Creating a Sentiment Lexicon with Game-Specific Words for Analyzing NPC Dialogue in The Elder Scrolls V: Skyrim

Thérèse Bergsma; Judith van Stegeren; Mariet  Theune

Creating a Sentiment Lexicon with Game-Specific Words for Analyzing NPC Dialogue in The Elder Scrolls V: Skyrim

Thérèse Bergsma, Judith van Stegeren, Mariet Theune

Human Media Interaction

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

113 Downloads (Pure)

Abstract

A weak point of rule-based sentiment analysis systems is that the underlying sentiment lexicons are often not adapted to the domain of the text we want to analyze. We created a game-specific sentiment lexicon for video game Skyrim based on the E-ANEW word list and a dataset of Skyrim's in-game documents. We calculated sentiment ratings for NPC dialogue using both our lexicon and E-ANEW and compared the resulting sentiment ratings to those of human raters. Both lexicons perform comparably well on our evaluation dialogues, but the game-specific extension performs slightly better on the dominance dimension for dialogue segments and the arousal dimension for full dialogues. To our knowledge, this is the first time that a sentiment analysis lexicon has been adapted to the video game domain.

Original language	English
Title of host publication	Proceedings of the LREC 2020 Workshop Games and Natural Language Processing
Editors	Stephanie M. Lukin
Place of Publication	Marseille, France
Publisher	European Language Resources Association (ELRA)
Pages	1-9
ISBN (Print)	979-10-95546-60-3
Publication status	Published - May 2020
Event	5th Games and Natural Language Processing Workshop, GAMNLP 2020 - Marseille, France Duration: 11 May 2020 → 11 May 2020 Conference number: 5

Workshop

Workshop	5th Games and Natural Language Processing Workshop, GAMNLP 2020
Abbreviated title	GAMNLP 2020
Country/Territory	France
City	Marseille
Period	11/05/20 → 11/05/20

Keywords

Sentiment analysis
sentiment lexicon
ANEW
Video games
Dialogue
Skyrim
The Elder Scrolls
E-ANEW

Access to Document

ArticleFinal published version, 225 KBLicence: CC BY-NC

https://www.aclweb.org/anthology/2020.gamnlp-1.1/Licence: CC BY-NC

Cite this

Bergsma, T., van Stegeren, J., & Theune, M. (2020). Creating a Sentiment Lexicon with Game-Specific Words for Analyzing NPC Dialogue in The Elder Scrolls V: Skyrim. In S. M. Lukin (Ed.), Proceedings of the LREC 2020 Workshop Games and Natural Language Processing (pp. 1-9). European Language Resources Association (ELRA). https://www.aclweb.org/anthology/2020.gamnlp-1.1/

@inproceedings{d0151d6a69ff4266b040c540161f0e1f,

title = "Creating a Sentiment Lexicon with Game-Specific Words for Analyzing NPC Dialogue in The Elder Scrolls V: Skyrim",

abstract = "A weak point of rule-based sentiment analysis systems is that the underlying sentiment lexicons are often not adapted to the domain of the text we want to analyze. We created a game-specific sentiment lexicon for video game Skyrim based on the E-ANEW word list and a dataset of Skyrim's in-game documents. We calculated sentiment ratings for NPC dialogue using both our lexicon and E-ANEW and compared the resulting sentiment ratings to those of human raters. Both lexicons perform comparably well on our evaluation dialogues, but the game-specific extension performs slightly better on the dominance dimension for dialogue segments and the arousal dimension for full dialogues. To our knowledge, this is the first time that a sentiment analysis lexicon has been adapted to the video game domain.",

keywords = "Sentiment analysis, sentiment lexicon, ANEW, Video games, Dialogue, Skyrim, The Elder Scrolls, E-ANEW",

author = "Th{\'e}r{\`e}se Bergsma and {van Stegeren}, Judith and Mariet Theune",

year = "2020",

month = may,

language = "English",

isbn = "979-10-95546-60-3",

pages = "1--9",

editor = "Lukin, {Stephanie M.}",

booktitle = "Proceedings of the LREC 2020 Workshop Games and Natural Language Processing",

publisher = "European Language Resources Association (ELRA)",

note = "5th Games and Natural Language Processing Workshop, GAMNLP 2020, GAMNLP 2020 ; Conference date: 11-05-2020 Through 11-05-2020",

}

Bergsma, T, van Stegeren, J & Theune, M 2020, Creating a Sentiment Lexicon with Game-Specific Words for Analyzing NPC Dialogue in The Elder Scrolls V: Skyrim. in SM Lukin (ed.), Proceedings of the LREC 2020 Workshop Games and Natural Language Processing. European Language Resources Association (ELRA), Marseille, France, pp. 1-9, 5th Games and Natural Language Processing Workshop, GAMNLP 2020, Marseille, France, 11/05/20. <https://www.aclweb.org/anthology/2020.gamnlp-1.1/>

Creating a Sentiment Lexicon with Game-Specific Words for Analyzing NPC Dialogue in The Elder Scrolls V: Skyrim. / Bergsma, Thérèse; van Stegeren, Judith; Theune, Mariet .
Proceedings of the LREC 2020 Workshop Games and Natural Language Processing. ed. / Stephanie M. Lukin. Marseille, France: European Language Resources Association (ELRA), 2020. p. 1-9.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Creating a Sentiment Lexicon with Game-Specific Words for Analyzing NPC Dialogue in The Elder Scrolls V: Skyrim

AU - Bergsma, Thérèse

AU - van Stegeren, Judith

AU - Theune, Mariet

N1 - Conference code: 5

PY - 2020/5

Y1 - 2020/5

N2 - A weak point of rule-based sentiment analysis systems is that the underlying sentiment lexicons are often not adapted to the domain of the text we want to analyze. We created a game-specific sentiment lexicon for video game Skyrim based on the E-ANEW word list and a dataset of Skyrim's in-game documents. We calculated sentiment ratings for NPC dialogue using both our lexicon and E-ANEW and compared the resulting sentiment ratings to those of human raters. Both lexicons perform comparably well on our evaluation dialogues, but the game-specific extension performs slightly better on the dominance dimension for dialogue segments and the arousal dimension for full dialogues. To our knowledge, this is the first time that a sentiment analysis lexicon has been adapted to the video game domain.

AB - A weak point of rule-based sentiment analysis systems is that the underlying sentiment lexicons are often not adapted to the domain of the text we want to analyze. We created a game-specific sentiment lexicon for video game Skyrim based on the E-ANEW word list and a dataset of Skyrim's in-game documents. We calculated sentiment ratings for NPC dialogue using both our lexicon and E-ANEW and compared the resulting sentiment ratings to those of human raters. Both lexicons perform comparably well on our evaluation dialogues, but the game-specific extension performs slightly better on the dominance dimension for dialogue segments and the arousal dimension for full dialogues. To our knowledge, this is the first time that a sentiment analysis lexicon has been adapted to the video game domain.

KW - Sentiment analysis

KW - sentiment lexicon

KW - ANEW

KW - Video games

KW - Dialogue

KW - Skyrim

KW - The Elder Scrolls

KW - E-ANEW

M3 - Conference contribution

SN - 979-10-95546-60-3

SP - 1

EP - 9

BT - Proceedings of the LREC 2020 Workshop Games and Natural Language Processing

A2 - Lukin, Stephanie M.

PB - European Language Resources Association (ELRA)

CY - Marseille, France

T2 - 5th Games and Natural Language Processing Workshop, GAMNLP 2020

Y2 - 11 May 2020 through 11 May 2020

ER -

Creating a Sentiment Lexicon with Game-Specific Words for Analyzing NPC Dialogue in The Elder Scrolls V: Skyrim

Abstract

Workshop

Keywords

Access to Document

Fingerprint

Cite this