Author Profiling using Stylometric and Structural Feature Groupings

Andreas Grivas; Anastasia Krithara; George Giannakopoulos

Author Profiling using Stylometric and Structural Feature Groupings

Andreas Grivas, Anastasia Krithara, George Giannakopoulos

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

Abstract

In this paper we present an approach for the task of author profiling. We propose a coherent grouping of features combined with appropriate preprocessing steps for each group. The groups we used were stylometric and structural, featuring among others, trigrams and counts of twitter specific characteristics. We address gender and age prediction as a classification task and personality prediction as a regression problem using Support Vector Machines and Support Vector Machine Regression respectively on documents created by joining each user’s tweets.

Original language	Undefined/Unknown
Title of host publication	Working Notes of CLEF 2015 - Conference and Labs of the Evaluation forum, Toulouse, France, September 8-11, 2015.
Editors	G.J.F. Jones, L. Cappellato, N. Ferro, E. San Juan
Publisher	CEUR-WS
Number of pages	7
Publication status	E-pub ahead of print - 11 Sept 2015
Externally published	Yes
Event	CLEF 2015: Conference and Labs of the Evaluation Forum Experimental IR meets Multilinguality, Multimodality and Interaction - Toulouse, France Duration: 8 Sept 2015 → 11 Sept 2015 Conference number: 6 http://clef2015.clef-initiative.eu/cfl.php

Publication series

Name	CEUR Workshop Proceedings
Publisher	CEUR-WS
Volume	1391
ISSN (Print)	1613-0073

Conference

Conference	CLEF 2015: Conference and Labs of the Evaluation Forum Experimental IR meets Multilinguality, Multimodality and Interaction
Abbreviated title	CLEF 2015
Country/Territory	France
City	Toulouse
Period	8/09/15 → 11/09/15
Internet address	http://clef2015.clef-initiative.eu/cfl.php

Keywords / Materials (for Non-textual outputs)

Information retrieval systems
Age predictions
Classification tasks
Personality predictions
Pre-processing step
Regression problem
Structural feature
Support vector machine regressions
Support vector machines

Access to Document

Author profiling using stylometric_GRIVAS_DoA110915_AFVAccepted author manuscript, 238 KB

http://ceur-ws.org/Vol-1391/68-CR.pdf

Cite this

Grivas, A., Krithara, A., & Giannakopoulos, G. (2015). Author Profiling using Stylometric and Structural Feature Groupings. In G. J. F. Jones, L. Cappellato, N. Ferro, & E. San Juan (Eds.), Working Notes of CLEF 2015 - Conference and Labs of the Evaluation forum, Toulouse, France, September 8-11, 2015. (CEUR Workshop Proceedings; Vol. 1391). CEUR-WS. Advance online publication. http://ceur-ws.org/Vol-1391/68-CR.pdf

@inproceedings{a0849c6113404b748dc2c991089cf020,

title = "Author Profiling using Stylometric and Structural Feature Groupings",

abstract = "In this paper we present an approach for the task of author profiling. We propose a coherent grouping of features combined with appropriate preprocessing steps for each group. The groups we used were stylometric and structural, featuring among others, trigrams and counts of twitter specific characteristics. We address gender and age prediction as a classification task and personality prediction as a regression problem using Support Vector Machines and Support Vector Machine Regression respectively on documents created by joining each user{\textquoteright}s tweets.",

keywords = "Information retrieval systems, Age predictions, Classification tasks, Personality predictions, Pre-processing step, Regression problem, Structural feature, Support vector machine regressions, Support vector machines",

author = "Andreas Grivas and Anastasia Krithara and George Giannakopoulos",

year = "2015",

month = sep,

day = "11",

language = "Undefined/Unknown",

series = "CEUR Workshop Proceedings",

publisher = "CEUR-WS",

editor = "G.J.F. Jones and L. Cappellato and N. Ferro and \{San Juan\}, \{E. \}",

booktitle = "Working Notes of CLEF 2015 - Conference and Labs of the Evaluation forum, Toulouse, France, September 8-11, 2015.",

note = "CLEF 2015: Conference and Labs of the Evaluation Forum <br/>Experimental IR meets Multilinguality, Multimodality and Interaction ; Conference date: 08-09-2015 Through 11-09-2015",

url = "http://clef2015.clef-initiative.eu/cfl.php",

}

Grivas, A, Krithara, A & Giannakopoulos, G 2015, Author Profiling using Stylometric and Structural Feature Groupings. in GJF Jones, L Cappellato, N Ferro & E San Juan (eds), Working Notes of CLEF 2015 - Conference and Labs of the Evaluation forum, Toulouse, France, September 8-11, 2015.. CEUR Workshop Proceedings, vol. 1391, CEUR-WS, CLEF 2015: Conference and Labs of the Evaluation Forum
Experimental IR meets Multilinguality, Multimodality and Interaction, Toulouse, France, 8/09/15. <http://ceur-ws.org/Vol-1391/68-CR.pdf>

Author Profiling using Stylometric and Structural Feature Groupings. / Grivas, Andreas; Krithara, Anastasia; Giannakopoulos, George.
Working Notes of CLEF 2015 - Conference and Labs of the Evaluation forum, Toulouse, France, September 8-11, 2015.. ed. / G.J.F. Jones; L. Cappellato; N. Ferro; E. San Juan. CEUR-WS, 2015. (CEUR Workshop Proceedings; Vol. 1391).

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

TY - GEN

T1 - Author Profiling using Stylometric and Structural Feature Groupings

AU - Grivas, Andreas

AU - Krithara, Anastasia

AU - Giannakopoulos, George

N1 - Conference code: 6

PY - 2015/9/11

Y1 - 2015/9/11

N2 - In this paper we present an approach for the task of author profiling. We propose a coherent grouping of features combined with appropriate preprocessing steps for each group. The groups we used were stylometric and structural, featuring among others, trigrams and counts of twitter specific characteristics. We address gender and age prediction as a classification task and personality prediction as a regression problem using Support Vector Machines and Support Vector Machine Regression respectively on documents created by joining each user’s tweets.

AB - In this paper we present an approach for the task of author profiling. We propose a coherent grouping of features combined with appropriate preprocessing steps for each group. The groups we used were stylometric and structural, featuring among others, trigrams and counts of twitter specific characteristics. We address gender and age prediction as a classification task and personality prediction as a regression problem using Support Vector Machines and Support Vector Machine Regression respectively on documents created by joining each user’s tweets.

KW - Information retrieval systems

KW - Age predictions

KW - Classification tasks

KW - Personality predictions

KW - Pre-processing step

KW - Regression problem

KW - Structural feature

KW - Support vector machine regressions

KW - Support vector machines

UR - http://clef2015.clef-initiative.eu/cfl.php

M3 - Conference contribution

T3 - CEUR Workshop Proceedings

BT - Working Notes of CLEF 2015 - Conference and Labs of the Evaluation forum, Toulouse, France, September 8-11, 2015.

A2 - Jones, G.J.F.

A2 - Cappellato, L.

A2 - Ferro, N.

A2 - San Juan, E.

PB - CEUR-WS

T2 - CLEF 2015: Conference and Labs of the Evaluation Forum <br/>Experimental IR meets Multilinguality, Multimodality and Interaction

Y2 - 8 September 2015 through 11 September 2015

ER -

Author Profiling using Stylometric and Structural Feature Groupings

Abstract

Publication series

Conference

Keywords / Materials (for Non-textual outputs)

Access to Document

Other files and links

Cite this