Publikationstyp: | Konferenz: Paper |
Art der Begutachtung: | Keine Angabe |
Titel: | Potential and limitations of commercial sentiment detection tools |
Autor/-in: | Cieliebak, Mark Dürr, Oliver Uzdilli, Fatih |
Tagungsband: | Proceedings of the First International Workshop on Emotion and Sentiment in Social and Expressive Media: approaches and perspectives from AI (ESSEM 2013) |
Seite(n): | 47 |
Seiten bis: | 58 |
Angaben zur Konferenz: | First International Workshop on Emotion and Sentiment in Social and Expressive Media (ESSEM 2013), Turin, Italy, 3 December 2013 |
Erscheinungsdatum: | 2013 |
Reihe: | CEUR Workshop Proceedings |
Reihenzählung: | 1096 |
Verlag / Hrsg. Institution: | RWTH Aachen |
ISSN: | 1613-0073 |
Andere Identifier: | urn:nbn:de:0074-1096-7 |
Sprache: | Englisch |
Schlagwörter: | Corpus analytics; Machine learning; Sentiment detection |
Fachgebiet (DDC): | 006: Spezielle Computerverfahren |
Zusammenfassung: | 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. In addition to the quality analysis (measured by various metrics), we also investigate the effect of increasing text length on the performance. Finally, we show that combining all tools using machine learning techniques increases the overall performance significantly. |
URI: | http://ceur-ws.org/Vol-1096/paper4.pdf https://digitalcollection.zhaw.ch/handle/11475/7121 |
Volltext Version: | Publizierte Version |
Lizenz (gemäss Verlagsvertrag): | Lizenz gemäss Verlagsvertrag |
Departement: | School of Engineering |
Organisationseinheit: | Institut für Informatik (InIT) Institut für Datenanalyse und Prozessdesign (IDP) |
Enthalten in den Sammlungen: | Publikationen School of Engineering |
Dateien zu dieser Ressource:
Es gibt keine Dateien zu dieser Ressource.
Zur Langanzeige
Cieliebak, M., Dürr, O., & Uzdilli, F. (2013). Potential and limitations of commercial sentiment detection tools [Conference paper]. Proceedings of the First International Workshop on Emotion and Sentiment in Social and Expressive Media: Approaches and Perspectives from AI (ESSEM 2013), 47–58. http://ceur-ws.org/Vol-1096/paper4.pdf
Cieliebak, M., Dürr, O. and Uzdilli, F. (2013) ‘Potential and limitations of commercial sentiment detection tools’, in Proceedings of the First International Workshop on Emotion and Sentiment in Social and Expressive Media: approaches and perspectives from AI (ESSEM 2013). RWTH Aachen, pp. 47–58. Available at: http://ceur-ws.org/Vol-1096/paper4.pdf.
M. Cieliebak, O. Dürr, and F. Uzdilli, “Potential and limitations of commercial sentiment detection tools,” in Proceedings of the First International Workshop on Emotion and Sentiment in Social and Expressive Media: approaches and perspectives from AI (ESSEM 2013), 2013, pp. 47–58. [Online]. Available: http://ceur-ws.org/Vol-1096/paper4.pdf
CIELIEBAK, Mark, Oliver DÜRR und Fatih UZDILLI, 2013. Potential and limitations of commercial sentiment detection tools. In: Proceedings of the First International Workshop on Emotion and Sentiment in Social and Expressive Media: approaches and perspectives from AI (ESSEM 2013) [online]. Conference paper. RWTH Aachen. 2013. S. 47–58. Verfügbar unter: http://ceur-ws.org/Vol-1096/paper4.pdf
Cieliebak, Mark, Oliver Dürr, and Fatih Uzdilli. 2013. “Potential and Limitations of Commercial Sentiment Detection Tools.” Conference paper. In Proceedings of the First International Workshop on Emotion and Sentiment in Social and Expressive Media: Approaches and Perspectives from AI (ESSEM 2013), 47–58. RWTH Aachen. http://ceur-ws.org/Vol-1096/paper4.pdf.
Cieliebak, Mark, et al. “Potential and Limitations of Commercial Sentiment Detection Tools.” Proceedings of the First International Workshop on Emotion and Sentiment in Social and Expressive Media: Approaches and Perspectives from AI (ESSEM 2013), RWTH Aachen, 2013, pp. 47–58, http://ceur-ws.org/Vol-1096/paper4.pdf.
Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.