Bibtex de la publication

@InProceedings{ Cl2016.1,
author = {Clos, Jérémie and Wiratunga, Nirmalie and Massie, Stewart and Cabanac, Guillaume},
title = "{Shallow techniques for argument mining (regular paper)}",
booktitle = "{European Conference on Argumentation (ECA 2015), Lisbon, Portugal, 09/06/15-12/06/15}",
editor = {Mohammed, Dima and Lewinski, Marcin},
year = {2016},
month = {juin},
publisher = {College Publications},
address = {},
volume = {63},
series = {Studies in Logic and Argumentation},
number = {2},
pages = {341--356},
language = {anglais},
URL = { -},
keywords = {argument mining, sentiment analysis, text mining},
note = {ISBN 978-1-84890-212-1},
abstract = {Argument mining has recently emerged as a promising field at the frontiers of the argumentation and text mining communities. However, most techniques developed within that field do not scale to larger amounts of data, depriving us for example of valuable insights in large-scale discussion forums. On two social media datasets, we study different lightweight scalable text mining techniques used within the sentiment analysis community and their applicability to the argument mining problem.}