Please use this identifier to cite or link to this item:
https://doi.org/10.21256/zhaw-1526| Publication type: | Conference paper |
| Type of review: | Peer review (publication) |
| Title: | Potential and limitations of cross-domain sentiment classification |
| Authors: | von Grünigen, Dirk Weilenmann, Martin Deriu, Jan Milan Cieliebak, Mark |
| DOI: | 10.18653/v1/W17-1103 10.21256/zhaw-1526 |
| Proceedings: | Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media |
| Page(s): | 17 |
| Pages to: | 24 |
| Conference details: | Fifth International Workshop on Natural Language Processing for Social Media, Valencia, Spain, 3-7 April 2017 |
| Issue Date: | 2017 |
| Publisher / Ed. Institution: | Association for Computational Linguistics |
| Publisher / Ed. Institution: | Stroudsburg |
| ISBN: | 9781510838710 |
| Language: | English |
| Subjects: | Sentiment Analysis |
| Subject (DDC): | 006: Special computer methods |
| Abstract: | In this paper we investigate the cross-domain performance of sentiment analysis systems. For this purpose we train a convolutional neural network (CNN) on data from different domains and evaluate its performance on other domains. Furthermore, we evaluate the usefulness of combining a large amount of different smaller annotated corpora to a large corpus. Our results show that more sophisticated approaches are required to train a system that works equally well on various domains. |
| URI: | https://digitalcollection.zhaw.ch/handle/11475/1852 |
| Fulltext version: | Published version |
| License (according to publishing contract): | Licence according to publishing contract |
| Departement: | School of Engineering |
| Organisational Unit: | Institute of Computer Science (InIT) |
| Appears in collections: | Publikationen School of Engineering |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| W17-1103.pdf | 1.67 MB | Adobe PDF |  View/Open |
Show full item record
von Grünigen, D., Weilenmann, M., Deriu, J. M., & Cieliebak, M. (2017). Potential and limitations of cross-domain sentiment classification [Conference paper]. Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media, 17–24. https://doi.org/10.18653/v1/W17-1103
von Grünigen, D. et al. (2017) ‘Potential and limitations of cross-domain sentiment classification’, in Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media. Stroudsburg: Association for Computational Linguistics, pp. 17–24. Available at: https://doi.org/10.18653/v1/W17-1103.
D. von Grünigen, M. Weilenmann, J. M. Deriu, and M. Cieliebak, “Potential and limitations of cross-domain sentiment classification,” in Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media, 2017, pp. 17–24. doi: 10.18653/v1/W17-1103.
VON GRÜNIGEN, Dirk, Martin WEILENMANN, Jan Milan DERIU und Mark CIELIEBAK, 2017. Potential and limitations of cross-domain sentiment classification. In: Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media. Conference paper. Stroudsburg: Association for Computational Linguistics. 2017. S. 17–24. ISBN 9781510838710
von Grünigen, Dirk, Martin Weilenmann, Jan Milan Deriu, and Mark Cieliebak. 2017. “Potential and Limitations of Cross-Domain Sentiment Classification.” Conference paper. In Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media, 17–24. Stroudsburg: Association for Computational Linguistics. https://doi.org/10.18653/v1/W17-1103.
von Grünigen, Dirk, et al. “Potential and Limitations of Cross-Domain Sentiment Classification.” Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media, Association for Computational Linguistics, 2017, pp. 17–24, https://doi.org/10.18653/v1/W17-1103.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.