Understanding fillers may facilitate automatic sarcasm comprehension: A structural analysis of Twitter data and a participant study

Fatemeh S. Tarighat; Walid Magdy; Martin Corley

Understanding fillers may facilitate automatic sarcasm comprehension: A structural analysis of Twitter data and a participant study

Fatemeh S. Tarighat, Walid Magdy, Martin Corley

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

Abstract / Description of output

Sarcasm detection models are often built based on self-annotated tagged data. However, fillers (e.g., um and hmm), deliberate use of which may indicate sarcasm, do not get enough attention in these models. We analyze five fillers in different categories of untagged tweets. We also present participant ratings of sarcasm, offensive language, language formality, and basic emotions in tweets with and without um and hmm. Our evidence, albeit weak, points to the importance of linguistic features such as these fillers in determining sarcastic meaning.

Original language	English
Title of host publication	Proceedings of the 26th Workshop on the Semantics and Pragmatics of Dialogue - Poster Abstracts
Editors	Eleni Gregoromichelaki, Julian Hough, John D. Kelleher
Publisher	SEMDIAL
Pages	1-3
Number of pages	3
Publication status	Published - 24 Aug 2022
Event	The 26th Workshop on the Semantics and Pragmatics of Dialogue - Technological University Dublin, Dublin, Ireland Duration: 22 Aug 2022 → 24 Aug 2022 Conference number: 26 https://semdial2022.github.io/

Publication series

Name	Proceedings of the Workshop Series on the Semantics and Pragmatics of Dialogue
Publisher	SEMDIAL
ISSN (Electronic)	2308-2275

Workshop

Workshop	The 26th Workshop on the Semantics and Pragmatics of Dialogue
Abbreviated title	SemDial 2022
Country/Territory	Ireland
City	Dublin
Period	22/08/22 → 24/08/22
Internet address	https://semdial2022.github.io/

Access to Document

TarighatEtalSemDial2022UnderstandingFillersMayFacilitateFinal published version, 91.7 KBLicence: Creative Commons: Attribution (CC-BY)

https://semdial.org/anthology/Z22-Tarighat_semdial_0023.pdfLicence: Creative Commons: Attribution (CC-BY)

Cite this

Tarighat, F. S., Magdy, W., & Corley, M. (2022). Understanding fillers may facilitate automatic sarcasm comprehension: A structural analysis of Twitter data and a participant study. In E. Gregoromichelaki, J. Hough, & J. D. Kelleher (Eds.), Proceedings of the 26th Workshop on the Semantics and Pragmatics of Dialogue - Poster Abstracts (pp. 1-3). (Proceedings of the Workshop Series on the Semantics and Pragmatics of Dialogue). SEMDIAL. https://semdial.org/anthology/Z22-Tarighat_semdial_0023.pdf

Tarighat, Fatemeh S. ; Magdy, Walid ; Corley, Martin. / Understanding fillers may facilitate automatic sarcasm comprehension : A structural analysis of Twitter data and a participant study. Proceedings of the 26th Workshop on the Semantics and Pragmatics of Dialogue - Poster Abstracts. editor / Eleni Gregoromichelaki ; Julian Hough ; John D. Kelleher. SEMDIAL, 2022. pp. 1-3 (Proceedings of the Workshop Series on the Semantics and Pragmatics of Dialogue).

@inproceedings{881eef7041c04919ad22450ca96f0b4a,

title = "Understanding fillers may facilitate automatic sarcasm comprehension: A structural analysis of Twitter data and a participant study",

abstract = "Sarcasm detection models are often built based on self-annotated tagged data. However, fillers (e.g., um and hmm), deliberate use of which may indicate sarcasm, do not get enough attention in these models. We analyze five fillers in different categories of untagged tweets. We also present participant ratings of sarcasm, offensive language, language formality, and basic emotions in tweets with and without um and hmm. Our evidence, albeit weak, points to the importance of linguistic features such as these fillers in determining sarcastic meaning.",

author = "Tarighat, {Fatemeh S.} and Walid Magdy and Martin Corley",

year = "2022",

month = aug,

day = "24",

language = "English",

series = "Proceedings of the Workshop Series on the Semantics and Pragmatics of Dialogue",

publisher = "SEMDIAL",

pages = "1--3",

editor = "Eleni Gregoromichelaki and Julian Hough and Kelleher, {John D.}",

booktitle = "Proceedings of the 26th Workshop on the Semantics and Pragmatics of Dialogue - Poster Abstracts",

note = "The 26th Workshop on the Semantics and Pragmatics of Dialogue, SemDial 2022 ; Conference date: 22-08-2022 Through 24-08-2022",

url = "https://semdial2022.github.io/",

}

Tarighat, FS, Magdy, W & Corley, M 2022, Understanding fillers may facilitate automatic sarcasm comprehension: A structural analysis of Twitter data and a participant study. in E Gregoromichelaki, J Hough & JD Kelleher (eds), Proceedings of the 26th Workshop on the Semantics and Pragmatics of Dialogue - Poster Abstracts. Proceedings of the Workshop Series on the Semantics and Pragmatics of Dialogue, SEMDIAL, pp. 1-3, The 26th Workshop on the Semantics and Pragmatics of Dialogue, Dublin, Ireland, 22/08/22. <https://semdial.org/anthology/Z22-Tarighat_semdial_0023.pdf>

Understanding fillers may facilitate automatic sarcasm comprehension: A structural analysis of Twitter data and a participant study. / Tarighat, Fatemeh S.; Magdy, Walid ; Corley, Martin.
Proceedings of the 26th Workshop on the Semantics and Pragmatics of Dialogue - Poster Abstracts. ed. / Eleni Gregoromichelaki; Julian Hough; John D. Kelleher. SEMDIAL, 2022. p. 1-3 (Proceedings of the Workshop Series on the Semantics and Pragmatics of Dialogue).

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

TY - GEN

T1 - Understanding fillers may facilitate automatic sarcasm comprehension

T2 - The 26th Workshop on the Semantics and Pragmatics of Dialogue

AU - Tarighat, Fatemeh S.

AU - Magdy, Walid

AU - Corley, Martin

N1 - Conference code: 26

PY - 2022/8/24

Y1 - 2022/8/24

N2 - Sarcasm detection models are often built based on self-annotated tagged data. However, fillers (e.g., um and hmm), deliberate use of which may indicate sarcasm, do not get enough attention in these models. We analyze five fillers in different categories of untagged tweets. We also present participant ratings of sarcasm, offensive language, language formality, and basic emotions in tweets with and without um and hmm. Our evidence, albeit weak, points to the importance of linguistic features such as these fillers in determining sarcastic meaning.

AB - Sarcasm detection models are often built based on self-annotated tagged data. However, fillers (e.g., um and hmm), deliberate use of which may indicate sarcasm, do not get enough attention in these models. We analyze five fillers in different categories of untagged tweets. We also present participant ratings of sarcasm, offensive language, language formality, and basic emotions in tweets with and without um and hmm. Our evidence, albeit weak, points to the importance of linguistic features such as these fillers in determining sarcastic meaning.

M3 - Conference contribution

T3 - Proceedings of the Workshop Series on the Semantics and Pragmatics of Dialogue

SP - 1

EP - 3

BT - Proceedings of the 26th Workshop on the Semantics and Pragmatics of Dialogue - Poster Abstracts

A2 - Gregoromichelaki, Eleni

A2 - Hough, Julian

A2 - Kelleher, John D.

PB - SEMDIAL

Y2 - 22 August 2022 through 24 August 2022

ER -

Tarighat FS, Magdy W , Corley M. Understanding fillers may facilitate automatic sarcasm comprehension: A structural analysis of Twitter data and a participant study. In Gregoromichelaki E, Hough J, Kelleher JD, editors, Proceedings of the 26th Workshop on the Semantics and Pragmatics of Dialogue - Poster Abstracts. SEMDIAL. 2022. p. 1-3. (Proceedings of the Workshop Series on the Semantics and Pragmatics of Dialogue).

Understanding fillers may facilitate automatic sarcasm comprehension: A structural analysis of Twitter data and a participant study

Abstract / Description of output

Publication series

Workshop

Access to Document

Fingerprint

Cite this