Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

A corpus analysis of online news comments using the Appraisal framework

Cavasso, Luca and Taboada, Maite 2021. A corpus analysis of online news comments using the Appraisal framework. Journal of Corpora and Discourse Studies 4 , pp. 1-38. 10.18573/jcads.61

PDF - Published Version
Available under License Creative Commons Attribution.

Download (1MB) | Preview


We present detailed analyses of the distribution of Appraisal categories (Martin and White, 2005) in a corpus of online news comments. The corpus consists of just over one thousand comments posted in response to a variety of opinion pieces on the website of the Canadian newspaper The Globe and Mail. We annotated all the comments with labels corresponding to different categories of the Appraisal framework. Analyses of the annotations show that comments are overwhelmingly negative, and that they favour two of the subtypes of Attitude (Judgment and Appreciation) over the third, Affect. The paper contributes a methodology for annotating Appraisal, and results that show the interaction of Appraisal with negation, the constructive (or not) nature of comments, and the level of toxicity found in them. The results show that highly opinionated language is expressed as an objective opinion (Judgement and Appreciation) rather than an emotional reaction (Affect). This finding, together with the interplay of evaluative language with constructiveness and toxicity in the comments, can be applied to the automatic moderation of comments.

Item Type: Article
Date Type: Publication
Status: Published
Schools: English, Communication and Philosophy
Subjects: H Social Sciences > H Social Sciences (General)
P Language and Literature > P Philology. Linguistics
Publisher: Cardiff University Press
ISSN: 2515-0251
Date of First Compliant Deposit: 7 May 2021
Date of Acceptance: 24 December 2020
Last Modified: 07 May 2021 10:25

Actions (repository staff only)

Edit Item Edit Item


Downloads per month over past year

View more statistics