Style mining of electronic messages for multiple authorship discrimination: first results

ABSTRACT

This paper considers the use of computational stylistics for performing authorship attribution of electronic messages, addressing categorization problems with as many as 20 different classes (authors). Effective stylistic characterization of text is potentially useful for a variety of tasks, as language style contains cues regarding the authorship, purpose, and mood of the text, all of which would be useful adjuncts to information retrieval or knowledge-management tasks. We focus here on the problem of determining the author of an anonymous message, based only on the message text. Several multiclass variants of the Winnow algorithm were applied to a vector representation of the message texts to learn models for discriminating different authors. We present results comparing the classification accuracy of the different approaches. The results show that stylistic models can be accurately learned to determine an author's identity.

REFERENCES

• 1: S. Argamon, M. Koppel, J. Fine, and A. R. Shimony. Gender, genre, and writing style in formal written texts. Text, 23(3), 2003.
• 2: J. F. Burrows. Computers and the study of literature. In Computers and Written Texts, pages 167--204. Oxford: Blackwell, 1992.
• 3: Koby Crammer , Yoram Singer, Ultraconservative Online Algorithms for Multiclass Problems, Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory, p.99-115, July 16-19, 2001
• 4: Nello Cristianini , John Shawe-Taylor, An introduction to support Vector Machines: and other kernel-based learning methods, Cambridge University Press, New York, NY, 1999
• 5: I. Dagan, Y. Karov, and D. Roth. Mistake-driven learning in text categorization. In Proc. EMNLP-97, Providence, RI.
• 6: O. de Vel. Mining e-mail authorship In KDD-2000 Workshop on Text Mining, Boston, MA, 2000.
• 7: R. S. Forsyth and D. I. Holmes. Feature finding for text classification. Lit. and Ling. Comp., 11(4):163--174, 1996.
• 8: S. Har-Peled, D. Roth, and D. Zimak. Constraint classification for multiclass classification and ranking. In NIPS-15, 2002.
• 9: D. I. Holmes. The evolution of stylometry in humanities scholarship. Lit. and Ling. Comp., 13(3):111--117, 1998.
• 10: J. Karlgren. Stylistic Experiments for Information Retrieval. PhD thesis, SICS, 2000.
• 11: Jyrki Kivinen , Manfred K. Warmuth, Exponentiated gradient versus gradient descent for linear predictors, Information and Computation, v.132 n.1, p.1-63, Jan. 10, 1997 [doi>10.1006/inco.1996.2612]
• 12: M. Koppel, S. Argamon, and A. R. Shimoni. Automatically categorizing written texts by author gender. Lit. and Ling. Comp., 17(4), 2003.
• 13: R. A. J. Matthews and T. V. N. Merriam. Neural computation in stylometry I: An application to the works of Shakespeare and Fletcher. Lit. and Ling. Comp., 8:103--209, 1993.
• 14: A. McEnery and M. Oakes. Authorship studies/textual statistics, pages 234--248. Marcel Dekker, 2000.
• 15: Roger Mitton, Spelling checkers,spelling correctors and the misspellings of poor spellers, Information Processing and Management: an International Journal, v.23 n.5, p.495-505, Sept. 1987 [doi>10.1016/0306-4573(87)90116-6]
• 16: F. Mosteller and D. Wallace. Inference and Disputed Authorship: The Federalist. Addison-Wesley, Reading, Massachusetts, 1964.
• 17: Fabrizio Sebastiani, Machine learning in automated text categorization, ACM Computing Surveys (CSUR), v.34 n.1, p.1-47, March 2002 [doi>10.1145/505282.505283]
• 18: Efstathios Stamatatos , George Kokkinakis , Nikos Fakotakis, Automatic text categorization in terms of genre and author, Computational Linguistics, v.26 n.4, p.471-495, December 2000 [doi>10.1162/089120100750105920]
• 19: F. Tweedie, S. Singh, and D. Holmes. Neural network applications in stylometry: The federalist papers. Computers and the Humanities, 30(1):1--10, 1996.
• 20: Maria Wolters , Mathias Kirsten, Exploring the use of linguistic features in domain and genre classification, Proceedings of the ninth conference on European chapter of the Association for Computational Linguistics, June 08-12, 1999, Bergen, Norway [doi>10.3115/977035.977055]
• 21: G. U. Yule. Statistical Study of Literary Vocabulary. Cambridge U. Press, 1944.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning

Additional Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval

Keywords:
authorship attribution, computational stylistics, electronic communication, text categorization, text mining