Public Debates on the Web
With the advent of social media, any piece of information may be spread all over the world in no time. Furthermore, the vast number of available communication channels makes it difficult to cross-check information that has been (re-)published on different media in real time. In this context where people may express their positions on many subjects, as well as launching new open initiatives, the public needs a mean to gather and compare ideas and opinions in a structured manner. The present paper presents the Open image in new window project, which aims to develop a collaborative platform where opinions, namely arguments, are gathered, analyzed and linked to one another via explicit relations. Open image in new window relies on various Natural Language Processing modules to semi-automatically extract information from the web and propose meaningful visualizations to the platform’s contributors. Furthermore, public actors may be identified and attached to the ideas they publish to create a structured knowledge base where annotated texts, extracted positions and alliances may be identified.
KeywordsSocial web Public debate Argumentation Speech acts Natural language processing
This work is funded by the Walloon Region of Belgium, under convention no. 1318202 (Programme Germaine Tillion). The authors also thank, in alphabetic order, L.-A. Cougnon, B. Delvaux, C. Fairon, P. Francq, S. Roekhaut and D. Uygur for their various contributions to this project.
Website and sources. A running instance of the platform can be found at https://webdeb.be. The sources are distributed under the LGPL license and available at https://bitbucket.org/fabgilson/webdeb-sources.
- 1.Austin, J.L.: How to Do Things with Words. Harvard University Press, Cambridge (1962). 2nd edn. (2005)Google Scholar
- 3.Bittar, A., Cougnon, A., Delvaux, B., Gilson, F., Fairon, C., Schobbens, P.Y.: Webdeb: learning to analyse public debate with the help of NLP. Submitted to Traitement Automatique des Langues on 28 October 2016. https://staff.info.unamur.be/fgi/webdeb/TAL_en_ex.pdf
- 5.Erhmann, M.: Les entités nommées, de la linguistique au TAL: statut théorique et méthodes de désambiguïsation. Ph.D. thesis, Université Paris 7, France (2008)Google Scholar
- 6.Jeong, M., Lin, C.Y., Lee, G.G.: Semi-supervised speech act recognition in emails and forums. In: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, EMNLP 2009, vol. 3, pp. 1250–1259. Association for Computational Linguistics, Stroudsburg (2009). http://dl.acm.org/citation.cfm?id=1699648.1699671
- 7.Litman, D.: Natural language processing for enhancing teaching and learning. In: Proceedings 30th Conference on Artificial Intelligence (AAAI), pp. 4170–4176. Phoenix (AZ), USA (2016)Google Scholar
- 8.Nadeau, D., Sekine, S.: A survey of named entity recognition and classification. In: Lingvisticæ Investigationes, vol. 30, pp. 3–26. John Benjamins Publishing Company (2007)Google Scholar
- 11.Toulmin, S., Rieke, R., Janik, A.: An Introduction to Reasoning, 2nd edn. Macmillian Publishing Co., Inc., New York (1984)Google Scholar
- 12.Vosoughi, S., Roy, D.: Tweet acts: a speech act classifier for twitter. In: Proceedings of the 10th International Conference on Web and Social Media, pp. 711–715 (2016). http://www.aaai.org/ocs/index.php/ICWSM/ICWSM16/paper/view/13171
- 14.Zhang, R., Gao, D., Li, W.: What are tweeters doing: recognizing speech acts in twitter. In: Proceedings of the 5th AAAI Conference on Analyzing Microtext, AAAIWS 2011-05, pp. 86–91. AAAI Press (2011). http://dl.acm.org/citation.cfm?id=2908630.2908645