Five-Dimensional Sentiment Analysis of Corpora, Documents and Words

Timo Honkela; Jaakko Korhonen; Krista Lagus; Esa Saarinen

doi:10.1007/978-3-319-07695-9_20

Five-Dimensional Sentiment Analysis of Corpora, Documents and Words

Timo Honkela^*, Jaakko Korhonen, Krista Lagus, Esa Saarinen

^*Corresponding author for this work

Department of Industrial Engineering and Management

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

9 Citations (Scopus)

326 Downloads (Pure)

Abstract

Sentiment analysis has become a widely used approach to assess the emotional content of written documents such as customer feedback. In positive psychology research, the typical one-dimensional analysis framework has been extended to include five dimensions. This five-dimensional model, PERMA, enables a fine-grained analysis of written texts. We propose an approach in which this model, statistical analysis and the self-organizing map are used. We analyze corpora from various genres. A hybrid methodology that uses the self-organizing maps algorithm and human judgment is suggested for expanding the PERMA lexicon. This vocabulary expansion can be useful for English but it is potentially even more crucial in the case of other languages for which the lexicon is not readily available. The challenges and solutions related to the text mining of texts written in a morphologically complex language such as Finnish are also considered.

Original language	English
Title of host publication	Advances in Self-Organizing Maps and Learning Vector Quantization - Proceedings of the 10th International Workshop, WSOM 2014
Publisher	Springer
Pages	209-218
Number of pages	10
ISBN (Print)	9783319076942
DOIs	https://doi.org/10.1007/978-3-319-07695-9_20
Publication status	Published - 2014
MoE publication type	A4 Conference publication
Event	Workshop on Self-Organizing Maps - Mittweida, Germany Duration: 2 Jul 2014 → 4 Jul 2014 Conference number: 10

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	295
ISSN (Print)	21945357

Workshop

Workshop	Workshop on Self-Organizing Maps
Abbreviated title	WSOM
Country/Territory	Germany
City	Mittweida
Period	02/07/2014 → 04/07/2014

Keywords

education
independent component analysis
life-philosophical lecturing
natural language processing
positive psychology
self-organizing map
Text mining

Access to Document

10.1007/978-3-319-07695-9_20

Honkela14permaAccepted author manuscript, 203 KB

Cite this

Honkela, T., Korhonen, J., Lagus, K., & Saarinen, E. (2014). Five-Dimensional Sentiment Analysis of Corpora, Documents and Words. In Advances in Self-Organizing Maps and Learning Vector Quantization - Proceedings of the 10th International Workshop, WSOM 2014 (pp. 209-218). (Advances in Intelligent Systems and Computing; Vol. 295). Springer. https://doi.org/10.1007/978-3-319-07695-9_20

@inproceedings{4f14ec40d6af422db294e05700691a22,

title = "Five-Dimensional Sentiment Analysis of Corpora, Documents and Words",

abstract = "Sentiment analysis has become a widely used approach to assess the emotional content of written documents such as customer feedback. In positive psychology research, the typical one-dimensional analysis framework has been extended to include five dimensions. This five-dimensional model, PERMA, enables a fine-grained analysis of written texts. We propose an approach in which this model, statistical analysis and the self-organizing map are used. We analyze corpora from various genres. A hybrid methodology that uses the self-organizing maps algorithm and human judgment is suggested for expanding the PERMA lexicon. This vocabulary expansion can be useful for English but it is potentially even more crucial in the case of other languages for which the lexicon is not readily available. The challenges and solutions related to the text mining of texts written in a morphologically complex language such as Finnish are also considered.",

keywords = "education, independent component analysis, life-philosophical lecturing, natural language processing, positive psychology, self-organizing map, Text mining",

author = "Timo Honkela and Jaakko Korhonen and Krista Lagus and Esa Saarinen",

year = "2014",

doi = "10.1007/978-3-319-07695-9_20",

language = "English",

isbn = "9783319076942",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer",

pages = "209--218",

booktitle = "Advances in Self-Organizing Maps and Learning Vector Quantization - Proceedings of the 10th International Workshop, WSOM 2014",

address = "Germany",

note = "Workshop on Self-Organizing Maps, WSOM ; Conference date: 02-07-2014 Through 04-07-2014",

}

Honkela, T, Korhonen, J, Lagus, K & Saarinen, E 2014, Five-Dimensional Sentiment Analysis of Corpora, Documents and Words. in Advances in Self-Organizing Maps and Learning Vector Quantization - Proceedings of the 10th International Workshop, WSOM 2014. Advances in Intelligent Systems and Computing, vol. 295, Springer, pp. 209-218, Workshop on Self-Organizing Maps, Mittweida, Germany, 02/07/2014. https://doi.org/10.1007/978-3-319-07695-9_20

Five-Dimensional Sentiment Analysis of Corpora, Documents and Words. / Honkela, Timo; Korhonen, Jaakko; Lagus, Krista et al.
Advances in Self-Organizing Maps and Learning Vector Quantization - Proceedings of the 10th International Workshop, WSOM 2014. Springer, 2014. p. 209-218 (Advances in Intelligent Systems and Computing; Vol. 295).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Five-Dimensional Sentiment Analysis of Corpora, Documents and Words

AU - Honkela, Timo

AU - Korhonen, Jaakko

AU - Lagus, Krista

AU - Saarinen, Esa

N1 - Conference code: 10

PY - 2014

Y1 - 2014

N2 - Sentiment analysis has become a widely used approach to assess the emotional content of written documents such as customer feedback. In positive psychology research, the typical one-dimensional analysis framework has been extended to include five dimensions. This five-dimensional model, PERMA, enables a fine-grained analysis of written texts. We propose an approach in which this model, statistical analysis and the self-organizing map are used. We analyze corpora from various genres. A hybrid methodology that uses the self-organizing maps algorithm and human judgment is suggested for expanding the PERMA lexicon. This vocabulary expansion can be useful for English but it is potentially even more crucial in the case of other languages for which the lexicon is not readily available. The challenges and solutions related to the text mining of texts written in a morphologically complex language such as Finnish are also considered.

AB - Sentiment analysis has become a widely used approach to assess the emotional content of written documents such as customer feedback. In positive psychology research, the typical one-dimensional analysis framework has been extended to include five dimensions. This five-dimensional model, PERMA, enables a fine-grained analysis of written texts. We propose an approach in which this model, statistical analysis and the self-organizing map are used. We analyze corpora from various genres. A hybrid methodology that uses the self-organizing maps algorithm and human judgment is suggested for expanding the PERMA lexicon. This vocabulary expansion can be useful for English but it is potentially even more crucial in the case of other languages for which the lexicon is not readily available. The challenges and solutions related to the text mining of texts written in a morphologically complex language such as Finnish are also considered.

KW - education

KW - independent component analysis

KW - life-philosophical lecturing

KW - natural language processing

KW - positive psychology

KW - self-organizing map

KW - Text mining

UR - http://www.scopus.com/inward/record.url?scp=84903549586&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-07695-9_20

DO - 10.1007/978-3-319-07695-9_20

M3 - Conference article in proceedings

AN - SCOPUS:84903549586

SN - 9783319076942

T3 - Advances in Intelligent Systems and Computing

SP - 209

EP - 218

BT - Advances in Self-Organizing Maps and Learning Vector Quantization - Proceedings of the 10th International Workshop, WSOM 2014

PB - Springer

T2 - Workshop on Self-Organizing Maps

Y2 - 2 July 2014 through 4 July 2014

ER -

Five-Dimensional Sentiment Analysis of Corpora, Documents and Words

Abstract

Publication series

Workshop

Keywords

Access to Document

Other files and links

Fingerprint

Cite this