Predicting Twitter Users' Political Orientation: An Application to the Italian Political Scenario

Matteo Cardaioli; Pallavi Kaliyar; Pasquale Capuozzo; Mauro Conti; Giuseppe Sartori; Merylin Monaro

doi:10.1109/ASONAM49781.2020.9381470

Predicting Twitter Users' Political Orientation: An Application to the Italian Political Scenario

Matteo Cardaioli, Pallavi Kaliyar, Pasquale Capuozzo, Mauro Conti, Giuseppe Sartori, Merylin Monaro

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

3 Citations (Scopus)

Abstract

Recently, the increasing spread of Online Social Networks (OSNs) provided an unprecedented opportunity of analysing online traces of human behaviour to get insight on individuals and society. Among the others, the possibility of predicting users' political orientation relying on data extracted from OSNs received growing attention. In this study, we introduce and make publicly available a dataset composed of 6.685 unique Twitter users and 9.593.055 Tweets. Differently from most of the dataset currently available in the literature, here, each user was manually labeled according to their political orientation by a pool of human judges, using strict inclusion criteria. Further, we address the feasibility of the automatic classification of Italian Twitter users' political orientation based on their Tweets content. Our analysis focuses first on implementing a series of classifiers with the aim of predicting users' political preference as right- or left-oriented. The built models were then evaluated for inferring the political orientation of those users supporting 'Movimento 5 Stelle' (M5S), an Italian political party with a still unclear political leaning. Results show high performances on the left-right classification task, with accuracy rates up to 93%. Finally, classification performances obtained on M5S supporters and possible applications of our findings are discussed.

Original language	English
Title of host publication	Proceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020
Editors	Martin Atzmuller, Michele Coscia, Rokia Missaoui
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	159-165
Number of pages	7
ISBN (Electronic)	9781728110561
DOIs	https://doi.org/10.1109/ASONAM49781.2020.9381470
Publication status	Published - 2020
Externally published	Yes
Event	12th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020 - Virtual, Online, Netherlands Duration: 7 Dec 2020 → 10 Dec 2020

Publication series

Name	Proceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020

Conference

Conference	12th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020
Country/Territory	Netherlands
City	Virtual, Online
Period	7/12/20 → 10/12/20

Keywords

Italian Politics
Natural Language Processing
Political Orientation Prediction
Twitter Dataset

Access to Document

10.1109/ASONAM49781.2020.9381470

Cite this

Cardaioli, M., Kaliyar, P., Capuozzo, P., Conti, M., Sartori, G., & Monaro, M. (2020). Predicting Twitter Users' Political Orientation: An Application to the Italian Political Scenario. In M. Atzmuller, M. Coscia, & R. Missaoui (Eds.), Proceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020 (pp. 159-165). Article 9381470 (Proceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ASONAM49781.2020.9381470

Cardaioli, Matteo ; Kaliyar, Pallavi ; Capuozzo, Pasquale et al. / Predicting Twitter Users' Political Orientation : An Application to the Italian Political Scenario. Proceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020. editor / Martin Atzmuller ; Michele Coscia ; Rokia Missaoui. Institute of Electrical and Electronics Engineers (IEEE), 2020. pp. 159-165 (Proceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020).

@inproceedings{eaebd630eb154b1fb784ec61946d9d76,

title = "Predicting Twitter Users' Political Orientation: An Application to the Italian Political Scenario",

abstract = "Recently, the increasing spread of Online Social Networks (OSNs) provided an unprecedented opportunity of analysing online traces of human behaviour to get insight on individuals and society. Among the others, the possibility of predicting users' political orientation relying on data extracted from OSNs received growing attention. In this study, we introduce and make publicly available a dataset composed of 6.685 unique Twitter users and 9.593.055 Tweets. Differently from most of the dataset currently available in the literature, here, each user was manually labeled according to their political orientation by a pool of human judges, using strict inclusion criteria. Further, we address the feasibility of the automatic classification of Italian Twitter users' political orientation based on their Tweets content. Our analysis focuses first on implementing a series of classifiers with the aim of predicting users' political preference as right- or left-oriented. The built models were then evaluated for inferring the political orientation of those users supporting 'Movimento 5 Stelle' (M5S), an Italian political party with a still unclear political leaning. Results show high performances on the left-right classification task, with accuracy rates up to 93%. Finally, classification performances obtained on M5S supporters and possible applications of our findings are discussed.",

keywords = "Italian Politics, Natural Language Processing, Political Orientation Prediction, Twitter Dataset",

author = "Matteo Cardaioli and Pallavi Kaliyar and Pasquale Capuozzo and Mauro Conti and Giuseppe Sartori and Merylin Monaro",

year = "2020",

doi = "10.1109/ASONAM49781.2020.9381470",

language = "English",

series = "Proceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "159--165",

editor = "Martin Atzmuller and Michele Coscia and Rokia Missaoui",

booktitle = "Proceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020",

address = "United States",

note = "12th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020 ; Conference date: 07-12-2020 Through 10-12-2020",

}

Cardaioli, M, Kaliyar, P, Capuozzo, P, Conti, M, Sartori, G & Monaro, M 2020, Predicting Twitter Users' Political Orientation: An Application to the Italian Political Scenario. in M Atzmuller, M Coscia & R Missaoui (eds), Proceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020., 9381470, Proceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020, Institute of Electrical and Electronics Engineers (IEEE), pp. 159-165, 12th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020, Virtual, Online, Netherlands, 7/12/20. https://doi.org/10.1109/ASONAM49781.2020.9381470

Predicting Twitter Users' Political Orientation: An Application to the Italian Political Scenario. / Cardaioli, Matteo; Kaliyar, Pallavi; Capuozzo, Pasquale et al.
Proceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020. ed. / Martin Atzmuller; Michele Coscia; Rokia Missaoui. Institute of Electrical and Electronics Engineers (IEEE), 2020. p. 159-165 9381470 (Proceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Predicting Twitter Users' Political Orientation

T2 - 12th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020

AU - Cardaioli, Matteo

AU - Kaliyar, Pallavi

AU - Capuozzo, Pasquale

AU - Conti, Mauro

AU - Sartori, Giuseppe

AU - Monaro, Merylin

PY - 2020

Y1 - 2020

N2 - Recently, the increasing spread of Online Social Networks (OSNs) provided an unprecedented opportunity of analysing online traces of human behaviour to get insight on individuals and society. Among the others, the possibility of predicting users' political orientation relying on data extracted from OSNs received growing attention. In this study, we introduce and make publicly available a dataset composed of 6.685 unique Twitter users and 9.593.055 Tweets. Differently from most of the dataset currently available in the literature, here, each user was manually labeled according to their political orientation by a pool of human judges, using strict inclusion criteria. Further, we address the feasibility of the automatic classification of Italian Twitter users' political orientation based on their Tweets content. Our analysis focuses first on implementing a series of classifiers with the aim of predicting users' political preference as right- or left-oriented. The built models were then evaluated for inferring the political orientation of those users supporting 'Movimento 5 Stelle' (M5S), an Italian political party with a still unclear political leaning. Results show high performances on the left-right classification task, with accuracy rates up to 93%. Finally, classification performances obtained on M5S supporters and possible applications of our findings are discussed.

AB - Recently, the increasing spread of Online Social Networks (OSNs) provided an unprecedented opportunity of analysing online traces of human behaviour to get insight on individuals and society. Among the others, the possibility of predicting users' political orientation relying on data extracted from OSNs received growing attention. In this study, we introduce and make publicly available a dataset composed of 6.685 unique Twitter users and 9.593.055 Tweets. Differently from most of the dataset currently available in the literature, here, each user was manually labeled according to their political orientation by a pool of human judges, using strict inclusion criteria. Further, we address the feasibility of the automatic classification of Italian Twitter users' political orientation based on their Tweets content. Our analysis focuses first on implementing a series of classifiers with the aim of predicting users' political preference as right- or left-oriented. The built models were then evaluated for inferring the political orientation of those users supporting 'Movimento 5 Stelle' (M5S), an Italian political party with a still unclear political leaning. Results show high performances on the left-right classification task, with accuracy rates up to 93%. Finally, classification performances obtained on M5S supporters and possible applications of our findings are discussed.

KW - Italian Politics

KW - Natural Language Processing

KW - Political Orientation Prediction

KW - Twitter Dataset

UR - http://www.scopus.com/inward/record.url?scp=85103685699&partnerID=8YFLogxK

U2 - 10.1109/ASONAM49781.2020.9381470

DO - 10.1109/ASONAM49781.2020.9381470

M3 - Conference contribution

AN - SCOPUS:85103685699

T3 - Proceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020

SP - 159

EP - 165

BT - Proceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020

A2 - Atzmuller, Martin

A2 - Coscia, Michele

A2 - Missaoui, Rokia

PB - Institute of Electrical and Electronics Engineers (IEEE)

Y2 - 7 December 2020 through 10 December 2020

ER -

Cardaioli M, Kaliyar P, Capuozzo P, Conti M, Sartori G, Monaro M. Predicting Twitter Users' Political Orientation: An Application to the Italian Political Scenario. In Atzmuller M, Coscia M, Missaoui R, editors, Proceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020. Institute of Electrical and Electronics Engineers (IEEE). 2020. p. 159-165. 9381470. (Proceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020). doi: 10.1109/ASONAM49781.2020.9381470

Predicting Twitter Users' Political Orientation: An Application to the Italian Political Scenario

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this