversations with major political or legal ramifications.
more »
« less
Relational AI: Facilitating Intergroup Cooperation with Socially Aware Conversational Support
Cooperation is challenging when group identities are involved. While people readily cooperate with in-group members, they struggle to build trust with out-group members. This study examines how text suggestions generated by Large Language Models (LLMs)can mitigate in-group-out-group bias and facilitate intergroup cooperation through conversations. We conducted an experiment with482 participants who communicated with either in-group partners sharing their views or out-group partners with differing views, based on a preliminary survey. Participants received either “personalized” message suggestions aligned with their own views and conversation styles, or “relational” suggestions using conversation styles tailored to whether their partner was in-group or out-group. Following the conversations, participants engaged in a cooperation game designed to measure trust behaviorally. Our results show that while personalized assistance widened the cooperation gap, relational assistance significantly improved out-group cooperation to match in-group levels. We discuss design implications for integrating social awareness into AI-driven conversational supportsystems.
more »
« less
- Award ID(s):
- 2237095
- PAR ID:
- 10662996
- Publisher / Repository:
- ACM
- Date Published:
- Page Range / eLocation ID:
- 1 to 22
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Social identity theory posits that individuals perceive the in-group as a homogenous entity comprised of depersonalized individuals, and this theory has provided a foundation to understand intergroup processes for many years. Cross-cultural research has suggested social identity theory may not apply to East Asians, who conceptualize their in-groups differently than those in from Western cultures. Specifically, Yuki and colleagues contend that East Asians perceive in-groups as networks wherein each individual is connected through personal ties, rather than homogenous entity comprised of depersonalized individuals. Furthermore, prior research has shown that East Asians are more likely to trust out-group members with potential personal connections, similarly to how they trust actual in-group members. This reflects their group boundary perception based on personal linkages rather than categorical membership. Conversely, individuals from Western cultures tend to trust in-group members more than out-group members, regardless of potential personal connections. Our preregistered study (N = 332 Japanese and 345 American university students) aimed to conceptually replicate key findings that support Yuki's account and expand upon the theory in the context of intergroup cooperation. Overall, we failed to find evidence for the network-based and category-based cooperation and trust among Japanese and Americans, respectively. Consequently, our results highlight the need for further experimental investigation and validation of Yuki and colleagues' theoretical framework.more » « less
-
Existing End-to-End secure messaging applications trust a single service provider to deliver messages in a consistent order to a consistent group of conversation members. We propose a protocol that removes this single point of failure by using multiple service providers, enforcing conversation integrity as long as one service provider out of N behave honestly. However, this approach could potentially increase the number of entities that learn the metadata for a conversation. In this work we discuss the challenges and provide a protocol that limits the metadata leakage to that of existing messaging applications while still providing strong conversation integrity.more » « less
-
BackgroundCross-neurotype differences in social communication patterns contribute to high unemployment rates among adults with autism. Adults with autism can be unsuccessful in job searches or terminated from employment due to mismatches between their social attention behaviors and society’s expectations on workplace communication. ObjectiveWe propose a behavioral intervention concerning distribution of attention in triadic (three-way) conversations. Specifically, the objective is to determine whether providing personalized feedback to each individual with autism based on an analysis of their attention distribution behavior during an initial conversation session would cause them to modify their orientation behavior in a subsequent conversation session. MethodsOur system uses an unobtrusive head orientation estimation model to track the focus of attention of each individual. Head orientation sequences from a conversation session are analyzed based on five statistical domains (eg, maximum exclusion duration and average contact duration) representing different types of attention distribution behavior. An intervention is provided to a participant if they exceeded the nonautistic average for that behavior by at least 2 SDs. The intervention uses data analysis and video modeling along with a constructive discussion about the targeted behaviors. Twenty-four individuals with autism with no intellectual disabilities participated in the study. The participants were divided into test and control groups of 12 participants each. ResultsBased on their attention distribution behavior in the initial conversation session, 11 of the 12 participants in the test group received an intervention in at least one domain. Of the 11 participants who received the intervention, 10 showed improvement in at least one domain on which they received feedback. Independent t tests for larger test groups (df>15) confirmed that the group improvements are statistically significant compared with the corresponding controls (P<.05). Crawford-Howell t tests confirmed that 78% of the interventions resulted in significant improvements when compared individually against corresponding controls (P<.05). Additional t tests comparing the first conversation sessions of the test and control groups and comparing the first and second conversation sessions of the control group resulted in nonsignificant differences, pointing to the intervention being the main effect behind the behavioral changes displayed by the test group, as opposed to confounding effects or group differences. ConclusionsOur proposed behavioral intervention offers a useful framework for practicing social attention behavior in multiparty conversations that are common in social and professional settings.more » « less
-
Using a dual-task paradigm, we explore how robot actions, performance, and the introduction of a secondary task influence human trust and engagement. In our study, a human supervisor simultaneously engages in a target-tracking task while supervising a mobile manipulator performing an object collection task. The robot can either autonomously collect the object or ask for human assistance. The human supervisor also has the choice to rely on or interrupt the robot. Using data from initial experiments, we model the dynamics of human trust and engagement using a linear dynamical system (LDS). Furthermore, we develop a human action model to define the probability of human reliance on the robot. Our model suggests that participants are more likely to interrupt the robot when their trust and engagement are low during high-complexity collection tasks. Using Model Predictive Control (MPC), we design an optimal assistance-seeking policy. Evaluation experiments demonstrate the superior performance of the MPC policy over the baseline policy for most participants.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Conference Paper:
- https://doi.org/10.1145/3706598.3713757
