Age Identification of Twitter Users: Classification Methods and Sociolinguistic Analysis

Vasiliki Simaki; Iosif Mporas; Vasileios Megalooikonomou

doi:10.1007/978-3-319-75487-1_30

Age Identification of Twitter Users: Classification Methods and Sociolinguistic Analysis

Vasiliki Simaki, Iosif Mporas, Vasileios Megalooikonomou

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

Sammanfattning

In this article, we address the problem of age identification of Twitter users, after their online text. We used a set of text mining, sociolinguistic-based and content-related text features, and we evaluated a number of well-known and widely used machine learning algorithms for classification, in order to examine their appropriateness on this task. The experimental results showed that Random Forest algorithm offered superior performance achieving accuracy equal to 61%. We ranked the classification features after their informativity, using the ReliefF algorithm, and we analyzed the results in terms of the sociolinguistic principles on age linguistic variation.

Originalspråk	engelska
Titel på värdpublikation	Computational Linguistics and Intelligent Text Processing
Undertitel på värdpublikation	17th International Conference, CICLing 2016, Konya, Turkey, April 3–9, 2016, Revised Selected Papers, Part II
Redaktörer	Alexander Gelbukh
Utgivningsort	Cham
Förlag	Springer
Sidor	385-395
ISBN (elektroniskt)	978-3-319-75487-1
ISBN (tryckt)	978-3-319-75486-4
DOI	https://doi.org/10.1007/978-3-319-75487-1_30
Status	Published - 2018
Externt publicerad	Ja
Evenemang	17th International Conference on Intelligent Text Processing and Computational Linguistics: CICLing 2016 - Konya, Turkiet Varaktighet: 2016 apr. 3 → 2016 apr. 9 http://www.cicling.org/2016/

Publikationsserier

Namn	Lecture Notes in Computer Science (LNCS)
Volym	9624

Konferens

Konferens	17th International Conference on Intelligent Text Processing and Computational Linguistics
Land/Territorium	Turkiet
Ort	Konya
Period	2016/04/03 → 2016/04/09
Internetadress	http://www.cicling.org/2016/

Ämnesklassifikation (UKÄ)

Jämförande språkvetenskap och lingvistik

Tillgång till dokument

10.1007/978-3-319-75487-1_30

Citera det här

Simaki, V., Mporas, I., & Megalooikonomou, V. (2018). Age Identification of Twitter Users: Classification Methods and Sociolinguistic Analysis. I A. Gelbukh (Red.), Computational Linguistics and Intelligent Text Processing: 17th International Conference, CICLing 2016, Konya, Turkey, April 3–9, 2016, Revised Selected Papers, Part II (s. 385-395). (Lecture Notes in Computer Science (LNCS); Vol. 9624). Springer. https://doi.org/10.1007/978-3-319-75487-1_30

Simaki, Vasiliki ; Mporas, Iosif ; Megalooikonomou, Vasileios. / Age Identification of Twitter Users : Classification Methods and Sociolinguistic Analysis. Computational Linguistics and Intelligent Text Processing: 17th International Conference, CICLing 2016, Konya, Turkey, April 3–9, 2016, Revised Selected Papers, Part II. redaktör / Alexander Gelbukh. Cham : Springer, 2018. s. 385-395 (Lecture Notes in Computer Science (LNCS)).

@inproceedings{5163ea4540d84baa9004b51a8cd3cb38,

title = "Age Identification of Twitter Users: Classification Methods and Sociolinguistic Analysis",

abstract = "In this article, we address the problem of age identification of Twitter users, after their online text. We used a set of text mining, sociolinguistic-based and content-related text features, and we evaluated a number of well-known and widely used machine learning algorithms for classification, in order to examine their appropriateness on this task. The experimental results showed that Random Forest algorithm offered superior performance achieving accuracy equal to 61%. We ranked the classification features after their informativity, using the ReliefF algorithm, and we analyzed the results in terms of the sociolinguistic principles on age linguistic variation.",

keywords = "Text mining, Age identification, Text classification, Computational Sociolinguistics, Sociolinguistics",

author = "Vasiliki Simaki and Iosif Mporas and Vasileios Megalooikonomou",

year = "2018",

doi = "10.1007/978-3-319-75487-1_30",

language = "English",

isbn = "978-3-319-75486-4",

series = "Lecture Notes in Computer Science (LNCS)",

publisher = "Springer",

pages = "385--395",

editor = "Alexander Gelbukh",

booktitle = "Computational Linguistics and Intelligent Text Processing",

address = "Germany",

note = "17th International Conference on Intelligent Text Processing and Computational Linguistics : CICLing 2016 ; Conference date: 03-04-2016 Through 09-04-2016",

url = "http://www.cicling.org/2016/",

}

Simaki, V, Mporas, I & Megalooikonomou, V 2018, Age Identification of Twitter Users: Classification Methods and Sociolinguistic Analysis. i A Gelbukh (red.), Computational Linguistics and Intelligent Text Processing: 17th International Conference, CICLing 2016, Konya, Turkey, April 3–9, 2016, Revised Selected Papers, Part II. Lecture Notes in Computer Science (LNCS), vol. 9624, Springer, Cham, s. 385-395, 17th International Conference on Intelligent Text Processing and Computational Linguistics, Konya, Turkiet, 2016/04/03. https://doi.org/10.1007/978-3-319-75487-1_30

Age Identification of Twitter Users: Classification Methods and Sociolinguistic Analysis. / Simaki, Vasiliki; Mporas, Iosif; Megalooikonomou, Vasileios.
Computational Linguistics and Intelligent Text Processing: 17th International Conference, CICLing 2016, Konya, Turkey, April 3–9, 2016, Revised Selected Papers, Part II. red. / Alexander Gelbukh. Cham: Springer, 2018. s. 385-395 (Lecture Notes in Computer Science (LNCS); Vol. 9624).

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

TY - GEN

T1 - Age Identification of Twitter Users

T2 - 17th International Conference on Intelligent Text Processing and Computational Linguistics

AU - Simaki, Vasiliki

AU - Mporas, Iosif

AU - Megalooikonomou, Vasileios

PY - 2018

Y1 - 2018

N2 - In this article, we address the problem of age identification of Twitter users, after their online text. We used a set of text mining, sociolinguistic-based and content-related text features, and we evaluated a number of well-known and widely used machine learning algorithms for classification, in order to examine their appropriateness on this task. The experimental results showed that Random Forest algorithm offered superior performance achieving accuracy equal to 61%. We ranked the classification features after their informativity, using the ReliefF algorithm, and we analyzed the results in terms of the sociolinguistic principles on age linguistic variation.

AB - In this article, we address the problem of age identification of Twitter users, after their online text. We used a set of text mining, sociolinguistic-based and content-related text features, and we evaluated a number of well-known and widely used machine learning algorithms for classification, in order to examine their appropriateness on this task. The experimental results showed that Random Forest algorithm offered superior performance achieving accuracy equal to 61%. We ranked the classification features after their informativity, using the ReliefF algorithm, and we analyzed the results in terms of the sociolinguistic principles on age linguistic variation.

KW - Text mining

KW - Age identification

KW - Text classification

KW - Computational Sociolinguistics

KW - Sociolinguistics

U2 - 10.1007/978-3-319-75487-1_30

DO - 10.1007/978-3-319-75487-1_30

M3 - Paper in conference proceeding

SN - 978-3-319-75486-4

T3 - Lecture Notes in Computer Science (LNCS)

SP - 385

EP - 395

BT - Computational Linguistics and Intelligent Text Processing

A2 - Gelbukh, Alexander

PB - Springer

CY - Cham

Y2 - 3 April 2016 through 9 April 2016

ER -

Simaki V, Mporas I, Megalooikonomou V. Age Identification of Twitter Users: Classification Methods and Sociolinguistic Analysis. I Gelbukh A, redaktör, Computational Linguistics and Intelligent Text Processing: 17th International Conference, CICLing 2016, Konya, Turkey, April 3–9, 2016, Revised Selected Papers, Part II. Cham: Springer. 2018. s. 385-395. (Lecture Notes in Computer Science (LNCS)). doi: 10.1007/978-3-319-75487-1_30

Age Identification of Twitter Users: Classification Methods and Sociolinguistic Analysis

Sammanfattning

Publikationsserier

Konferens

Ämnesklassifikation (UKÄ)

Tillgång till dokument

Fingeravtryck

Citera det här