Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 9.83 MB
Add to list
  1. Search results
  2. Comparison of automatic vs. manual la...

Comparison of automatic vs. manual language identification in multilingual social media texts

Jennifer-Carmen Frey, Egon W. Stemle and A. Seza Doğruöz (UGent)
(2019) Building computer mediated corpora for sociolinguistic analysis. In Cahiers du Laboratoire de recherche sur le langage 8. p.28-44
Author
Organization
Abstract
Multilingual speakers communicate in more than one language in daily life and on social media. In order to process or investigate multilingual communication, there is a need for language identification. This study compares the performance of human annotators with automatic ways of language identification on a multilingual (mainly German-Italian-English) social media corpus collected in South Tyrol, Italy. Our results indicate that humans and Natural Language Processing (NLP) systems follow their individual techniques to make a decision about multilingual text messages. This results in low agreement when different annotators or NLP systems execute the same task. In general, annotators agree with each other more than NLP systems. However, there is also variation in human agreement depending on the prior establishment of guidelines for the annotation task or not.
Keywords
Automatic Language Identification, Social Media, Italian, German, South Tyrol, Lt3, Computer Mediated Communication (CMC), computational sociolinguistics, computational social sciences

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 9.83 MB

Citation

Please use this url to cite or link to this publication:

MLA
Frey, Jennifer-Carmen, et al. “Comparison of Automatic vs. Manual Language Identification in Multilingual Social Media Texts.” Building Computer Mediated Corpora for Sociolinguistic Analysis, edited by Ciara R. Wigham and Egon W. Stemle, vol. 8, Presses universitaires Blaise Pascal, 2019, pp. 28–44.
APA
Frey, J.-C., Stemle, E. W., & Doğruöz, A. S. (2019). Comparison of automatic vs. manual language identification in multilingual social media texts. In C. R. Wigham & E. W. Stemle (Eds.), Building computer mediated corpora for sociolinguistic analysis (Vol. 8, pp. 28–44). Presses universitaires Blaise Pascal.
Chicago author-date
Frey, Jennifer-Carmen, Egon W. Stemle, and A. Seza Doğruöz. 2019. “Comparison of Automatic vs. Manual Language Identification in Multilingual Social Media Texts.” In Building Computer Mediated Corpora for Sociolinguistic Analysis, edited by Ciara R. Wigham and Egon W. Stemle, 8:28–44. Presses universitaires Blaise Pascal.
Chicago author-date (all authors)
Frey, Jennifer-Carmen, Egon W. Stemle, and A. Seza Doğruöz. 2019. “Comparison of Automatic vs. Manual Language Identification in Multilingual Social Media Texts.” In Building Computer Mediated Corpora for Sociolinguistic Analysis, ed by. Ciara R. Wigham and Egon W. Stemle, 8:28–44. Presses universitaires Blaise Pascal.
Vancouver
1.
Frey J-C, Stemle EW, Doğruöz AS. Comparison of automatic vs. manual language identification in multilingual social media texts. In: Wigham CR, Stemle EW, editors. Building computer mediated corpora for sociolinguistic analysis. Presses universitaires Blaise Pascal; 2019. p. 28–44.
IEEE
[1]
J.-C. Frey, E. W. Stemle, and A. S. Doğruöz, “Comparison of automatic vs. manual language identification in multilingual social media texts,” in Building computer mediated corpora for sociolinguistic analysis, vol. 8, C. R. Wigham and E. W. Stemle, Eds. Presses universitaires Blaise Pascal, 2019, pp. 28–44.
@incollection{8694805,
  abstract     = {{Multilingual speakers communicate in more than one language in daily life and on social media. In order to process or investigate multilingual communication, there is a need for language identification. This study compares the performance of human annotators with automatic ways of language identification on a multilingual (mainly German-Italian-English) social media corpus collected in South Tyrol, Italy. Our results indicate that humans and Natural Language Processing (NLP) systems follow their individual techniques to make a decision about multilingual text messages. This results in low agreement when different annotators or NLP systems execute the same task. In general, annotators agree with each other more than NLP systems. However, there is also variation in human agreement depending on the prior establishment of guidelines for the annotation task or not.}},
  author       = {{Frey, Jennifer-Carmen and Stemle, Egon W. and Doğruöz, A. Seza}},
  booktitle    = {{Building computer mediated corpora for sociolinguistic analysis}},
  editor       = {{Wigham, Ciara R. and Stemle, Egon W.}},
  isbn         = {{9782845168596}},
  issn         = {{1960-3479}},
  keywords     = {{Automatic Language Identification,Social Media,Italian,German,South Tyrol,Lt3,Computer Mediated Communication (CMC),computational sociolinguistics,computational social sciences}},
  language     = {{eng}},
  pages        = {{28--44}},
  publisher    = {{Presses universitaires Blaise Pascal}},
  series       = {{Cahiers du Laboratoire de recherche sur le langage}},
  title        = {{Comparison of automatic vs. manual language identification in multilingual social media texts}},
  volume       = {{8}},
  year         = {{2019}},
}