@inproceedings{3dc4ba687a5f4095b716bb880afec4c6,
title = "A corpus of Wikipedia discussions: over the years, with topic, power and gender labels",
abstract = "In order to gain a deep understanding of how social context manifests in interactions, we need data that represents interactions from a large community of people over a long period of time, capturing different aspects of social context. In this paper, we present a large corpus of Wikipedia Talk page discussions that are collected from a broad range of topics, containing discussions that happened over a period of 15 years. The dataset contains 166,322 discussion threads, across 1236 articles/topics that span 15 different topic categories or domains. The dataset also captures whether the post is made by an registered user or not, and whether he/she was an administrator at the time of making the post. It also captures the Wikipedia age of editors in terms of number of months spent as an editor, as well as their gender. This corpus will be a valuable resource to investigate a variety of computational sociolinguistics research questions regarding online social interactions.",
keywords = "Computational sociolinguistics, Dialog, Gender, Online interactions, Power, Wikipedia",
author = "Vinodkumar Prabhakaran and Owen Rambow",
year = "2016",
language = "English",
series = "Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016",
publisher = "European Language Resources Association (ELRA)",
pages = "2034--2038",
editor = "Nicoletta Calzolari and Khalid Choukri and Helene Mazo and Asuncion Moreno and Thierry Declerck and Sara Goggi and Marko Grobelnik and Jan Odijk and Stelios Piperidis and Bente Maegaard and Joseph Mariani",
booktitle = "Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016",
note = "10th International Conference on Language Resources and Evaluation, LREC 2016 ; Conference date: 23-05-2016 Through 28-05-2016",
}