Measuring vagueness and subjectivity in texts: from symbolic to neural VAGO

TL;DR

This paper introduces a hybrid method combining symbolic and neural approaches to measure vagueness and subjectivity in texts, demonstrating its effectiveness on French press data and enabling multilingual applications.

Contribution

It presents VAGO, an expert system for textual vagueness and subjectivity detection, and develops a neural clone based on BERT trained on symbolic scores for improved analysis.

Findings

VAGO effectively distinguishes fact from opinion sentences.

The neural clone enhances lexicon enrichment and multilingual capabilities.

Subjective markers are more prevalent in satirical texts.

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.