Human misidentification in Turing tests

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

This paper presents some important issues on misidentification of human interlocutors in text-based communication during practical Turing tests. The study here presents transcripts in which human judges succumbed to theconfederate effect, misidentifying hidden human foils for machines. An attempt is made to assess the reasons for this. The practical Turing tests in question were held on 23 June 2012 at Bletchley Park, England. A selection of actual full transcripts from the tests is shown and an analysis is given in each case. As a result of these tests, conclusions are drawn with regard to the sort of strategies which can perhaps lead to erroneous conclusions when one is involved as an interrogator. Such results also serve to indicate conversational directions to avoid for those machine designers who wish to create a conversational entity that performs well on the Turing test.
Original languageEnglish
Pages (from-to)123-135
JournalJournal of Experimental & Theoretical Artificial Intelligence
Volume27
Issue number2
Early online date24 Jun 2014
DOIs
Publication statusPublished - 2015

Fingerprint

Turing
Metal foil
Communication
Bletchley Park
Sort
Human

Bibliographical note

This article is not available on the repository

Keywords

  • chatbots
  • confederate effect
  • practical Turing tests
  • imitation game
  • intelligence
  • philosophy of mind

Cite this

Human misidentification in Turing tests. / Warwick, Kevin; Shah, Huma.

In: Journal of Experimental & Theoretical Artificial Intelligence, Vol. 27, No. 2, 2015, p. 123-135.

Research output: Contribution to journalArticle

@article{e6ef8248f64f49629bece086ac123353,
title = "Human misidentification in Turing tests",
abstract = "This paper presents some important issues on misidentification of human interlocutors in text-based communication during practical Turing tests. The study here presents transcripts in which human judges succumbed to theconfederate effect, misidentifying hidden human foils for machines. An attempt is made to assess the reasons for this. The practical Turing tests in question were held on 23 June 2012 at Bletchley Park, England. A selection of actual full transcripts from the tests is shown and an analysis is given in each case. As a result of these tests, conclusions are drawn with regard to the sort of strategies which can perhaps lead to erroneous conclusions when one is involved as an interrogator. Such results also serve to indicate conversational directions to avoid for those machine designers who wish to create a conversational entity that performs well on the Turing test.",
keywords = "chatbots, confederate effect, practical Turing tests, imitation game, intelligence, philosophy of mind",
author = "Kevin Warwick and Huma Shah",
note = "This article is not available on the repository",
year = "2015",
doi = "10.1080/0952813X.2014.921734",
language = "English",
volume = "27",
pages = "123--135",
journal = "Journal of Experimental and Theoretical Artificial Intelligence",
issn = "0952-813X",
publisher = "Taylor & Francis",
number = "2",

}

TY - JOUR

T1 - Human misidentification in Turing tests

AU - Warwick, Kevin

AU - Shah, Huma

N1 - This article is not available on the repository

PY - 2015

Y1 - 2015

N2 - This paper presents some important issues on misidentification of human interlocutors in text-based communication during practical Turing tests. The study here presents transcripts in which human judges succumbed to theconfederate effect, misidentifying hidden human foils for machines. An attempt is made to assess the reasons for this. The practical Turing tests in question were held on 23 June 2012 at Bletchley Park, England. A selection of actual full transcripts from the tests is shown and an analysis is given in each case. As a result of these tests, conclusions are drawn with regard to the sort of strategies which can perhaps lead to erroneous conclusions when one is involved as an interrogator. Such results also serve to indicate conversational directions to avoid for those machine designers who wish to create a conversational entity that performs well on the Turing test.

AB - This paper presents some important issues on misidentification of human interlocutors in text-based communication during practical Turing tests. The study here presents transcripts in which human judges succumbed to theconfederate effect, misidentifying hidden human foils for machines. An attempt is made to assess the reasons for this. The practical Turing tests in question were held on 23 June 2012 at Bletchley Park, England. A selection of actual full transcripts from the tests is shown and an analysis is given in each case. As a result of these tests, conclusions are drawn with regard to the sort of strategies which can perhaps lead to erroneous conclusions when one is involved as an interrogator. Such results also serve to indicate conversational directions to avoid for those machine designers who wish to create a conversational entity that performs well on the Turing test.

KW - chatbots

KW - confederate effect

KW - practical Turing tests

KW - imitation game

KW - intelligence

KW - philosophy of mind

U2 - 10.1080/0952813X.2014.921734

DO - 10.1080/0952813X.2014.921734

M3 - Article

VL - 27

SP - 123

EP - 135

JO - Journal of Experimental and Theoretical Artificial Intelligence

JF - Journal of Experimental and Theoretical Artificial Intelligence

SN - 0952-813X

IS - 2

ER -