China 
Africa 
Explore chapters and articles related to this topic
Reliability rating of news-related posts on Facebook using sentiment analysis
Published in Shin-ya Nishizaki, Masayuki Numao, Jaime Caro, Merlin Teodosia Suarez, Theory and Practice of Computation, 2019
M.A. Solis, Q.J. San Juan, L.L. Figueroa
CMC communication and news content have also shown deception cues at the discourse level. Rhetorical Structure Theory (RST) analytic framework achieves a description of discourse that describes instances of rhetoric relations between elements of linguistic. Deceptive and truthful messages have exhibited systematic differences in terms of their coherence and structure has been combined with a Vector Space Model (VSM) that evaluates search message’s position in multi-dimensional RST space accordingly to its distance to truth and deceptive centers (Rubin & Lukoianova, 2014). The prominent use of certain rhetorical relations can indicate deception at this linguistic analysis level.
Natural Language Processing for Writing and Speaking
Published in Duanli Yan, André A. Rupp, Peter W. Foltz, Handbook of Automated Scoring, 2020
Other studies have adapted approaches that were originally designed for the evaluation of discourse coherence in essays and applied them to spoken responses such as using entity grids to model the relationships between entities in adjacent sentences (Wang et al., 2013) and using features based on how the discourse elements in the response are represented in tree based on rhetorical structure theory (Wang, Bruno, Molloy, Evanini, & Zechner, 2017).
Detecting logical argumentation in text via communicative discourse tree
Published in Journal of Experimental & Theoretical Artificial Intelligence, 2018
Boris Galitsky, Dmitry Ilvovsky, Sergey O. Kuznetsov
Annotation of discourse structure which aims at identifying discourse relations that are held between adjacent text units, e.g. sentences, clauses and nominalisations (Webber, Egg, & Kordoni, 2012), is a field that is closely related to the annotation of argumentation structures (Kirschner, Eckle-Kohler, & Gurevych, 2015). Naturally, there is a correspondence between discourse units and argument components, and discourse relations are closely related to argumentative relations. Most previous work in automated discourse analysis is based on corpora annotated with discourse relations, most notably the Penn Discourse Treebank (PDTB) (Prasad et al., 2008) and the Rhetorical Structure Theory Discourse Treebank (Carlson, Marcu, & Okurowski, 2001). However, the data consist of newspaper articles which do not necessarily involve heavy argumentation, and only relations between adjacent text units are identified. It is still an open question how the proposed discourse relations relate to argumentative relations (Biran & Rambow, 2011).
Finding influential users in microblogs: state-of-the-art methods and open research challenges
Published in Behaviour & Information Technology, 2022
Umar Ishfaq, Hikmat Ullah Khan, Shahid Iqbal, Mohammed Alghobiri
On the other hand, the argumentation system utilise Rhetorical Structure Theory (RST) relations in RST Penn Treebank (Carlson, Marcu, and Okurowski 2003) for extracting the list of indicators of relations and co-occurring pairs of content words for each of the indicators of relations. In addition, the study tracks whether the first sentence of a post is a claim or argumentation. Starting a post with a claim or an argument indicates that it is stronger.