Abstract
We present a hybrid approach to the automated measurement of vagueness and subjectivity in texts. We first introduce the expert system VAGO, we illustrate it on a small benchmark of fact vs. opinion sentences, and then test it on the larger French press corpus FreSaDa to confirm the higher prevalence of subjective markers in satirical vs. regular texts. We then build a neural clone of VAGO, based on a BERT-like architecture, trained on the symbolic VAGO scores obtained on FreSaDa. Using explainability tools (LIME), we show the interest of this neural version for the enrichment of the lexicons of the symbolic version, and for the production of versions in other languages.
Full Text
Topics from this Paper
Regular Texts
Opinion Sentences
French Corpus
Versions In Languages
Press Corpus
+ Show 5 more
Create a personalized feed of these topics
Get StartedSimilar Papers
MedieKultur: Journal of media and communication research
Nov 2, 2017
Palgrave Communications
May 1, 2020
Polibits
Jun 30, 2011
Jan 3, 1989
International Journal of Intelligent Systems in Accounting, Finance & Management
Jan 1, 2006
Journal of Clinical Medicine
Jul 29, 2021
Intelligent Systems in Accounting, Finance and Management
Jan 1, 2006
Journal of Clinical Images and Medical Case Reports
Oct 5, 2021
Marketing Intelligence & Planning
Sep 1, 2002
Expert Systems with Applications
Sep 1, 2017
Engineering with Computers
Jun 1, 1987
Computers in Industry
Jun 1, 1991
2013 Seventh International Conference on Complex, Intelligent, and Software Intensive Systems
Jul 3, 2013
Sep 10, 1990