Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen:
https://doi.org/10.21256/zhaw-1526
Publikationstyp: | Konferenz: Paper |
Art der Begutachtung: | Peer review (Publikation) |
Titel: | Potential and limitations of cross-domain sentiment classification |
Autor/-in: | von Grünigen, Dirk Weilenmann, Martin Deriu, Jan Milan Cieliebak, Mark |
DOI: | 10.18653/v1/W17-1103 10.21256/zhaw-1526 |
Tagungsband: | Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media |
Seite(n): | 17 |
Seiten bis: | 24 |
Angaben zur Konferenz: | Fifth International Workshop on Natural Language Processing for Social Media, Valencia, Spain, 3-7 April 2017 |
Erscheinungsdatum: | 2017 |
Verlag / Hrsg. Institution: | Association for Computational Linguistics |
Verlag / Hrsg. Institution: | Stroudsburg |
ISBN: | 9781510838710 |
Sprache: | Englisch |
Schlagwörter: | Sentiment Analysis |
Fachgebiet (DDC): | 006: Spezielle Computerverfahren |
Zusammenfassung: | 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 |
Volltext Version: | Publizierte Version |
Lizenz (gemäss Verlagsvertrag): | Lizenz gemäss Verlagsvertrag |
Departement: | School of Engineering |
Organisationseinheit: | Institut für Informatik (InIT) |
Enthalten in den Sammlungen: | Publikationen School of Engineering |
Dateien zu dieser Ressource:
Datei | Beschreibung | Größe | Format | |
---|---|---|---|---|
W17-1103.pdf | 1.67 MB | Adobe PDF | Öffnen/Anzeigen |
Zur Langanzeige
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.
Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.