Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cieliebak, Mark | - |
dc.contributor.author | Dürr, Oliver | - |
dc.contributor.author | Uzdilli, Fatih | - |
dc.date.accessioned | 2018-06-26T14:38:16Z | - |
dc.date.available | 2018-06-26T14:38:16Z | - |
dc.date.issued | 2014 | - |
dc.identifier.isbn | 978-1-63266-621-5 | de_CH |
dc.identifier.uri | https://digitalcollection.zhaw.ch/handle/11475/7360 | - |
dc.description.abstract | In this paper, we analyze the quality of several commercial tools for sentiment detection. All tools are tested on nearly 30,000 short texts from various sources, such as tweets, news, reviews etc. The best commercial tools have average accuracy of 60%. We then apply machine learning techniques (Random Forests) to combine all tools, and show that this results in a meta-classifier that improves the overall performance significantly. | de_CH |
dc.language.iso | en | de_CH |
dc.publisher | Association for Computational Linguistics | de_CH |
dc.rights | Licence according to publishing contract | de_CH |
dc.subject | Opinion mining | de_CH |
dc.subject | Machine learning | de_CH |
dc.subject | Sentiment analysis | de_CH |
dc.subject | Corpus analytics | de_CH |
dc.subject.ddc | 410.285: Computerlinguistik | de_CH |
dc.title | Meta-classifiers easily improve commercial sentiment detection tools | de_CH |
dc.type | Konferenz: Paper | de_CH |
dcterms.type | Text | de_CH |
zhaw.departement | School of Engineering | de_CH |
zhaw.organisationalunit | Institut für Informatik (InIT) | de_CH |
zhaw.organisationalunit | Institut für Datenanalyse und Prozessdesign (IDP) | de_CH |
zhaw.conference.details | 9th International Conference on Language Resources and Evaluation, Reykjavik, Iceland, 26-31 May 2014 | de_CH |
zhaw.funding.eu | No | de_CH |
zhaw.originated.zhaw | Yes | de_CH |
zhaw.pages.end | 3947 | de_CH |
zhaw.pages.start | 3943 | de_CH |
zhaw.publication.status | publishedVersion | de_CH |
zhaw.publication.review | Not specified | de_CH |
zhaw.title.proceedings | Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC 2014) | de_CH |
zhaw.webfeed | Software Systems | de_CH |
zhaw.webfeed | Natural Language Processing | de_CH |
Appears in collections: | Publikationen School of Engineering |
Files in This Item:
There are no files associated with this item.
Show simple item record
Cieliebak, M., Dürr, O., & Uzdilli, F. (2014). Meta-classifiers easily improve commercial sentiment detection tools [Conference paper]. Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC 2014), 3943–3947.
Cieliebak, M., Dürr, O. and Uzdilli, F. (2014) ‘Meta-classifiers easily improve commercial sentiment detection tools’, in Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC 2014). Association for Computational Linguistics, pp. 3943–3947.
M. Cieliebak, O. Dürr, and F. Uzdilli, “Meta-classifiers easily improve commercial sentiment detection tools,” in Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC 2014), 2014, pp. 3943–3947.
CIELIEBAK, Mark, Oliver DÜRR und Fatih UZDILLI, 2014. Meta-classifiers easily improve commercial sentiment detection tools. In: Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC 2014). Conference paper. Association for Computational Linguistics. 2014. S. 3943–3947. ISBN 978-1-63266-621-5
Cieliebak, Mark, Oliver Dürr, and Fatih Uzdilli. 2014. “Meta-Classifiers Easily Improve Commercial Sentiment Detection Tools.” Conference paper. In Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC 2014), 3943–47. Association for Computational Linguistics.
Cieliebak, Mark, et al. “Meta-Classifiers Easily Improve Commercial Sentiment Detection Tools.” Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC 2014), Association for Computational Linguistics, 2014, pp. 3943–47.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.