Argument Mining on Twitter: Arguments, Facts and Sources

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2317–2322 Copenhagen, Denmark, September 7–11, 2017. c⃝2017 Association for Computational Linguistics Argument Mining on Twitter: Arguments, Facts and Sources Mihai Dusmanu and Elena Cabrio and Serena Villata Universit´e Cˆote dAzur, CNRS, Inria, I3S, France Abstract Social media collect and spread on the Web personal opinions, facts, fake news and all kind of information users may be interested in. Applying argument min- ing methods to such heterogeneous data sources is a challenging open research is- sue, in particular considering the peculiar- ities of the language used to write textual messages on social media. In addition, new issues emerge when dealing with ar- guments posted on such platforms, such as the need to make a distinction between personal opinions and actual facts, and to detect the source disseminating informa- tion about such facts to allow for prove- nance verification. In this paper, we ap- ply supervised classification to identify ar- guments on Twitter, and we present two new tasks for argument mining, namely facts recognition and source identification. We study the feasibility of the approaches proposed to address these tasks on a set of tweets related to the Grexit and Brexit news topics. 1 Introduction Argument mining aims at automatically extract- ing natural language arguments and their relations from a variety of textual corpora, with the fi- nal goal of providing machine-processable struc- tured data for computational models of arguments and reasoning engines (Peldszus and Stede, 2013; Lippi and Torroni, 2016). Several approaches have been proposed so far to tackle the two main tasks identified in the field: i) arguments extraction, i.e., to detect arguments within the input natural language texts and the further detection of their boundaries, and ii) relations prediction, i.e., to predict what are the relations holding between the arguments identified in the first task1. Social me- dia platforms like Twitter2 and newspapers blogs allow users to post their own viewpoints on a cer- tain topic, or to disseminate news read on news- papers. Being these texts short, without standard spelling and with specific conventions (e.g., hash- tags, emoticons), they represent an open challenge for standard argument mining approaches (Sna- jder, 2017). The nature and peculiarity of social media data rise also the need of defining new tasks in the argument mining domain (Addawood and Bashir, 2016; Llewellyn et al., 2014). In this paper, we tackle the first standard task in argument mining, addressing the research ques- tion: how to mine arguments from Twitter? Going a step further, we address also the following sub- questions that arise in the context of social media: i) how to distinguish factual arguments from opin- ions? ii) how to automatically detect the source of factual arguments? To answer these questions, we extend and annotate a dataset of tweets ex- tracted from the streams about the Grexit and the Brexit news. To address the first task of argument detection, we apply supervised classification to separate argument-tweets from non-argumentative ones. By considering …

Content truncated to 500 words