Measuring cultural relativity of emotional valence and arousal using semantic clustering and Twitter

Eugene Y. Bann, Joanna J. Bryson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Researchers since at least Darwin have debated whether and to what extent emotions are universal or culture-dependent. How- ever, previous studies have primarily focused on facial expressions and on a limited set of emotions. Given that emotions have a substantial impact on human lives, evidence for cultural emotional relativity might be derived by applying distributional semantics techniques to a text corpus of self-reported behaviour. Here, we explore this idea by measuring the valence and arousal of the twelve most popular emotion keywords ex- pressed on the micro-blogging site Twitter. We do this in three geographical regions: Europe, Asia and North America. We demonstrate that in our sample, the valence and arousal levels of the same emotion keywords differ significantly with respect to these geographical regions — Europeans are, or at least present themselves as more positive and aroused, North Americans are more negative and Asians appear to be more positive but less aroused when compared to global valence and arousal levels of the same emotion keywords. Our work is the first in kind to programatically map large text corpora to a dimensional model of affect.
LanguageEnglish
Title of host publicationCOGSCI 2013
PublisherCognitive Science Society
Pages1809-1814
Number of pages6
ISBN (Print)9780976831891
StatusPublished - 1 Aug 2013
EventCogSci 2013: The 35th Annual Meeting of the Cognitive Science Society - Berlin, Germany
Duration: 30 Jul 20132 Aug 2013

Conference

ConferenceCogSci 2013: The 35th Annual Meeting of the Cognitive Science Society
CountryGermany
CityBerlin
Period30/07/132/08/13

Fingerprint

twitter
emotion
semantics
facial expression
present
evidence

Cite this

Bann, E. Y., & Bryson, J. J. (2013). Measuring cultural relativity of emotional valence and arousal using semantic clustering and Twitter. In COGSCI 2013 (pp. 1809-1814). Cognitive Science Society.

Measuring cultural relativity of emotional valence and arousal using semantic clustering and Twitter. / Bann, Eugene Y.; Bryson, Joanna J.

COGSCI 2013. Cognitive Science Society, 2013. p. 1809-1814.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bann, EY & Bryson, JJ 2013, Measuring cultural relativity of emotional valence and arousal using semantic clustering and Twitter. in COGSCI 2013. Cognitive Science Society, pp. 1809-1814, CogSci 2013: The 35th Annual Meeting of the Cognitive Science Society, Berlin, Germany, 30/07/13.
@inproceedings{fbb189dc821346f1b23b42895a0d140f,
title = "Measuring cultural relativity of emotional valence and arousal using semantic clustering and Twitter",
abstract = "Researchers since at least Darwin have debated whether and to what extent emotions are universal or culture-dependent. How- ever, previous studies have primarily focused on facial expressions and on a limited set of emotions. Given that emotions have a substantial impact on human lives, evidence for cultural emotional relativity might be derived by applying distributional semantics techniques to a text corpus of self-reported behaviour. Here, we explore this idea by measuring the valence and arousal of the twelve most popular emotion keywords ex- pressed on the micro-blogging site Twitter. We do this in three geographical regions: Europe, Asia and North America. We demonstrate that in our sample, the valence and arousal levels of the same emotion keywords differ significantly with respect to these geographical regions — Europeans are, or at least present themselves as more positive and aroused, North Americans are more negative and Asians appear to be more positive but less aroused when compared to global valence and arousal levels of the same emotion keywords. Our work is the first in kind to programatically map large text corpora to a dimensional model of affect.",
author = "Bann, {Eugene Y.} and Bryson, {Joanna J.}",
year = "2013",
month = "8",
day = "1",
language = "English",
isbn = "9780976831891",
pages = "1809--1814",
booktitle = "COGSCI 2013",
publisher = "Cognitive Science Society",

}

TY - GEN

T1 - Measuring cultural relativity of emotional valence and arousal using semantic clustering and Twitter

AU - Bann,Eugene Y.

AU - Bryson,Joanna J.

PY - 2013/8/1

Y1 - 2013/8/1

N2 - Researchers since at least Darwin have debated whether and to what extent emotions are universal or culture-dependent. How- ever, previous studies have primarily focused on facial expressions and on a limited set of emotions. Given that emotions have a substantial impact on human lives, evidence for cultural emotional relativity might be derived by applying distributional semantics techniques to a text corpus of self-reported behaviour. Here, we explore this idea by measuring the valence and arousal of the twelve most popular emotion keywords ex- pressed on the micro-blogging site Twitter. We do this in three geographical regions: Europe, Asia and North America. We demonstrate that in our sample, the valence and arousal levels of the same emotion keywords differ significantly with respect to these geographical regions — Europeans are, or at least present themselves as more positive and aroused, North Americans are more negative and Asians appear to be more positive but less aroused when compared to global valence and arousal levels of the same emotion keywords. Our work is the first in kind to programatically map large text corpora to a dimensional model of affect.

AB - Researchers since at least Darwin have debated whether and to what extent emotions are universal or culture-dependent. How- ever, previous studies have primarily focused on facial expressions and on a limited set of emotions. Given that emotions have a substantial impact on human lives, evidence for cultural emotional relativity might be derived by applying distributional semantics techniques to a text corpus of self-reported behaviour. Here, we explore this idea by measuring the valence and arousal of the twelve most popular emotion keywords ex- pressed on the micro-blogging site Twitter. We do this in three geographical regions: Europe, Asia and North America. We demonstrate that in our sample, the valence and arousal levels of the same emotion keywords differ significantly with respect to these geographical regions — Europeans are, or at least present themselves as more positive and aroused, North Americans are more negative and Asians appear to be more positive but less aroused when compared to global valence and arousal levels of the same emotion keywords. Our work is the first in kind to programatically map large text corpora to a dimensional model of affect.

UR - http://cognitivesciencesociety.org/

UR - http://www.cs.bath.ac.uk/~jjb/ftp/BannCogSci13.pdf

M3 - Conference contribution

SN - 9780976831891

SP - 1809

EP - 1814

BT - COGSCI 2013

PB - Cognitive Science Society

ER -