Author verification by linguistic profiling: An exploration of the parameter space

ABSTRACT

This article explores the effects of parameter settings in linguistic profiling, a technique in which large numbers of counts of linguistic features are used as a text profile which can then be compared to average profiles for groups of texts. Although the technique proves to be quite effective for authorship verification, with the best overall parameter settings yielding an equal error rate of 3% on a test corpus of student essays, the optimal parameters vary greatly depending on author and evaluation criterion.

REFERENCES

• 1: Baayen, R. H., Van Halteren, H., Neijt, A., and Tweedie, F. 2002. An experiment in authorship attribution. In Proceedings of the International Conference in Textual Data Statistical Analysis (JADT). 69--75.
• 2: Broeders, T. 2001. Forensic speech and audio analysis, forensic linguistics 1998-2001---A review. In Proceedings of the 13th Interpol Forensic Science Symposium Lyon, France.
• 3: Chaski, C. 2001. Empirical evaluations of language-based author identification techniques. Forensic Linguistics 8, 1, 1--65.
• 4: Coppen, P. A. 2003. Rejuvenating the amazon parser. Computational Linguistics in the Netherlands (CLIN'03), Antwerp, Belgium (Dec).
• 5: Hans van Halteren, Linguistic profiling for author recognition and verification, Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics, p.199-es, July 21-26, 2004, Barcelona, Spain [doi>10.3115/1218955.1218981]
• 6: Hans van Halteren , Walter Daelemans , Jakub Zavrel, Improving accuracy in word class tagging through the combination of machine learning systems, Computational Linguistics, v.27 n.2, p.199-229, June 2001 [doi>10.1162/089120101750300508]
• 7: Hans Van Halteren , Nelleke Oostdijk, Linguistic profiling of texts for the purpose of language verification, Proceedings of the 20th international conference on Computational Linguistics, p.966-es, August 23-27, 2004, Geneva, Switzerland [doi>10.3115/1220355.1220494]
• 8: van Halteren, H., Haverkort, M., Baayen, R. H., Neijt, A., and Tweedie, F. 2005. New machine learning methods demonstrate the existence of a human stylome. J. Quantitat. Linguistics 12, 1, 65--78.
• 9: Holmes, D. 1998. Authorship attribution. Literary Linguistic Comput. 13, 3, 111--117.
• 10: Kešelj, V., Peng, F., Cercone, N., and Thomas, C. 2003. N-gram-based author profiles for authorship attribution. In Proceedings of the Pacific Conference Association for Computational Linguistics (PACLING'03). Halifax, Nova Scotia, Canada (Aug.).
• 11: Koppel, M., and Schler, J. 2003. Exploiting stylistic idiosyncrasies for authorship attribution. In Proceedings of Workshop on Computational Approaches to Style Analysis and Synthesis, (IJCAI'03). Acapulco, Mexico.
• 12: Koppel, M., Akiva, N., and Dagan, I. 2003. A corpus-independent feature set for style based text categorization. In Proceedings of Workshop on Computational Approaches to Style Analysis and Synthesis (IJCAI'03). Acapulco, Mexico.
• 13: Mosteller, F. and Wallace, D. L. 1984. Applied Bayesian and Classical Inference in the Case of the Federalist Papers, 2nd ed. Springer Verlag, Berlin, Germany.
• 14: Uit Den Boogaart, P. C. 1975. Woordfrequenties in geschreven en gesproken Nederlands. Oosthoek, Scheltema & Holkema, Utrecht.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.7 Natural Language Processing
          Subjects: Text analysis

Additional Classification:
  I. Computing Methodologies
  I.5 PATTERN RECOGNITION
      I.5.1 Models
          Subjects: Statistical
  I.7 DOCUMENT AND TEXT PROCESSING
      I.7.m Miscellaneous

  J. Computer Applications
  J.5 ARTS AND HUMANITIES
      Subjects: Linguistics; Literature

General Terms:
Algorithms, Experimentation, Security

Keywords:
Authorship attribution, authorship recognition, authorship verification, machine learning