Identifying the Authors’ National Variety of English in Social Media Texts

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceeding

Abstract

In this paper, we present a study for the identification of authors’ national variety of English in texts from social media. In data from Facebook and Twitter, information about the author’s social profile is annotated, and the national English variety (US, UK, AUS, CAN, NNS) that each author uses is attributed. We tested four feature types: formal linguistic features, POS features, lexicon-based features related to the different varieties, and data-based features from each English variety. We used various machine learning algorithms for the classification experiments, and we implemented a feature selection
process. The classification accuracy achieved, when the 31 highest ranked
features were used, was up to 77.32%. The experimental results are evaluated, and the efficacy of the ranked features discussed.

Details

Authors
Organisations
External organisations
  • XPLAIN
  • Linnaeus University
Research areas and keywords

Subject classification (UKÄ) – MANDATORY

  • General Language Studies and Linguistics
Original languageEnglish
Title of host publicationRecent Advances in Natural Language Processing
Subtitle of host publicationProceedings
EditorsGalia Angelova, Kalina Bontcheva, Ruslan Metkov, Ivelina Nikolova, Irina Temnikova
Place of PublicationVarna
PublisherAssociation for Computational Linguistics
Pages671-678
ISBN (Electronic)978-954-452-049-6
ISBN (Print)978-954-452-048-9
Publication statusPublished - 2017
Publication categoryResearch
Peer-reviewedYes
EventThe 11th Biennial Conference on Recent Advances In Natural Language Processing (RANLP '17), 2-8 September 2017, Varna, Bulgaria - Varna, Bulgaria
Duration: 2017 Sep 22017 Sep 8
http://lml.bas.bg/ranlp2017/start.php

Conference

ConferenceThe 11th Biennial Conference on Recent Advances In Natural Language Processing (RANLP '17), 2-8 September 2017, Varna, Bulgaria
Abbreviated titleRANLP '17
CountryBulgaria
CityVarna
Period2017/09/022017/09/08
Internet address