Supporting Reasoning with Different Types of Evidence in Intelligence Analysis

Alice Toniolo; Timothy J Norman; Anthony Anietie Etuk; Federico Cerutti; Robin Wentao Ouyang; Mani Srivastava; Nir Oren; Timothy  Dropps; John A.  Allen; Paul Sullivan

Supporting Reasoning with Different Types of Evidence in Intelligence Analysis

Alice Toniolo, Timothy J Norman, Anthony Anietie Etuk, Federico Cerutti, Robin Wentao Ouyang, Mani Srivastava, Nir Oren, Timothy Dropps, John A. Allen, Paul Sullivan

Computing Science

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

43 Citations (Scopus)

Abstract

The aim of intelligence analysis is to make sense of information that is often conflicting or incomplete, and to weigh competing hypotheses that may explain a situation. This imposes a high cognitive load on analysts, and there are few automated tools to aid them in their task. In this paper, we present an agent-based tool to help analysts in acquiring, evaluating and interpreting information in collaboration with others. Agents assist analysts in reasoning with different types of evidence to identify what happened and why, what is credible, and how to obtain further evidence. Argumentation schemes lie at the heart of the tool, and sensemaking agents assist analysts in structuring evidence and identifying plausible hypotheses. A crowdsourcing agent is used to reason about structured information explicitly obtained from groups of contributors, and provenance is used to assess the credibility of hypotheses based on the origins of the supporting information.

Original language	English
Title of host publication	Proceedings of the Fourteenth International Conference on Autonomous Agents and Multiagent Systems
Publisher	ACM
Pages	781-789
Number of pages	9
ISBN (Electronic)	978-1-4503-3413-6
Publication status	Published - 2015
Event	14th International Conference on Autonomous Agents and Multiagent Systems Systems - Istanbul, Turkey Duration: 4 May 2015 → 8 May 2015

Conference

Conference	14th International Conference on Autonomous Agents and Multiagent Systems Systems
Abbreviated title	AAMAS 2015
Country/Territory	Turkey
City	Istanbul
Period	4/05/15 → 8/05/15

Keywords

Innovative Applications
Aerospace and Defense
Argumentation
Collective intelligence
Human-agent Interaction

Access to Document

http://www.ifaamas.org/Proceedings/aamas2015/aamas/p781.pdf

Nir Oren
- Agents at Aberdeen
- School of Natural & Computing Sciences, Computing Science - Personal Chair
- Human-Centred Computing
Person: Academic

Cite this

Toniolo, A., Norman, T. J., Etuk, A. A., Cerutti, F., Ouyang, R. W., Srivastava, M., Oren, N., Dropps, T., Allen, J. A., & Sullivan, P. (2015). Supporting Reasoning with Different Types of Evidence in Intelligence Analysis. In Proceedings of the Fourteenth International Conference on Autonomous Agents and Multiagent Systems (pp. 781-789). ACM. http://www.ifaamas.org/Proceedings/aamas2015/aamas/p781.pdf

Toniolo, A, Norman, TJ, Etuk, AA, Cerutti, F, Ouyang, RW, Srivastava, M, Oren, N, Dropps, T, Allen, JA & Sullivan, P 2015, Supporting Reasoning with Different Types of Evidence in Intelligence Analysis. in Proceedings of the Fourteenth International Conference on Autonomous Agents and Multiagent Systems. ACM, pp. 781-789, 14th International Conference on Autonomous Agents and Multiagent Systems
Systems , Istanbul, Turkey, 4/05/15. <http://www.ifaamas.org/Proceedings/aamas2015/aamas/p781.pdf>

@inproceedings{f9084d63d67944089acf387ab6bc1543,

title = "Supporting Reasoning with Different Types of Evidence in Intelligence Analysis",

abstract = "The aim of intelligence analysis is to make sense of information that is often conflicting or incomplete, and to weigh competing hypotheses that may explain a situation. This imposes a high cognitive load on analysts, and there are few automated tools to aid them in their task. In this paper, we present an agent-based tool to help analysts in acquiring, evaluating and interpreting information in collaboration with others. Agents assist analysts in reasoning with different types of evidence to identify what happened and why, what is credible, and how to obtain further evidence. Argumentation schemes lie at the heart of the tool, and sensemaking agents assist analysts in structuring evidence and identifying plausible hypotheses. A crowdsourcing agent is used to reason about structured information explicitly obtained from groups of contributors, and provenance is used to assess the credibility of hypotheses based on the origins of the supporting information.",

keywords = "Innovative Applications, Aerospace and Defense, Argumentation, Collective intelligence, Human-agent Interaction",

author = "Alice Toniolo and Norman, {Timothy J} and Etuk, {Anthony Anietie} and Federico Cerutti and Ouyang, {Robin Wentao} and Mani Srivastava and Nir Oren and Timothy Dropps and Allen, {John A.} and Paul Sullivan",

year = "2015",

language = "English",

pages = "781--789",

booktitle = "Proceedings of the Fourteenth International Conference on Autonomous Agents and Multiagent Systems",

publisher = "ACM",

note = "14th International Conference on Autonomous Agents and Multiagent Systems<br/>Systems , AAMAS 2015 ; Conference date: 04-05-2015 Through 08-05-2015",

}

TY - GEN

T1 - Supporting Reasoning with Different Types of Evidence in Intelligence Analysis

AU - Toniolo, Alice

AU - Norman, Timothy J

AU - Etuk, Anthony Anietie

AU - Cerutti, Federico

AU - Ouyang, Robin Wentao

AU - Srivastava, Mani

AU - Oren, Nir

AU - Dropps, Timothy

AU - Allen, John A.

AU - Sullivan, Paul

PY - 2015

Y1 - 2015

N2 - The aim of intelligence analysis is to make sense of information that is often conflicting or incomplete, and to weigh competing hypotheses that may explain a situation. This imposes a high cognitive load on analysts, and there are few automated tools to aid them in their task. In this paper, we present an agent-based tool to help analysts in acquiring, evaluating and interpreting information in collaboration with others. Agents assist analysts in reasoning with different types of evidence to identify what happened and why, what is credible, and how to obtain further evidence. Argumentation schemes lie at the heart of the tool, and sensemaking agents assist analysts in structuring evidence and identifying plausible hypotheses. A crowdsourcing agent is used to reason about structured information explicitly obtained from groups of contributors, and provenance is used to assess the credibility of hypotheses based on the origins of the supporting information.

AB - The aim of intelligence analysis is to make sense of information that is often conflicting or incomplete, and to weigh competing hypotheses that may explain a situation. This imposes a high cognitive load on analysts, and there are few automated tools to aid them in their task. In this paper, we present an agent-based tool to help analysts in acquiring, evaluating and interpreting information in collaboration with others. Agents assist analysts in reasoning with different types of evidence to identify what happened and why, what is credible, and how to obtain further evidence. Argumentation schemes lie at the heart of the tool, and sensemaking agents assist analysts in structuring evidence and identifying plausible hypotheses. A crowdsourcing agent is used to reason about structured information explicitly obtained from groups of contributors, and provenance is used to assess the credibility of hypotheses based on the origins of the supporting information.

KW - Innovative Applications

KW - Aerospace and Defense

KW - Argumentation

KW - Collective intelligence

KW - Human-agent Interaction

M3 - Published conference contribution

SP - 781

EP - 789

BT - Proceedings of the Fourteenth International Conference on Autonomous Agents and Multiagent Systems

PB - ACM

T2 - 14th International Conference on Autonomous Agents and Multiagent Systems<br/>Systems

Y2 - 4 May 2015 through 8 May 2015

ER -

Supporting Reasoning with Different Types of Evidence in Intelligence Analysis

Abstract

Conference

Keywords

Access to Document

Fingerprint

Profiles

Nir Oren

Cite this