Prior Polarity Lexical Resources for the Italian Language

TL;DR

This paper introduces SABRINA, a comprehensive manually annotated lexical resource for Italian sentiment analysis, including a large dictionary and polarity modifiers, advancing opinion mining in Italian NLP.

Contribution

It presents the first manually annotated prior polarity lexical resource for Italian, covering over 277,000 words and 200 modifiers for sentiment analysis.

Findings

The resource enables more accurate sentiment analysis in Italian.

It supports compound sentiment induction using polarity modifiers.

First of its kind for Italian natural language applications.

Abstract

In this paper we present SABRINA (Sentiment Analysis: a Broad Resource for Italian Natural language Applications) a manually annotated prior polarity lexical resource for Italian natural language applications in the field of opinion mining and sentiment induction. The resource consists in two different sets, an Italian dictionary of more than 277.000 words tagged with their prior polarity value, and a set of polarity modifiers, containing more than 200 words, which can be used in combination with non neutral terms of the dictionary in order to induce the sentiment of Italian compound terms. To the best of our knowledge this is the first prior polarity manually annotated resource which has been developed for the Italian natural language.