Detection of Stance-Related Characteristics in Social Media Text

Vasiliki Simaki; Panagiotis Simakis; Carita Paradis; Andreas Kerren

doi:10.1145/3200947.3201017

Detection of Stance-Related Characteristics in Social Media Text

Vasiliki Simaki, Panagiotis Simakis, Carita Paradis, Andreas Kerren

Forskningsoutput: Kapitel i bok/rapport/Conference proceeding › Konferenspaper i proceeding › Peer review

272 Nedladdningar (Pure)

Sammanfattning

In this paper, we present a study for the identification of stancerelated features in text data from social media. Based on our previous work on stance and our findings on stance patterns, we detected stance-related characteristics in a data set from Twitter and Facebook. We extracted various corpus-, quantitative- and computational-based features that proved to be significant for six stance categories (contrariety, hypotheticality, necessity, prediction, source of knowledge, and uncertainty), and we tested them in our data set. The results of a preliminary clustering method are presented and discussed as a starting point for future contributions in the field. The results of our experiments showed a strong correlation between different characteristics and stance constructions, which can lead us to a methodology for automatic stance annotation of these data.

Originalspråk	engelska
Titel på värdpublikation	SETN '18 Proceedings of the 10th Hellenic Conference on Artificial Intelligence
Utgivningsort	New York
Förlag	Association for Computing Machinery (ACM)
Antal sidor	7
ISBN (tryckt)	978-1-4503-6433-1
DOI	https://doi.org/10.1145/3200947.3201017
Status	Published - 2018 juli 15
Evenemang	The 10th Hellenic Conference on Artificial Intelligence - University of Patras, Patras, Grekland Varaktighet: 2018 juli 9 → 2018 juli 15 Konferensnummer: 10 http://setn2018.upatras.gr/

Konferens

Konferens	The 10th Hellenic Conference on Artificial Intelligence
Förkortad titel	SETN '18
Land/Territorium	Grekland
Ort	Patras
Period	2018/07/09 → 2018/07/15
Internetadress	http://setn2018.upatras.gr/

Ämnesklassifikation (UKÄ)

Jämförande språkvetenskap och lingvistik

Tillgång till dokument

10.1145/3200947.3201017

Simaki Paradi Kerren Patras sample-sigconfAccepterat manuskript från författare, 544 KB

StaViCTA - Nya landvinningar inom beskrivning och förklaring av ställningstagande i språklig kommunikation genom metoder från datalogi och informationvisualisering
Paradis, C., Kerren, A., Sahlgren, M., Kucher, K., Skeppstedt, M. & Simaki, V.
Swedish Research Council
2013/01/01 → 2018/01/02
Projekt: Forskning

Citera det här

@inproceedings{e8c1cdaa6c8c4865b0b0b165ab862a96,

title = "Detection of Stance-Related Characteristics in Social Media Text",

abstract = "In this paper, we present a study for the identification of stancerelated features in text data from social media. Based on our previous work on stance and our findings on stance patterns, we detected stance-related characteristics in a data set from Twitter and Facebook. We extracted various corpus-, quantitative- and computational-based features that proved to be significant for six stance categories (contrariety, hypotheticality, necessity, prediction, source of knowledge, and uncertainty), and we tested them in our data set. The results of a preliminary clustering method are presented and discussed as a starting point for future contributions in the field. The results of our experiments showed a strong correlation between different characteristics and stance constructions, which can lead us to a methodology for automatic stance annotation of these data.",

keywords = "stance-taking, text, clustering, feature extraction, social media",

author = "Vasiliki Simaki and Panagiotis Simakis and Carita Paradis and Andreas Kerren",

year = "2018",

month = jul,

day = "15",

doi = "10.1145/3200947.3201017",

language = "English",

isbn = "978-1-4503-6433-1",

booktitle = "SETN '18 Proceedings of the 10th Hellenic Conference on Artificial Intelligence",

publisher = "Association for Computing Machinery (ACM)",

address = "United States",

note = "The 10th Hellenic Conference on Artificial Intelligence , SETN '18 ; Conference date: 09-07-2018 Through 15-07-2018",

url = "http://setn2018.upatras.gr/",

}

Simaki, V, Simakis, P, Paradis, C & Kerren, A 2018, Detection of Stance-Related Characteristics in Social Media Text. i SETN '18 Proceedings of the 10th Hellenic Conference on Artificial Intelligence . Association for Computing Machinery (ACM), New York, The 10th Hellenic Conference on Artificial Intelligence , Patras, Grekland, 2018/07/09. https://doi.org/10.1145/3200947.3201017

Detection of Stance-Related Characteristics in Social Media Text. / Simaki, Vasiliki; Simakis, Panagiotis; Paradis, Carita et al.

SETN '18 Proceedings of the 10th Hellenic Conference on Artificial Intelligence . New York : Association for Computing Machinery (ACM), 2018.

Forskningsoutput: Kapitel i bok/rapport/Conference proceeding › Konferenspaper i proceeding › Peer review

TY - GEN

T1 - Detection of Stance-Related Characteristics in Social Media Text

AU - Simaki, Vasiliki

AU - Simakis, Panagiotis

AU - Paradis, Carita

AU - Kerren, Andreas

N1 - Conference code: 10

PY - 2018/7/15

Y1 - 2018/7/15

N2 - In this paper, we present a study for the identification of stancerelated features in text data from social media. Based on our previous work on stance and our findings on stance patterns, we detected stance-related characteristics in a data set from Twitter and Facebook. We extracted various corpus-, quantitative- and computational-based features that proved to be significant for six stance categories (contrariety, hypotheticality, necessity, prediction, source of knowledge, and uncertainty), and we tested them in our data set. The results of a preliminary clustering method are presented and discussed as a starting point for future contributions in the field. The results of our experiments showed a strong correlation between different characteristics and stance constructions, which can lead us to a methodology for automatic stance annotation of these data.

AB - In this paper, we present a study for the identification of stancerelated features in text data from social media. Based on our previous work on stance and our findings on stance patterns, we detected stance-related characteristics in a data set from Twitter and Facebook. We extracted various corpus-, quantitative- and computational-based features that proved to be significant for six stance categories (contrariety, hypotheticality, necessity, prediction, source of knowledge, and uncertainty), and we tested them in our data set. The results of a preliminary clustering method are presented and discussed as a starting point for future contributions in the field. The results of our experiments showed a strong correlation between different characteristics and stance constructions, which can lead us to a methodology for automatic stance annotation of these data.

KW - stance-taking

KW - text

KW - clustering

KW - feature extraction

KW - social media

U2 - 10.1145/3200947.3201017

DO - 10.1145/3200947.3201017

M3 - Paper in conference proceeding

SN - 978-1-4503-6433-1

BT - SETN '18 Proceedings of the 10th Hellenic Conference on Artificial Intelligence

PB - Association for Computing Machinery (ACM)

CY - New York

T2 - The 10th Hellenic Conference on Artificial Intelligence

Y2 - 9 July 2018 through 15 July 2018

ER -

Detection of Stance-Related Characteristics in Social Media Text

Sammanfattning

Konferens

Ämnesklassifikation (UKÄ)

Tillgång till dokument

Fingeravtryck

Projekt

StaViCTA - Nya landvinningar inom beskrivning och förklaring av ställningstagande i språklig kommunikation genom metoder från datalogi och informationvisualisering

Citera det här