Symptoms of cognitive load in interactions with a dialogue system

José Lopes; Katrin Lohan; Helen Hastie

doi:10.1145/3279810.3279851

Symptoms of cognitive load in interactions with a dialogue system

José Lopes, Katrin Lohan, Helen Hastie

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

Abstract

Humans adapt their behaviour to the perceived cognitive load of their dialogue partner, for example, delaying non-essential information. We propose that spoken dialogue systems should do the same, particularly in high-stakes scenarios, such as emergency response. In this paper, we provide a summary of the prosodic, turn-taking and other linguistic symptoms of cognitive load analysed in the literature. We then apply these features to a single corpus in the restaurant-finding domain and propose new symptoms that are evidenced through interaction with the dialogue system, including utterance entropy, speech recognition confidence, as well as others based on dialogue acts.

Original language	English
Title of host publication	Proceedings of the Workshop on Modeling Cognitive Processes from Multimodal Data
Place of Publication	United States
Publisher	ACM Association for Computing Machinery
Pages	1-5
ISBN (Electronic)	9781450360722
DOIs	https://doi.org/10.1145/3279810.3279851
Publication status	Published - 16 Oct 2018
Event	Workshop on Modeling Cognitive Processes from Multimodal Data 2018 - Boulder, United States Duration: 16 Oct 2018 → 16 Oct 2018 https://www.uni-bremen.de/csl/icmi-2018-mcpmd.html

Conference

Conference	Workshop on Modeling Cognitive Processes from Multimodal Data 2018
Abbreviated title	ICMI 2018
Country/Territory	United States
City	Boulder
Period	16/10/18 → 16/10/18
Internet address	https://www.uni-bremen.de/csl/icmi-2018-mcpmd.html

Keywords / Materials (for Non-textual outputs)

cognitive load
multi-modal Systems
spoken dialogue systems

Access to Document

10.1145/3279810.3279851Licence: All Rights Reserved

https://dl.acm.org/doi/10.1145/3279810.3279851Licence: All Rights Reserved

Cite this

@inproceedings{80a683a8aff044bc87c74ea68c663f2b,

title = "Symptoms of cognitive load in interactions with a dialogue system",

abstract = "Humans adapt their behaviour to the perceived cognitive load of their dialogue partner, for example, delaying non-essential information. We propose that spoken dialogue systems should do the same, particularly in high-stakes scenarios, such as emergency response. In this paper, we provide a summary of the prosodic, turn-taking and other linguistic symptoms of cognitive load analysed in the literature. We then apply these features to a single corpus in the restaurant-finding domain and propose new symptoms that are evidenced through interaction with the dialogue system, including utterance entropy, speech recognition confidence, as well as others based on dialogue acts.",

keywords = "cognitive load, multi-modal Systems, spoken dialogue systems",

author = "Jos{\'e} Lopes and Katrin Lohan and Helen Hastie",

note = "We would like to thank Dr. Milica Ga{\v s}i{\'c} and the authors of [8] for access to their dataset and assistance. This research was funded by EPSRC ORCA Hub (EP/R026173/1, 2017-2021); RAEng/Leverhulme Trust Senior Research Fellowship Scheme (Hastie/LTSRF1617/13/37).; Workshop on Modeling Cognitive Processes from Multimodal Data 2018, ICMI 2018 ; Conference date: 16-10-2018 Through 16-10-2018",

year = "2018",

month = oct,

day = "16",

doi = "10.1145/3279810.3279851",

language = "English",

pages = "1--5",

booktitle = "Proceedings of the Workshop on Modeling Cognitive Processes from Multimodal Data",

publisher = "ACM Association for Computing Machinery",

url = "https://www.uni-bremen.de/csl/icmi-2018-mcpmd.html",

}

Lopes, J, Lohan, K & Hastie, H 2018, Symptoms of cognitive load in interactions with a dialogue system. in Proceedings of the Workshop on Modeling Cognitive Processes from Multimodal Data., 4, ACM Association for Computing Machinery, United States, pp. 1-5, Workshop on Modeling Cognitive Processes from Multimodal Data 2018, Boulder, Colorado, United States, 16/10/18. https://doi.org/10.1145/3279810.3279851

TY - GEN

T1 - Symptoms of cognitive load in interactions with a dialogue system

AU - Lopes, José

AU - Lohan, Katrin

AU - Hastie, Helen

N1 - We would like to thank Dr. Milica Gašić and the authors of [8] for access to their dataset and assistance. This research was funded by EPSRC ORCA Hub (EP/R026173/1, 2017-2021); RAEng/Leverhulme Trust Senior Research Fellowship Scheme (Hastie/LTSRF1617/13/37).

PY - 2018/10/16

Y1 - 2018/10/16

N2 - Humans adapt their behaviour to the perceived cognitive load of their dialogue partner, for example, delaying non-essential information. We propose that spoken dialogue systems should do the same, particularly in high-stakes scenarios, such as emergency response. In this paper, we provide a summary of the prosodic, turn-taking and other linguistic symptoms of cognitive load analysed in the literature. We then apply these features to a single corpus in the restaurant-finding domain and propose new symptoms that are evidenced through interaction with the dialogue system, including utterance entropy, speech recognition confidence, as well as others based on dialogue acts.

AB - Humans adapt their behaviour to the perceived cognitive load of their dialogue partner, for example, delaying non-essential information. We propose that spoken dialogue systems should do the same, particularly in high-stakes scenarios, such as emergency response. In this paper, we provide a summary of the prosodic, turn-taking and other linguistic symptoms of cognitive load analysed in the literature. We then apply these features to a single corpus in the restaurant-finding domain and propose new symptoms that are evidenced through interaction with the dialogue system, including utterance entropy, speech recognition confidence, as well as others based on dialogue acts.

KW - cognitive load

KW - multi-modal Systems

KW - spoken dialogue systems

U2 - 10.1145/3279810.3279851

DO - 10.1145/3279810.3279851

M3 - Conference contribution

SP - 1

EP - 5

BT - Proceedings of the Workshop on Modeling Cognitive Processes from Multimodal Data

PB - ACM Association for Computing Machinery

CY - United States

T2 - Workshop on Modeling Cognitive Processes from Multimodal Data 2018

Y2 - 16 October 2018 through 16 October 2018

ER -

Symptoms of cognitive load in interactions with a dialogue system

Abstract

Conference

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Cite this