Formal Arguments, Preferences, and Natural Language Interfaces to Humans: an Empirical Evaluation

Federico Cerutti, Nava Tintarev, Nir Oren

Research output: Contribution to conferencePaper

28 Citations (Scopus)

Abstract

It has been claimed that computational models of argumentation
provide support for complex decision making activities in part due to the close alignment between their semantics and human intuition. In this paper we assess this claim by means of an experiment: people’s evaluation of formal arguments — presented in plain English — is compared to the conclusions obtained from argumentation semantics. Our results show a correspondence between the acceptability of arguments by human subjects and the justification status prescribed by the formal theory in the majority of the cases. However, post-
hoc analyses show that there are some significant deviations, which appear to arise from implicit knowledge regarding the domains in which evaluation took place. We argue that in order to create argumentation systems, designers must take implicit domain specific knowledge into account.
Original languageEnglish
Pages207-212
Number of pages6
Publication statusPublished - 2014
EventEuropean Conference on Artificial Intelligence (ECAI-2014) - Prague, United Kingdom
Duration: 18 Aug 201422 Aug 2014

Conference

ConferenceEuropean Conference on Artificial Intelligence (ECAI-2014)
CountryUnited Kingdom
CityPrague
Period18/08/1422/08/14

Fingerprint

Evaluation
Natural Language Interfaces
Argumentation
Intuition
Designer
Decision Making
Acceptability
Implicit Knowledge
Alignment
Computational Model
Human Subjects
Experiment
Justification
Deviation

Keywords

  • Measures
  • Intelligent Systems
  • Cognitive load
  • User-studies
  • Plans
  • Information visualization

Cite this

Cerutti, F., Tintarev, N., & Oren, N. (2014). Formal Arguments, Preferences, and Natural Language Interfaces to Humans: an Empirical Evaluation. 207-212. Paper presented at European Conference on Artificial Intelligence (ECAI-2014), Prague, United Kingdom.

Formal Arguments, Preferences, and Natural Language Interfaces to Humans : an Empirical Evaluation. / Cerutti, Federico; Tintarev, Nava; Oren, Nir.

2014. 207-212 Paper presented at European Conference on Artificial Intelligence (ECAI-2014), Prague, United Kingdom.

Research output: Contribution to conferencePaper

Cerutti, F, Tintarev, N & Oren, N 2014, 'Formal Arguments, Preferences, and Natural Language Interfaces to Humans: an Empirical Evaluation' Paper presented at European Conference on Artificial Intelligence (ECAI-2014), Prague, United Kingdom, 18/08/14 - 22/08/14, pp. 207-212.
Cerutti F, Tintarev N, Oren N. Formal Arguments, Preferences, and Natural Language Interfaces to Humans: an Empirical Evaluation. 2014. Paper presented at European Conference on Artificial Intelligence (ECAI-2014), Prague, United Kingdom.
Cerutti, Federico ; Tintarev, Nava ; Oren, Nir. / Formal Arguments, Preferences, and Natural Language Interfaces to Humans : an Empirical Evaluation. Paper presented at European Conference on Artificial Intelligence (ECAI-2014), Prague, United Kingdom.6 p.
@conference{c3814675409343c38e034d617204856c,
title = "Formal Arguments, Preferences, and Natural Language Interfaces to Humans: an Empirical Evaluation",
abstract = "It has been claimed that computational models of argumentationprovide support for complex decision making activities in part due to the close alignment between their semantics and human intuition. In this paper we assess this claim by means of an experiment: people’s evaluation of formal arguments — presented in plain English — is compared to the conclusions obtained from argumentation semantics. Our results show a correspondence between the acceptability of arguments by human subjects and the justification status prescribed by the formal theory in the majority of the cases. However, post-hoc analyses show that there are some significant deviations, which appear to arise from implicit knowledge regarding the domains in which evaluation took place. We argue that in order to create argumentation systems, designers must take implicit domain specific knowledge into account.",
keywords = "Measures, Intelligent Systems, Cognitive load, User-studies, Plans, Information visualization",
author = "Federico Cerutti and Nava Tintarev and Nir Oren",
year = "2014",
language = "English",
pages = "207--212",
note = "European Conference on Artificial Intelligence (ECAI-2014) ; Conference date: 18-08-2014 Through 22-08-2014",

}

TY - CONF

T1 - Formal Arguments, Preferences, and Natural Language Interfaces to Humans

T2 - an Empirical Evaluation

AU - Cerutti, Federico

AU - Tintarev, Nava

AU - Oren, Nir

PY - 2014

Y1 - 2014

N2 - It has been claimed that computational models of argumentationprovide support for complex decision making activities in part due to the close alignment between their semantics and human intuition. In this paper we assess this claim by means of an experiment: people’s evaluation of formal arguments — presented in plain English — is compared to the conclusions obtained from argumentation semantics. Our results show a correspondence between the acceptability of arguments by human subjects and the justification status prescribed by the formal theory in the majority of the cases. However, post-hoc analyses show that there are some significant deviations, which appear to arise from implicit knowledge regarding the domains in which evaluation took place. We argue that in order to create argumentation systems, designers must take implicit domain specific knowledge into account.

AB - It has been claimed that computational models of argumentationprovide support for complex decision making activities in part due to the close alignment between their semantics and human intuition. In this paper we assess this claim by means of an experiment: people’s evaluation of formal arguments — presented in plain English — is compared to the conclusions obtained from argumentation semantics. Our results show a correspondence between the acceptability of arguments by human subjects and the justification status prescribed by the formal theory in the majority of the cases. However, post-hoc analyses show that there are some significant deviations, which appear to arise from implicit knowledge regarding the domains in which evaluation took place. We argue that in order to create argumentation systems, designers must take implicit domain specific knowledge into account.

KW - Measures

KW - Intelligent Systems

KW - Cognitive load

KW - User-studies

KW - Plans

KW - Information visualization

M3 - Paper

SP - 207

EP - 212

ER -