Inferring the socioeconomic status of social media users based on behaviour and language

Vasileios Lampos; Nikolaos Aletras; Jens K. Geyti; Bin Zou; Ingemar Johansson Cox

doi:10.1007/978-3-319-30671-1_54

Inferring the socioeconomic status of social media users based on behaviour and language

Vasileios Lampos, Nikolaos Aletras, Jens K. Geyti, Bin Zou, Ingemar Johansson Cox

Department of Computer Science

30 Citations (Scopus)

Abstract

This paper presents a method to classify social media users based on their socioeconomic status. Our experiments are conducted on a curated set of Twitter profiles, where each user is represented by the posted text, topics of discussion, interactive behaviour and estimated impact on the microblogging platform. Initially, we formulate a 3-way classification task, where users are classified as having an upper, middle or lower socioeconomic status. A nonlinear, generative learning approach using a composite Gaussian Process kernel provides significantly better classification accuracy (75%) than a competitive linear alternative. By turning this task into a binary classification – upper vs. medium and lower class – the proposed classifier reaches an accuracy of 82%.

Original language	English
Title of host publication	Advances in Information Retrieval : 38th European Conference on IR Research, ECIR 2016, Padua, Italy, March 20–23, 2016. Proceedings
Editors	Nicola Ferro, Fabio Crestani, Marie-Francine Moens, Josiane Mothe, Fabrizio Silvestri, Giorgio Maria Di Nunzio, Claudia Hauff, Gianmaria Silvello
Number of pages	7
Publisher	Springer
Publication date	2016
Pages	689-695
ISBN (Print)	978-3-319-30671-1
ISBN (Electronic)	978-3-319-30671-1
DOIs	https://doi.org/10.1007/978-3-319-30671-1_54
Publication status	Published - 2016
Event	38th European Conference on Information Retrieval - Padua, Italy Duration: 20 Mar 2016 → 23 Mar 2016

Conference

Conference	38th European Conference on Information Retrieval
Country/Territory	Italy
City	Padua
Period	20/03/2016 → 23/03/2016

Series	Lecture notes in computer science
Volume	9626
ISSN	0302-9743

Access to Document

10.1007/978-3-319-30671-1_54

Cite this

Lampos, V., Aletras, N., Geyti, J. K., Zou, B., & Cox, I. J. (2016). Inferring the socioeconomic status of social media users based on behaviour and language. In N. Ferro, F. Crestani, M.-F. Moens, J. Mothe, F. Silvestri, G. M. Di Nunzio, C. Hauff, & G. Silvello (Eds.), Advances in Information Retrieval: 38th European Conference on IR Research, ECIR 2016, Padua, Italy, March 20–23, 2016. Proceedings (pp. 689-695). Springer. https://doi.org/10.1007/978-3-319-30671-1_54

Inferring the socioeconomic status of social media users based on behaviour and language. / Lampos, Vasileios; Aletras, Nikolaos; Geyti, Jens K. et al.
Advances in Information Retrieval: 38th European Conference on IR Research, ECIR 2016, Padua, Italy, March 20–23, 2016. Proceedings. ed. / Nicola Ferro; Fabio Crestani; Marie-Francine Moens; Josiane Mothe; Fabrizio Silvestri; Giorgio Maria Di Nunzio; Claudia Hauff; Gianmaria Silvello. Springer, 2016. p. 689-695 (Lecture notes in computer science, Vol. 9626).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Lampos, V, Aletras, N, Geyti, JK, Zou, B & Cox, IJ 2016, Inferring the socioeconomic status of social media users based on behaviour and language. in N Ferro, F Crestani, M-F Moens, J Mothe, F Silvestri, GM Di Nunzio, C Hauff & G Silvello (eds), Advances in Information Retrieval: 38th European Conference on IR Research, ECIR 2016, Padua, Italy, March 20–23, 2016. Proceedings. Springer, Lecture notes in computer science, vol. 9626, pp. 689-695, 38th European Conference on Information Retrieval, Padua, Italy, 20/03/2016. https://doi.org/10.1007/978-3-319-30671-1_54

Lampos V, Aletras N, Geyti JK, Zou B, Cox IJ. Inferring the socioeconomic status of social media users based on behaviour and language. In Ferro N, Crestani F, Moens MF, Mothe J, Silvestri F, Di Nunzio GM, Hauff C, Silvello G, editors, Advances in Information Retrieval: 38th European Conference on IR Research, ECIR 2016, Padua, Italy, March 20–23, 2016. Proceedings. Springer. 2016. p. 689-695. (Lecture notes in computer science, Vol. 9626). doi: 10.1007/978-3-319-30671-1_54

Lampos, Vasileios ; Aletras, Nikolaos ; Geyti, Jens K. et al. / Inferring the socioeconomic status of social media users based on behaviour and language. Advances in Information Retrieval: 38th European Conference on IR Research, ECIR 2016, Padua, Italy, March 20–23, 2016. Proceedings. editor / Nicola Ferro ; Fabio Crestani ; Marie-Francine Moens ; Josiane Mothe ; Fabrizio Silvestri ; Giorgio Maria Di Nunzio ; Claudia Hauff ; Gianmaria Silvello. Springer, 2016. pp. 689-695 (Lecture notes in computer science, Vol. 9626).

@inproceedings{f46c991be3b34ff3a3d8cd1bee86bdd4,

title = "Inferring the socioeconomic status of social media users based on behaviour and language",

abstract = "This paper presents a method to classify social media users based on their socioeconomic status. Our experiments are conducted on a curated set of Twitter profiles, where each user is represented by the posted text, topics of discussion, interactive behaviour and estimated impact on the microblogging platform. Initially, we formulate a 3-way classification task, where users are classified as having an upper, middle or lower socioeconomic status. A nonlinear, generative learning approach using a composite Gaussian Process kernel provides significantly better classification accuracy (75%) than a competitive linear alternative. By turning this task into a binary classification – upper vs. medium and lower class – the proposed classifier reaches an accuracy of 82%.",

author = "Vasileios Lampos and Nikolaos Aletras and Geyti, {Jens K.} and Bin Zou and Cox, {Ingemar Johansson}",

year = "2016",

doi = "10.1007/978-3-319-30671-1_54",

language = "English",

isbn = "978-3-319-30671-1",

series = "Lecture notes in computer science",

publisher = "Springer",

pages = "689--695",

editor = "Nicola Ferro and Fabio Crestani and Marie-Francine Moens and Josiane Mothe and Fabrizio Silvestri and {Di Nunzio}, {Giorgio Maria} and Claudia Hauff and Gianmaria Silvello",

booktitle = "Advances in Information Retrieval",

note = "38th European Conference on Information Retrieval, ECIR 2016 ; Conference date: 20-03-2016 Through 23-03-2016",

}

TY - GEN

T1 - Inferring the socioeconomic status of social media users based on behaviour and language

AU - Lampos, Vasileios

AU - Aletras, Nikolaos

AU - Geyti, Jens K.

AU - Zou, Bin

AU - Cox, Ingemar Johansson

PY - 2016

Y1 - 2016

N2 - This paper presents a method to classify social media users based on their socioeconomic status. Our experiments are conducted on a curated set of Twitter profiles, where each user is represented by the posted text, topics of discussion, interactive behaviour and estimated impact on the microblogging platform. Initially, we formulate a 3-way classification task, where users are classified as having an upper, middle or lower socioeconomic status. A nonlinear, generative learning approach using a composite Gaussian Process kernel provides significantly better classification accuracy (75%) than a competitive linear alternative. By turning this task into a binary classification – upper vs. medium and lower class – the proposed classifier reaches an accuracy of 82%.

AB - This paper presents a method to classify social media users based on their socioeconomic status. Our experiments are conducted on a curated set of Twitter profiles, where each user is represented by the posted text, topics of discussion, interactive behaviour and estimated impact on the microblogging platform. Initially, we formulate a 3-way classification task, where users are classified as having an upper, middle or lower socioeconomic status. A nonlinear, generative learning approach using a composite Gaussian Process kernel provides significantly better classification accuracy (75%) than a competitive linear alternative. By turning this task into a binary classification – upper vs. medium and lower class – the proposed classifier reaches an accuracy of 82%.

U2 - 10.1007/978-3-319-30671-1_54

DO - 10.1007/978-3-319-30671-1_54

M3 - Article in proceedings

SN - 978-3-319-30671-1

T3 - Lecture notes in computer science

SP - 689

EP - 695

BT - Advances in Information Retrieval

A2 - Ferro, Nicola

A2 - Crestani, Fabio

A2 - Moens, Marie-Francine

A2 - Mothe, Josiane

A2 - Silvestri, Fabrizio

A2 - Di Nunzio, Giorgio Maria

A2 - Hauff, Claudia

A2 - Silvello, Gianmaria

PB - Springer

T2 - 38th European Conference on Information Retrieval

Y2 - 20 March 2016 through 23 March 2016

ER -

Inferring the socioeconomic status of social media users based on behaviour and language

Abstract

Conference

Access to Document

Fingerprint

Cite this