Argument Extraction from News, Blogs, and the Social Web

Abstract

Argument extraction is the task of identifying arguments, along with their components in text. Arguments can be usually decomposed into a claim and one or more premises justifying it. Among the novel aspects of this work is the thematic domain itself which relates to Social Media, in contrast to traditional research in the area, which concentrates mainly on law documents and scientific publications. The huge increase of social media communities, along with their user tendency to debate, makes the identification of arguments in these texts a necessity. Argument extraction from Social Media is more challenging because texts may not always contain arguments, as is the case of legal documents or scientific publications usually studied. In addition, being less formal in nature, texts in Social Media may not even have proper syntax or spelling. This paper presents a two-step approach for argument extraction from social media texts. During the first step, the proposed approach tries to classify the sentences into “sentences that contain arguments” and “sentences that don’t contain arguments”. In the second step, it tries to identify the exact fragments that contain the premises from the sentences that contain arguments, by utilizing conditional random fields. The results exceed significantly the base line approach, and according to literature, are quite promising.

Argument Mining on Twitter: Arguments, Facts and Sources

“…Bosc et al (2016a,b) address a binary classification task (argument-tweet vs. non argument), as first step of their pipeline. Goudas et al (2015) experiments machine learning techniques over a dataset in Greek extracted from social media. They first detect argumentative sentences, and second identify premises and claims.…”

Unsupervised Detection of Argumentative Units though Topic Modeling Techniques

“…As reported also by Lippi and Torroni (2015a), the vast majority of existing approaches employ "classic, off-the-self" classifiers, while most of the effort is devoted to highly engineered features. A plethora of learning algorithms have been applied on the task, including Naive Bayes (Moens et al, 2007;Park and Cardie, 2014), Support Vector Machines (SVM) (Mochales and Moens, 2011;Rooney et al, 2012;Park and Cardie, 2014;Stab and Gurevych, 2014b;Lippi and Torroni, 2015b), Maximum Entropy (Mochales and Moens, 2011), Logistic Regression (Goudas et al, 2014(Goudas et al, , 2015Levy et al, 2014), Decision Trees and Random Forests (Goudas et al, 2014(Goudas et al, , 2015Stab and Gurevych, 2014b).…”

“…supports, attacks) among these components in texts. Primarily aiming to extract arguments from texts in order to provide structured data for computational models of argument and reasoning engines (Lippi and Torroni, 2015a), argument mining has additionally the potential to support applications in various research fields, such as opinion mining (Goudas et al, 2015), stance detection (Hasan and Ng, 2014), policy modelling (Florou et al, 2013;Goudas et al, 2014), legal information systems (Palau and Moens, 2009), etc. Argument mining is usually addressed as a pipeline of several sub-tasks. Typically the first sub-task is the separation between argumentative and non-argumentative text units, which can be performed at various granularity levels, from clauses to several sentences, usually depending on corpora characteristics.…”

Proceedings of the 4th Workshop on Argument Mining

“…As reported also by Lippi and Torroni (2015a), the vast majority of existing approaches employ "classic, off-the-self" classifiers, while most of the effort is devoted to highly engineered features. A plethora of learning algorithms have been applied on the task, including Naive Bayes , Support Vector Machines (SVM) Lippi and Torroni, 2015b), Maximum Entropy , Logistic Regression (Goudas et al, 2014(Goudas et al, , 2015, Decision Trees and Random Forests (Goudas et al, 2014(Goudas et al, , 2015.…”

“…supports, attacks) among these components in texts. Primarily aiming to extract arguments from texts in order to provide structured data for computational models of argument and reasoning engines (Lippi and Torroni, 2015a), argument mining has additionally the potential to support applications in various research fields, such as opinion mining (Goudas et al, 2015), stance detection (Hasan and Ng, 2014), policy modelling (Florou et al, 2013;Goudas et al, 2014), legal information systems , etc.…”