Automatic assessment of dimensional affective content in Turkish multi-party chat messages

Eda Aydin Oktay; Koray Balci; Albert Ali Salah

doi:10.1145/2829966.2829972

Automatic assessment of dimensional affective content in Turkish multi-party chat messages

Eda Aydin Oktay, Koray Balci, Albert Ali Salah

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

Abstract

This study presents a model for affective text analysis of online multi-party chat records in Turkish language. Online chats have challenges like non-standard word usage, grammatical irregularities, abbreviation usage, and spelling mistakes. We propose several pre-processing steps to deal with these. We adapt an affective word dictionary from English to Turkish, and by expanding it, obtain 15,222 words with annotations for valence, arousal, and dominance. We also employ a list of abbreviations, emoticons, interjections, modifiers (intensifiers and diminishers), and other linguistic indicators to capture the overall affective state at the sentence level. Lastly, we recruit and train annotators to obtain affective ground truth, and assess the accuracy of the proposed rule-based approach on a multi-party chat database collected from an online gaming environment.

Original language	English
Title of host publication	ERM4CT 2015 - Proceedings of the International Workshop on Emotion Representations and Modelling for Companion Technologies, co-located with ICMI 2015
Publisher	Association for Computing Machinery
Pages	19-24
Number of pages	6
ISBN (Electronic)	9781450339889
DOIs	https://doi.org/10.1145/2829966.2829972
Publication status	Published - 13 Nov 2015
Externally published	Yes
Event	International Workshop on Emotion Representations and Modelling for Companion Technologies, ERM4CT 2015 - Seattle, United States Duration: 13 Nov 2015 → …

Conference

Conference	International Workshop on Emotion Representations and Modelling for Companion Technologies, ERM4CT 2015
Country/Territory	United States
City	Seattle
Period	13/11/15 → …

Keywords

Afiective computing
Chat
Computer games
Natural language processing
Turkish

Access to Document

10.1145/2829966.2829972

Cite this

Oktay, E. A., Balci, K., & Salah, A. A. (2015). Automatic assessment of dimensional affective content in Turkish multi-party chat messages. In ERM4CT 2015 - Proceedings of the International Workshop on Emotion Representations and Modelling for Companion Technologies, co-located with ICMI 2015 (pp. 19-24). Association for Computing Machinery. https://doi.org/10.1145/2829966.2829972

@inproceedings{5e2fa121cf524467ac7aba193e41e5fd,

title = "Automatic assessment of dimensional affective content in Turkish multi-party chat messages",

abstract = "This study presents a model for affective text analysis of online multi-party chat records in Turkish language. Online chats have challenges like non-standard word usage, grammatical irregularities, abbreviation usage, and spelling mistakes. We propose several pre-processing steps to deal with these. We adapt an affective word dictionary from English to Turkish, and by expanding it, obtain 15,222 words with annotations for valence, arousal, and dominance. We also employ a list of abbreviations, emoticons, interjections, modifiers (intensifiers and diminishers), and other linguistic indicators to capture the overall affective state at the sentence level. Lastly, we recruit and train annotators to obtain affective ground truth, and assess the accuracy of the proposed rule-based approach on a multi-party chat database collected from an online gaming environment.",

keywords = "Afiective computing, Chat, Computer games, Natural language processing, Turkish",

author = "Oktay, {Eda Aydin} and Koray Balci and Salah, {Albert Ali}",

year = "2015",

month = nov,

day = "13",

doi = "10.1145/2829966.2829972",

language = "English",

pages = "19--24",

booktitle = "ERM4CT 2015 - Proceedings of the International Workshop on Emotion Representations and Modelling for Companion Technologies, co-located with ICMI 2015",

publisher = "Association for Computing Machinery",

address = "United States",

note = "International Workshop on Emotion Representations and Modelling for Companion Technologies, ERM4CT 2015 ; Conference date: 13-11-2015",

}

Oktay, EA, Balci, K & Salah, AA 2015, Automatic assessment of dimensional affective content in Turkish multi-party chat messages. in ERM4CT 2015 - Proceedings of the International Workshop on Emotion Representations and Modelling for Companion Technologies, co-located with ICMI 2015. Association for Computing Machinery, pp. 19-24, International Workshop on Emotion Representations and Modelling for Companion Technologies, ERM4CT 2015, Seattle, United States, 13/11/15. https://doi.org/10.1145/2829966.2829972

Automatic assessment of dimensional affective content in Turkish multi-party chat messages. / Oktay, Eda Aydin; Balci, Koray; Salah, Albert Ali.
ERM4CT 2015 - Proceedings of the International Workshop on Emotion Representations and Modelling for Companion Technologies, co-located with ICMI 2015. Association for Computing Machinery, 2015. p. 19-24.

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

TY - GEN

T1 - Automatic assessment of dimensional affective content in Turkish multi-party chat messages

AU - Oktay, Eda Aydin

AU - Balci, Koray

AU - Salah, Albert Ali

PY - 2015/11/13

Y1 - 2015/11/13

N2 - This study presents a model for affective text analysis of online multi-party chat records in Turkish language. Online chats have challenges like non-standard word usage, grammatical irregularities, abbreviation usage, and spelling mistakes. We propose several pre-processing steps to deal with these. We adapt an affective word dictionary from English to Turkish, and by expanding it, obtain 15,222 words with annotations for valence, arousal, and dominance. We also employ a list of abbreviations, emoticons, interjections, modifiers (intensifiers and diminishers), and other linguistic indicators to capture the overall affective state at the sentence level. Lastly, we recruit and train annotators to obtain affective ground truth, and assess the accuracy of the proposed rule-based approach on a multi-party chat database collected from an online gaming environment.

AB - This study presents a model for affective text analysis of online multi-party chat records in Turkish language. Online chats have challenges like non-standard word usage, grammatical irregularities, abbreviation usage, and spelling mistakes. We propose several pre-processing steps to deal with these. We adapt an affective word dictionary from English to Turkish, and by expanding it, obtain 15,222 words with annotations for valence, arousal, and dominance. We also employ a list of abbreviations, emoticons, interjections, modifiers (intensifiers and diminishers), and other linguistic indicators to capture the overall affective state at the sentence level. Lastly, we recruit and train annotators to obtain affective ground truth, and assess the accuracy of the proposed rule-based approach on a multi-party chat database collected from an online gaming environment.

KW - Afiective computing

KW - Chat

KW - Computer games

KW - Natural language processing

KW - Turkish

UR - http://www.scopus.com/inward/record.url?scp=84960466688&partnerID=8YFLogxK

U2 - 10.1145/2829966.2829972

DO - 10.1145/2829966.2829972

M3 - Conference contribution

AN - SCOPUS:84960466688

SP - 19

EP - 24

BT - ERM4CT 2015 - Proceedings of the International Workshop on Emotion Representations and Modelling for Companion Technologies, co-located with ICMI 2015

PB - Association for Computing Machinery

T2 - International Workshop on Emotion Representations and Modelling for Companion Technologies, ERM4CT 2015

Y2 - 13 November 2015

ER -

Automatic assessment of dimensional affective content in Turkish multi-party chat messages

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this