Log in / Register
Home arrow Computer Science arrow Social Computing, Behavioral-Cultural Modeling and Prediction
< Prev   CONTENTS   Next >

Identifying Emergent Thought Leaders

Abstract. Determining the emergent thought leader of an ad hoc organization would have enormous benefit in a variety of domains including emergency response. To determine if such leaders could be identified automatically, we compared an observer-based assessment to an automated approach for detecting leaders of 3-person ad hoc teams performing a logistics planning task. The automated coding used a combination of indicator phrases indicative of reasoning and uncertainty. The member of the team with the most reasoning and least uncertainty matched the observer-based leader in two thirds of the teams. This determination could be combined with other analyses of the topics of discussion to determine emergent thought leaders in different domains. As an example, a real-time user interface providing this information is shown which highlights communications by others that are relevant to the automatically detected, topic-specific, emergent thought leader.

Keywords: communications, leader, ad hoc teams, dialogue act analysis.

1 Introduction

An emergent leader is defined as an individual in an ad hoc group who is not assigned to a leadership position, but emerges over time as dominant in power, decisionmaking, and communications and is accepted by other members when acting in the capacity of how an assigned leader would be expected to act [1]. We define here an emergent thought leader (ETL) as one who emerges as a leader with respect to a particular topic or for a particular analytic task.

Detection of ETLs is critical, especially in situations without a clear command and control hierarchy or even knowledge of who is actually contributing. Being able to efficiently identify and communicate directly with such leaders is critical during timepressured, high-consequence responses to emergencies to prioritize activities, allocate resources, and communicate with other entities. For example, following a hurricane, governmental and non-governmental organizations need to coordinate to distribute resources such as food and water, shelter, and medical services. The ETL with regards to medicine may be different than one that which emerges for shelter. The person most aware of these resources may change dynamically over a period of hours, and may not be the officially designated person. For example, an ETL for medicine could be a physician on voluntary leave from their hospital in another state to provide emergency medical support and becomes the central figure working with the military branches and the Red Cross to provide medical resources to displaced civilians within a particular region. In turn, the ETL should also be aware of information and communication that may impact their decision-making.

We compare the observed leader to that assigned using an automated approach applied to transcripts of conversation from 12 three-person ad hoc teams doing a simulated logistics task. The automated approach used a form of dialogue act analysis previously shown to be useful with regards to military chat [2] and recognizes twothirds of the ETLs correctly. We combined this process with statistical topic extraction [3] to show how a user interface could be powered by these analyses to highlight information appropriate for the ETL of each topic.

Found a mistake? Please highlight the word and press Shift + Enter  
< Prev   CONTENTS   Next >
Business & Finance
Computer Science
Language & Literature
Political science