Edinburgh Research Explorer

Author Profiling using Stylometric and Structural Feature Groupings

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Open Access permissions

Open

Documents

http://ceur-ws.org/Vol-1391/68-CR.pdf
Original languageUndefined/Unknown
Title of host publicationWorking Notes of CLEF 2015 - Conference and Labs of the Evaluation forum, Toulouse, France, September 8-11, 2015.
EditorsG.J.F. Jones, L. Cappellato, N. Ferro, E. San Juan
PublisherCEUR-WS
Number of pages7
Publication statusE-pub ahead of print - 11 Sep 2015
Externally publishedYes
EventCLEF 2015: Conference and Labs of the Evaluation Forum
Experimental IR meets Multilinguality, Multimodality and Interaction
- Toulouse, France
Duration: 8 Sep 201511 Sep 2015
Conference number: 6
http://clef2015.clef-initiative.eu/cfl.php

Publication series

NameCEUR Workshop Proceedings
PublisherCEUR-WS
Volume1391
ISSN (Print)1613-0073

Conference

ConferenceCLEF 2015: Conference and Labs of the Evaluation Forum
Experimental IR meets Multilinguality, Multimodality and Interaction
Abbreviated titleCLEF 2015
CountryFrance
CityToulouse
Period8/09/1511/09/15
Internet address

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.

    Research areas

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

ID: 101074175