Semantic Clustering of Basic Emotion Sets

E. Y. Bann

Research output: Book/ReportOther report

Abstract

A plethora of words are used to describe the spectrum of human emotions, but how many emotions are there really, and how do they interact? Over the past few decades, several theories of emotion have been proposed, each based around the existence of a set of basic emotions, and each supported by an extensive variety of research including studies in facial expression, ethology, neurology and physiology. Here we present research based on
a theory that people transmit their understanding of emotions through the language they use surrounding emotion keywords. Using a labelled corpus of over 21,000 tweets, six of the basic emotion sets proposed in existing literature were analysed using Latent Semantic Clustering (LSC), evaluating the distinctiveness of the semantic meaning attached to the emotional label. We hypothesise that the more distinct the language is used to express a
certain emotion, then the more distinct the perception (including proprioception) of that emotion is, and thus more basic. This allows us to select the dimensions best representing the entire spectrum of emotion. We find that Ekman’s set, arguably the most frequently used for classifying emotions, is in fact the most semantically distinct overall. Next, taking
all analysed (that is, previously proposed) emotion terms into account, we determine the optimal semantically irreducible basic emotion set using an iterative LSC algorithm. Our newly-derived set (Accepting, Ashamed, Contempt, Interested, Joyful, Pleased, Sleepy, Stressed) generates a 6.1% increase in distinctiveness over Ekman’s set (Angry, Disgusted, Joyful, Sad, Scared). We also demonstrate how using LSC data can help visualise emotions. We introduce the concept of an Emotion Profile and briefly analyse
compound emotions both visually and mathematically.
LanguageEnglish
Place of PublicationBath, U. K.
PublisherDepartment of Computer Science, University of Bath
Number of pages118
StatusPublished - Jan 2013

Publication series

NameDepartment of Computer Science Technical Report Series
No.CSBU-2013-01
ISSN (Print)1740-9497

Fingerprint

Semantics
Physiology
Neurology
Clustering algorithms
Labels

Cite this

Bann, E. Y. (2013). Semantic Clustering of Basic Emotion Sets. (Department of Computer Science Technical Report Series; No. CSBU-2013-01). Bath, U. K.: Department of Computer Science, University of Bath.

Semantic Clustering of Basic Emotion Sets. / Bann, E. Y.

Bath, U. K. : Department of Computer Science, University of Bath, 2013. 118 p. (Department of Computer Science Technical Report Series; No. CSBU-2013-01).

Research output: Book/ReportOther report

Bann, EY 2013, Semantic Clustering of Basic Emotion Sets. Department of Computer Science Technical Report Series, no. CSBU-2013-01, Department of Computer Science, University of Bath, Bath, U. K.
Bann EY. Semantic Clustering of Basic Emotion Sets. Bath, U. K.: Department of Computer Science, University of Bath, 2013. 118 p. (Department of Computer Science Technical Report Series; CSBU-2013-01).
Bann, E. Y. / Semantic Clustering of Basic Emotion Sets. Bath, U. K. : Department of Computer Science, University of Bath, 2013. 118 p. (Department of Computer Science Technical Report Series; CSBU-2013-01).
@book{3ad82db4acbb469fbf2df06ce14834dd,
title = "Semantic Clustering of Basic Emotion Sets",
abstract = "A plethora of words are used to describe the spectrum of human emotions, but how many emotions are there really, and how do they interact? Over the past few decades, several theories of emotion have been proposed, each based around the existence of a set of basic emotions, and each supported by an extensive variety of research including studies in facial expression, ethology, neurology and physiology. Here we present research based ona theory that people transmit their understanding of emotions through the language they use surrounding emotion keywords. Using a labelled corpus of over 21,000 tweets, six of the basic emotion sets proposed in existing literature were analysed using Latent Semantic Clustering (LSC), evaluating the distinctiveness of the semantic meaning attached to the emotional label. We hypothesise that the more distinct the language is used to express acertain emotion, then the more distinct the perception (including proprioception) of that emotion is, and thus more basic. This allows us to select the dimensions best representing the entire spectrum of emotion. We find that Ekman’s set, arguably the most frequently used for classifying emotions, is in fact the most semantically distinct overall. Next, takingall analysed (that is, previously proposed) emotion terms into account, we determine the optimal semantically irreducible basic emotion set using an iterative LSC algorithm. Our newly-derived set (Accepting, Ashamed, Contempt, Interested, Joyful, Pleased, Sleepy, Stressed) generates a 6.1{\%} increase in distinctiveness over Ekman’s set (Angry, Disgusted, Joyful, Sad, Scared). We also demonstrate how using LSC data can help visualise emotions. We introduce the concept of an Emotion Profile and briefly analysecompound emotions both visually and mathematically.",
author = "Bann, {E. Y.}",
note = "Undergraduate Dissertation",
year = "2013",
month = "1",
language = "English",
series = "Department of Computer Science Technical Report Series",
publisher = "Department of Computer Science, University of Bath",
number = "CSBU-2013-01",

}

TY - BOOK

T1 - Semantic Clustering of Basic Emotion Sets

AU - Bann, E. Y.

N1 - Undergraduate Dissertation

PY - 2013/1

Y1 - 2013/1

N2 - A plethora of words are used to describe the spectrum of human emotions, but how many emotions are there really, and how do they interact? Over the past few decades, several theories of emotion have been proposed, each based around the existence of a set of basic emotions, and each supported by an extensive variety of research including studies in facial expression, ethology, neurology and physiology. Here we present research based ona theory that people transmit their understanding of emotions through the language they use surrounding emotion keywords. Using a labelled corpus of over 21,000 tweets, six of the basic emotion sets proposed in existing literature were analysed using Latent Semantic Clustering (LSC), evaluating the distinctiveness of the semantic meaning attached to the emotional label. We hypothesise that the more distinct the language is used to express acertain emotion, then the more distinct the perception (including proprioception) of that emotion is, and thus more basic. This allows us to select the dimensions best representing the entire spectrum of emotion. We find that Ekman’s set, arguably the most frequently used for classifying emotions, is in fact the most semantically distinct overall. Next, takingall analysed (that is, previously proposed) emotion terms into account, we determine the optimal semantically irreducible basic emotion set using an iterative LSC algorithm. Our newly-derived set (Accepting, Ashamed, Contempt, Interested, Joyful, Pleased, Sleepy, Stressed) generates a 6.1% increase in distinctiveness over Ekman’s set (Angry, Disgusted, Joyful, Sad, Scared). We also demonstrate how using LSC data can help visualise emotions. We introduce the concept of an Emotion Profile and briefly analysecompound emotions both visually and mathematically.

AB - A plethora of words are used to describe the spectrum of human emotions, but how many emotions are there really, and how do they interact? Over the past few decades, several theories of emotion have been proposed, each based around the existence of a set of basic emotions, and each supported by an extensive variety of research including studies in facial expression, ethology, neurology and physiology. Here we present research based ona theory that people transmit their understanding of emotions through the language they use surrounding emotion keywords. Using a labelled corpus of over 21,000 tweets, six of the basic emotion sets proposed in existing literature were analysed using Latent Semantic Clustering (LSC), evaluating the distinctiveness of the semantic meaning attached to the emotional label. We hypothesise that the more distinct the language is used to express acertain emotion, then the more distinct the perception (including proprioception) of that emotion is, and thus more basic. This allows us to select the dimensions best representing the entire spectrum of emotion. We find that Ekman’s set, arguably the most frequently used for classifying emotions, is in fact the most semantically distinct overall. Next, takingall analysed (that is, previously proposed) emotion terms into account, we determine the optimal semantically irreducible basic emotion set using an iterative LSC algorithm. Our newly-derived set (Accepting, Ashamed, Contempt, Interested, Joyful, Pleased, Sleepy, Stressed) generates a 6.1% increase in distinctiveness over Ekman’s set (Angry, Disgusted, Joyful, Sad, Scared). We also demonstrate how using LSC data can help visualise emotions. We introduce the concept of an Emotion Profile and briefly analysecompound emotions both visually and mathematically.

M3 - Other report

T3 - Department of Computer Science Technical Report Series

BT - Semantic Clustering of Basic Emotion Sets

PB - Department of Computer Science, University of Bath

CY - Bath, U. K.

ER -