Abstract
E-mails to government institutions as well as to large companies may contain a large proportion of queries that can be answered in a uniform way. We analysed and manually annotated 4,404 e-mails from citizens to the Swedish Social Insurance Agency, and compared two methods for detecting answerable e-mails: manually-created text patterns (rule-based) and machine learning-based methods. We found that the text pattern-based method gave much higher precision at 89 percent than the machine learning-based method that gave only 63 percent precision. The recall was slightly higher (66 percent) for the machine learning-based methods than for the text patterns (47 percent). We also found that 23 percent of the total e-mail flow was processed by the automatic e-mail answering system.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Busemann, S., Schmeier, S., Arens, R.G.: Message classification in the call center. In: Proceedings of the Sixth Conference on Applied Natural Language Processing, Seattle, Washington, pp. 158–165. ACL (2000)
Scheffer, T.: E-mail answering assistance by semi-supervised text classification. Intelligent Data Analysis 8(5), 481–493 (2004)
Lapalme, G., Kosseim, L.: Mercure: Towards an automatic e-mail follow-up system. IEEE Computational Intelligence Bulletin 2(1), 14–18 (2003)
Sneiders, E.: Automated E-mail Answering by Text Pattern Matching. In: Loftsson, H., Rögnvaldsson, E., Helgadóttir, S. (eds.) IceTAL 2010. LNCS, vol. 6233, pp. 381–392. Springer, Heidelberg (2010)
Dalianis, H., Rosell, M., Sneiders, E.: Clustering E-mails for the swedish social insurance agency – what part of the E-mail thread gives the best quality? In: Loftsson, H., Rögnvaldsson, E., Helgadóttir, S. (eds.) IceTAL 2010. LNCS, vol. 6233, pp. 115–120. Springer, Heidelberg (2010)
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA Data Mining Software: An Update. SIGKDD Explorations 11( 1) (2005)
Cohn, D.A., Zoubin, G., Michael, I.J.: Active learning with statistical models. Journal of Artificial Intelligence Research 4, 129–145 (1996)
Lampert, A., Dale, R., Paris, C.: Detecting Emails Containing Requests for Action. In: The Proceeding of Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, NAACL-HLT, Los Angeles, pp. 984–992 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dalianis, H., Sjöbergh, J., Sneiders, E. (2011). Comparing Manual Text Patterns and Machine Learning for Classification of E-Mails for Automatic Answering by a Government Agency. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2011. Lecture Notes in Computer Science, vol 6609. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19437-5_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-19437-5_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19436-8
Online ISBN: 978-3-642-19437-5
eBook Packages: Computer ScienceComputer Science (R0)