loading...
Michael Yeomans, Assistant Professor, Imperial College Business School
We examine how the choices made during conversation can foster co-operative goals during disagreement, and prevent conversational conflict spirals. We develop a machine learning algorithm to identify the linguistic profile of “conversational receptiveness.” Our model could label receptiveness as accurately as any human raters, by focusing on structural elements of language (eg hedges, acknowledgment, negation) that made our model interpretable to humans, and generalisable across topics and domains. We also show that receptiveness is reciprocated in kind, in two field settings from globally distributed teams where conflict is endemic to productivity. In discussion forums for online courses, receptive posts receive more receptive replies. Furthermore, wikipedia editors who are more receptive are less prone to receive personal attacks from others. We also find that giving writers in conflict a “receptiveness recipe” intervention, based on our algorithm, can improve their trust and persuasiveness to their opponents. Overall, we find that conversational receptiveness is reliably measurable, has meaningful relational consequences, and can be misunderstood by people in conflict.
Speaker bio
Michael Yeomans is an Assistant Professor in Strategy and Organisational Behaviour at Imperial College Business School. His research focuses on how machine learning can be used to understand and improve human judgment and decision-making – in particular, by using natural language processing to study decisions during conversations. His research has been published in many journals, including Journal of Personality and Social Psychology, Proceedings of the National Academy of Sciences, Management Science, and Organizational Behavior and Human Decision Processes. He received his PhD from the University of Chicago and prior to joining Imperial, he completed a post-doctoral fellowship at Harvard University.
To join the seminar, join the Zoom meeting.
Meeting ID: 986 8873 4768
Password: 655793
The webinars may be recorded and shared on Cambridge Judge Business School’s websites, social media and other channels.
For more information, please contact Luke Slater.