Detecting Stance in Czech News Commentaries

Tomáš Hercig Peter Krejzl Josef Steinberger and Ladislav Lenc
Proceedings of the 17th ITAT: Slovenskočeský NLP workshop (SloNLP 2017) (2017)


Research topics:

Sentiment Analysis


This paper describes our system created to detect stance in online discussions. The goal is to identify whether the author of a comment is in favor of the given target or against. We created an extended corpus of Czech news comments and evaluated a support vector machines classifier, a maximum entropy classifier, and a convolu- tional neural network.



@inproceedings{SLON2017-Stance, title = {Detecting Stance in Czech News Commentaries}, author = {Tom\'{a}\v{s} Hercig and Peter Krejzl and Barbora Hourov\'{a} and Josef Steinberger and Ladislav Lenc}, booktitle = {Proceedings of the 17th {ITAT}: Slovensko{\v{c}}esk{\'{y}} {NLP} workshop (Slo{NLP} 2017)}, editor = {Jaroslava Hlav{\'{a}}{\v{c}}ov{\'{a}}}, year = {2017}, publisher = {CreateSpace Independent Publishing Platform}, organization = {Comenius University in Bratislava, Faculty of Mathematics, Physics and Informatics}, address = {Bratislava, Slovakia}, venue = {Martinsk{\'{e}} hole}, series = {{CEUR} Workshop Proceedings}, volume = {1885}, pages = {176-180}, isbn = {978-1974274741}, issn = {1613-0073} }
Back to Top