Comparing manual text patterns and machine learning for classification of e-mails for automatic answering by a government agency
2011 (English)In: 12th International Conference on Computational Linguistics and Intelligent Text Processing, CICLing 2011, 2011, no PART 2, 234-243 p.Conference paper (Refereed)
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.
Place, publisher, year, edition, pages
2011. no PART 2, 234-243 p.
, Lecture Notes in Computer Science, ISSN 0302-9743 ; 6609
automatic e-mail answering, E-government, machine learning, Naïve Bayes, SVM, text pattern matching, Computational linguistics, Government data processing, Learning systems, Pattern matching, Text processing, Word processing, Electronic mail
IdentifiersURN: urn:nbn:se:kth:diva-151431DOI: 10.1007/978-3-642-19437-5_19ISI: 000302000800019ScopusID: 2-s2.0-79952274522ISBN: 9783642194368OAI: oai:DiVA.org:kth-151431DiVA: diva2:748908
20 February 2011 through 26 February 2011, Tokyo
QC 201409222014-09-222014-09-222014-09-22Bibliographically approved