Behind the Article: Recognizing Dialog Acts in Wikipedia Talk Pages

Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, pages 777–786, Avignon, France, April 23 - 27 2012. c⃝2012 Association for Computational Linguistics Behind the Article: Recognizing Dialog Acts in Wikipedia Talk Pages Oliver Ferschke‡, Iryna Gurevych†‡ and Yevgen Chebotar‡ † Ubiquitous Knowledge Processing Lab (UKP-DIPF) German Institute for Educational Research and Educational Information ‡ Ubiquitous Knowledge Processing Lab (UKP-TUDA) Department of Computer Science Technische Universit¨at Darmstadt http://www.ukp.tu-darmstadt.de Abstract In this paper, we propose an annota- tion schema for the discourse analysis of Wikipedia Talk pages aimed at the coor- dination efforts for article improvement. We apply the annotation schema to a cor- pus of 100 Talk pages from the Simple English Wikipedia and make the resulting dataset freely available for download1. Fur- thermore, we perform automatic dialog act classification on Wikipedia discussions and achieve an average F1-score of 0.82 with our classification pipeline. 1 Introduction Over the past decade, the paradigm of information sharing in the web has shifted towards participa- tory and collaborative content production. Texts are no longer exclusively prepared by individuals and then shared with the community. They are in- creasingly created collaboratively by multiple au- thors and iteratively revised by the community. When researchers first conducted surveys on professional writers in the 1980s, they found that the collaborative writing process differs consider- ably from the way individual writing is done (Pos- ner and Baecker, 1992). In joint writing, the writ- ers have to externalize processes that are other- wise not made explicit, like the planning and the organization of the text. The authors have to com- municate how the text should be written and what exactly it should contain. Today, many tools are available that support collaborative writing. A tool that has particu- larly taken hold is the Wiki, a web-based, asyn- 1http://www.ukp.tu-darmstadt.de/data/ wikidiscourse chronous co-authoring tool. A unique character- istic of Wikis is the documentation of the edit history which keeps track of every change that is made to a Wiki page. With this information, it is possible to reconstruct the writing process from the beginning to the end. Additionally, many Wikis offer their users a communication platform, the Talk pages, where they can discuss the ongo- ing writing process with other users. The most prominent example for a successful, large-scale Wiki is Wikipedia, a collaboratively created online encyclopedia, which has grown considerably since its launch in 2001, and con- tains a total of almost 20 million articles in 282 languages and dialects, as of Sept. 2011. As there is no editorial body that manages Wikipedia top- down, it is an open question how the huge on- line community around Wikipedia regulates and enforces standards of behavior and article qual- ity. The user discussions on the article Talk pages might shed light on this issue and give an insight into the otherwise hidden processes of collabora- tion that, until now, could only be analyzed via interviews or group observations in experimental settings. The main goal of the present …

Content truncated to 500 words