Publications (8)0 Total impact
-
Article: Human dynamics: computation for organizations: Human dynamics: computation for organizations.
Pattern Recognition Letters. 01/2005; 26:503-511. -
Article: Human dynamics: computation for organizations
[show abstract] [hide abstract]
ABSTRACT: The human dynamics group at the MIT Media Laboratory proposes that active pattern analysis of face-to-face interactions within the workplace can radically improve the functioning of the organization. There are several different types of information inherent in such conversations: interaction features, participants, context, and content. By aggre-gating this information, high-potential collaborations and expertise within the organization can be identified, and infor-mation efficiently distributed. Examples of using wearable machine perception to characterize face-to-face interactions and using the results to initiate productive connections are described, and privacy concerns are addressed. Ó 2004 Elsevier B.V. All rights reserved.10/2004; -
Article: Accepted to the Artificial Intelligence, Information Access, and Mobile Computing Workshop at the 18th International Joint Conference
[show abstract] [hide abstract]
ABSTRACT: We introduce a method for situation understanding in natural, face-to-face conversation. Our method combines a network of commonsense knowledge with keyword spotting and contextual information automatically obtained from a wearable device such as a PDA or cell phone. Using this method we demonstrate the potential for high accuracy, detailed classification of conversation topic.07/2003; -
Article: Wearable Common Sense: Gisting Conversations with Contextual Information and Common Sense
[show abstract] [hide abstract]
ABSTRACT: This paper introduces a system that incorporates both contextual and commonsensical information to understand the gist of an informal, face-to-face conversation. We show that wearable devices, such as PDAs or cell phones, can provide the valuable contextual information critical for robust classification of a detailed conversation topic.06/2003; -
Article: Wearables in the Workplace: Sensing Interactions at the Office
[show abstract] [hide abstract]
ABSTRACT: Wearable computers, such as PDAs and cell phones, are proliferating in organizations. This paper introduces a methodology for leveraging this wearable infrastructure to provide insight to the underlying social dynamics of an organization. The work lays a foundation that will enable a variety of applications, from knowledge management to organizational simulation.06/2003; -
Article: Social Network Computing
[show abstract] [hide abstract]
ABSTRACT: A ubiquitous wearable computing infrastructure is now firmly entrenched within organizations across the globe, yet much of its potential remains untapped. This paper describes how the handheld computers and mobile phones in today's organizations can be used to quantify face-to-face interactions and to infer aspects about a user's situation, enabling more creative and transparent functioning of human organizations.06/2003; -
Article: Common Sense Conversations: Understanding Casual Conversation using a Common Sense Database
[show abstract] [hide abstract]
ABSTRACT: We introduce a method for situation understanding in natural, face-to-face conversation. Our method combines a network of commonsense knowledge with keyword spotting and contextual information automatically obtained from a wearable device such as a PDA or cell phone. Using this method we demonstrate the potential for high accuracy, detailed classification of conversation topic.04/2003; -
Article: Context sensing using speech and common sense
[show abstract] [hide abstract]
ABSTRACT: We present a method of inferring aspects of a person's context by capturing conversation topics and using prior knowledge of human behavior. This paper claims that topic-spotting performance can be improved by using a large database of common sense knowledge. We describe two systems we built to infer context from noisy transcriptions of spoken conversa-tions using common sense, and detail some preliminary results. The GISTER system uses OMCSNet, a commonsense semantic net-work, to infer the most likely topics under dis-cussion in a conversation stream. The OVERHEAR system is built on top of GISTER, and distinguishes between aspects of the conversation that refer to past, present, and future events by using LifeNet, a prob-abilistic graphical model of human behavior, to help infer the events that occurred in each of those three time periods. We conclude by discussing some of the future directions we may take this work.
