Who Wins the Game of Thrones? How Sentiments Improve the Prediction of Candidate Choice

Chaehan So

doi:10.1109/ICAIIC48513.2020.9065248

Who Wins the Game of Thrones? How Sentiments Improve the Prediction of Candidate Choice

Chaehan So

Humanities, Arts, and Social Sciences Field

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

Abstract

This paper analyzes how candidate choice prediction improves by different psychological predictors. To investigate this question, it collected an original survey dataset featuring the popular TV series 'Game of Thrones'. The respondents answered which character they anticipated to win in the final episode of the series, and explained their choice of the final candidate in free text from which sentiments were extracted. These sentiments were compared to feature sets derived from candidate likeability and candidate personality ratings. In our benchmarking of 10-fold cross-validation in 100 repetitions, all feature sets except the likeability ratings yielded a 10-11% improvement in accuracy on the holdout set over the base model. Treating the class imbalance with synthetic minority oversampling (SMOTE) increased holdout set performance by 20-34% but surprisingly not testing set performance. Taken together, our study provides a quantified estimation of the additional predictive value of psychological predictors. Likeability ratings were clearly outperformed by the feature sets based on personality, emotional valence, and basic emotions.

Original language	English
Title of host publication	2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	330-335
Number of pages	6
ISBN (Electronic)	9781728149851
DOIs	https://doi.org/10.1109/ICAIIC48513.2020.9065248
Publication status	Published - 2020 Feb
Event	2nd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020 - Fukuoka, Japan Duration: 2020 Feb 19 → 2020 Feb 21

Publication series

Name	2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020

Conference

Conference	2nd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020
Country/Territory	Japan
City	Fukuoka
Period	20/2/19 → 20/2/21

Bibliographical note

Funding Information:
The author would like to thank Takeshi Teshima, Tokyo University, for the interesting discussion on an earlier draft of this paper. This research was supported by the Yonsei University Faculty Research Fund of 2019-22-0199.

Funding Information:
ACKNOWLEDGMENT The author would like to thank Takeshi Teshima, Tokyo University, for the interesting discussion on an earlier draft of this paper. This research was supported by the Yonsei University Faculty Research Fund of 2019-22-0199.

Publisher Copyright:
© 2020 IEEE.

All Science Journal Classification (ASJC) codes

Information Systems and Management
Artificial Intelligence
Computer Networks and Communications
Computer Vision and Pattern Recognition
Information Systems
Signal Processing

Access to Document

10.1109/ICAIIC48513.2020.9065248

Cite this

So, C. (2020). Who Wins the Game of Thrones? How Sentiments Improve the Prediction of Candidate Choice. In 2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020 (pp. 330-335). [9065248] (2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICAIIC48513.2020.9065248

So, Chaehan. / Who Wins the Game of Thrones? How Sentiments Improve the Prediction of Candidate Choice. 2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 330-335 (2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020).

@inproceedings{e78c7e0f73ba49659c572637cf1575a8,

title = "Who Wins the Game of Thrones? How Sentiments Improve the Prediction of Candidate Choice",

abstract = "This paper analyzes how candidate choice prediction improves by different psychological predictors. To investigate this question, it collected an original survey dataset featuring the popular TV series 'Game of Thrones'. The respondents answered which character they anticipated to win in the final episode of the series, and explained their choice of the final candidate in free text from which sentiments were extracted. These sentiments were compared to feature sets derived from candidate likeability and candidate personality ratings. In our benchmarking of 10-fold cross-validation in 100 repetitions, all feature sets except the likeability ratings yielded a 10-11% improvement in accuracy on the holdout set over the base model. Treating the class imbalance with synthetic minority oversampling (SMOTE) increased holdout set performance by 20-34% but surprisingly not testing set performance. Taken together, our study provides a quantified estimation of the additional predictive value of psychological predictors. Likeability ratings were clearly outperformed by the feature sets based on personality, emotional valence, and basic emotions.",

author = "Chaehan So",

note = "Funding Information: The author would like to thank Takeshi Teshima, Tokyo University, for the interesting discussion on an earlier draft of this paper. This research was supported by the Yonsei University Faculty Research Fund of 2019-22-0199. Funding Information: ACKNOWLEDGMENT The author would like to thank Takeshi Teshima, Tokyo University, for the interesting discussion on an earlier draft of this paper. This research was supported by the Yonsei University Faculty Research Fund of 2019-22-0199. Publisher Copyright: {\textcopyright} 2020 IEEE.; 2nd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020 ; Conference date: 19-02-2020 Through 21-02-2020",

year = "2020",

month = feb,

doi = "10.1109/ICAIIC48513.2020.9065248",

language = "English",

series = "2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "330--335",

booktitle = "2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020",

address = "United States",

}

So, C 2020, Who Wins the Game of Thrones? How Sentiments Improve the Prediction of Candidate Choice. in 2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020., 9065248, 2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020, Institute of Electrical and Electronics Engineers Inc., pp. 330-335, 2nd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020, Fukuoka, Japan, 20/2/19. https://doi.org/10.1109/ICAIIC48513.2020.9065248

Who Wins the Game of Thrones? How Sentiments Improve the Prediction of Candidate Choice. / So, Chaehan.

2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 330-335 9065248 (2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020).

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

TY - GEN

T1 - Who Wins the Game of Thrones? How Sentiments Improve the Prediction of Candidate Choice

AU - So, Chaehan

N1 - Funding Information: The author would like to thank Takeshi Teshima, Tokyo University, for the interesting discussion on an earlier draft of this paper. This research was supported by the Yonsei University Faculty Research Fund of 2019-22-0199. Funding Information: ACKNOWLEDGMENT The author would like to thank Takeshi Teshima, Tokyo University, for the interesting discussion on an earlier draft of this paper. This research was supported by the Yonsei University Faculty Research Fund of 2019-22-0199. Publisher Copyright: © 2020 IEEE.

PY - 2020/2

Y1 - 2020/2

N2 - This paper analyzes how candidate choice prediction improves by different psychological predictors. To investigate this question, it collected an original survey dataset featuring the popular TV series 'Game of Thrones'. The respondents answered which character they anticipated to win in the final episode of the series, and explained their choice of the final candidate in free text from which sentiments were extracted. These sentiments were compared to feature sets derived from candidate likeability and candidate personality ratings. In our benchmarking of 10-fold cross-validation in 100 repetitions, all feature sets except the likeability ratings yielded a 10-11% improvement in accuracy on the holdout set over the base model. Treating the class imbalance with synthetic minority oversampling (SMOTE) increased holdout set performance by 20-34% but surprisingly not testing set performance. Taken together, our study provides a quantified estimation of the additional predictive value of psychological predictors. Likeability ratings were clearly outperformed by the feature sets based on personality, emotional valence, and basic emotions.

AB - This paper analyzes how candidate choice prediction improves by different psychological predictors. To investigate this question, it collected an original survey dataset featuring the popular TV series 'Game of Thrones'. The respondents answered which character they anticipated to win in the final episode of the series, and explained their choice of the final candidate in free text from which sentiments were extracted. These sentiments were compared to feature sets derived from candidate likeability and candidate personality ratings. In our benchmarking of 10-fold cross-validation in 100 repetitions, all feature sets except the likeability ratings yielded a 10-11% improvement in accuracy on the holdout set over the base model. Treating the class imbalance with synthetic minority oversampling (SMOTE) increased holdout set performance by 20-34% but surprisingly not testing set performance. Taken together, our study provides a quantified estimation of the additional predictive value of psychological predictors. Likeability ratings were clearly outperformed by the feature sets based on personality, emotional valence, and basic emotions.

UR - http://www.scopus.com/inward/record.url?scp=85084055248&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85084055248&partnerID=8YFLogxK

U2 - 10.1109/ICAIIC48513.2020.9065248

DO - 10.1109/ICAIIC48513.2020.9065248

M3 - Conference contribution

AN - SCOPUS:85084055248

T3 - 2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020

SP - 330

EP - 335

BT - 2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020

Y2 - 19 February 2020 through 21 February 2020

ER -

So C. Who Wins the Game of Thrones? How Sentiments Improve the Prediction of Candidate Choice. In 2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020. Institute of Electrical and Electronics Engineers Inc. 2020. p. 330-335. 9065248. (2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020). doi: 10.1109/ICAIIC48513.2020.9065248

Who Wins the Game of Thrones? How Sentiments Improve the Prediction of Candidate Choice

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this