A POS Tagger for Social Media Texts Trained on Web Comments

 

Melanie Neunerdt, Michael Reyer, and Rudolf Mathar

The authors are with the Institute for Theoretical Information Technology, RWTH Aachen University, Germany (e-mail: neunerdt@ti.rwth-aachen.de, reyer@ti.rwth-aachen.de, mathar@ti.rwth-aachen.de).

 

Manuscript received on August 2, 2013.
Accepted for publication on September 30, 2013.

 

Abstract

Using social media tools such as blogs and forums have become more and more popular in recent years. Hence, a huge collection of social media texts from different communities is available for accessing user opinions, e.g., for marketing studies or acceptance research. Typically, methods from Natural Language Processing are applied to social media texts to automatically recognize user opinions. A fundamental component of the linguistic pipeline in Natural Language Processing is Part-of-Speech tagging. Most state-of-the-art Part-of-Speech taggers are trained on newspaper corpora, which differ in many ways from non-standardized social media text. Hence, applying common taggers to such texts results in performance degradation. In this paper, we present extensions to a basic Markov model tagger for the annotation of social media texts. Considering the German standard Stuttgart/Tübinger TagSet (STTS), we distinguish 54 tag classes. Applying our approach improves the tagging accuracy for social media texts considerably, when we train our model on a combination of annotated texts from newspapers and Web comments.

Key words: Natural language processing, part-of-speech tagging, opinion mining, German.

  

DESCARGAR ARTÍCULO EN FORMATO PDF

 

Acknowledgment

This work was partially supported by the Project House HumTec at RWTH Aachen University, Germany. We would like to thank Phillip VaBen for his contribution.

 

References

[1] K. Toutanova, D. Klein, C. D. Manning, and Y. Singer, "Feature-rich Part-of-Speech Tagging With a Cyclic Dependency Network," in Proceedings of Human Language Technology Conference, 2003, pp. 173-180.         [ Links ]

[2] P. Gadde, L. V. Subramaniam, and T. A. Faruquie, "Adapting a WSJ Trained Part-of-Speech Tagger to Noisy Text: Preliminary Results," in Proceedings of the 2011 Joint Workshop on Multilingual OCR and Analytics for Noisy Unstructured Text Data, 2011, pp. 5:1-5:8.         [ Links ]

[3] H. Schmid, "Probabilistic Part-of-Speech Tagging Using Decision Trees," in Proceedings of International Conference on New Methods in Language Processing, 1994, pp. 44-49.         [ Links ]

[4] ----------, "Improvements in Part-of-Speech Tagging With an Application to German," in Proceedings of the ACL SIGDAT-Workshop, 1995, pp. 47-50.         [ Links ]

[5] T. Brants, "TnT - A Statistical Part-of-Speech Tagger," in Proceedings of the 6th Applied Natural Language Processing Conference, 2000, pp. 224-231.         [ Links ]

[6] A. Schiller, S. Teufel, C. Stóckert, and C. Thielen, "Guidelines für das Tagging deutscher Textcorpora mit STTS," 1999, university of Stuttgart.         [ Links ]

[7] J. Giménez and L. Márquez, "Svmtool: A General POS Tagger Generator Based on Support Vector Machines," in Proceedings of the 4th International Conference on Language Resources and Evaluation, 2004, pp. 43-46.         [ Links ]

[8] H. Schmid, "Part-of-Speech Tagging With Neural Networks," in Proceedings of the 15th Conference on Computational Linguistics, 1994, pp. 172-176.         [ Links ]

[9] M. Volk and G. Schneider, "Comparing a statistical and a rule-based tagger for German," in Proceedings of the 4th Conference on Natural Language Processing, 1998, pp. 125-137.         [ Links ]

[10] E. Giesbrecht and S. Evert, "Is Part-of-Speech Tagging a Solved Task? An Evaluation of POS Taggers for the German Web as Corpus," in Proceedings of the Fifth Web as Corpus Workshop, 2009, pp. 27-35.         [ Links ]

[11] A. Mikheev, "Automatic Rule Induction for Unknown Word Guessing," Computational Linguistics, vol. 23, pp. 405-423, 1997.         [ Links ]

[12] H. Schtitze, "Distributional Part-of-Speech Tagging," in Proceedings of 7th Conference of the European Chapter of the Association for Computational Linguistics, 1995, pp. 141-148.         [ Links ]

[13] O. Owoputi, B. O'Connor, C. Dyer, K. Gimpel, and N. Schneider, "Part-of-Speech Tagging for Twitter: Word Clusters and Other Advances," School of Computer Science, Carnegie Mellon University, Tech. Rep., 2012.         [ Links ]

[14] K. Gimpel, N. Schneider, B. O'Connor, D. Das, D. Mills, J. Eisenstein, M. Heilman, D. Yogatama, J. Flanigan, and N. A. Smith, "Part-of-Speech tagging for Twitter: annotation, features, and experiments," in Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics, 2011, pp. 42-47.         [ Links ]

[15] M. Neunerdt, M. Reyer, and R. Mathar, "Part-of-Speech Tagging for Social Media Texts," in Proceedings of The International Conference of the German Society for Computational Linguistics and Language Technology, 2013.         [ Links ]

[16] B. Trevisan, M. Neunerdt, and E.-M. Jakobs, "A Multi-level Annotation Model for Fine-grained Opinion Detection in German Blog Comments," in Proceedings of KONVENS 2012, 2012, pp. 179-188.         [ Links ]

[17] M. BeiBwenger, M. Ermakova, A. Geyken, L. Lemnitzer, and A. Storrer, "A TEI Schema for the Representation of Computer-mediated Communication," Journal of the Text Encoding Initiative, no. 3, pp. 1-31, 2012. [Online]. Available: http://jtei.revues.org/476        [ Links ]

[18] J. R. Quinlan, "Induction of Decision Trees," Machine Learning, pp. 81-106, 1986.         [ Links ]

[19] S. Brants, S. Dipper, P. Eisenberg, S. Hansen-Schirra, E. Kónig, W. Lezius, C. Rohrer, G. Smith, and H. Uszkoreit, "TIGER: Linguistic Interpretation of a German Corpus," Research on Language & Computation, pp. 597-620, 2004.         [ Links ]

[20] M. BeiBwenger, "Corpora zur computervermittelten (internetbasierten) Kommunikation," Zeitschrift für germanistische Linguistik, vol. 35, pp. 496-503, 2007.         [ Links ]