Semi-Automatic Approaches for Exploiting Shifter Patterns in Domain-Specific Sentiment Analysis

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3A49KCB4RR" target="_blank" >RIV/00216208:11320/22:49KCB4RR - isvavai.cz</a>

Výsledek na webu

<a href="https://www.mdpi.com/2227-7390/10/18/3232" target="_blank" >https://www.mdpi.com/2227-7390/10/18/3232</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/math10183232" target="_blank" >10.3390/math10183232</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Semi-Automatic Approaches for Exploiting Shifter Patterns in Domain-Specific Sentiment Analysis

Popis výsledku v původním jazyce

This paper describes two different approaches to sentiment analysis. The first is a form of symbolic approach that exploits a sentiment lexicon together with a set of shifter patterns and rules. The sentiment lexicon includes single words (unigrams) and is developed automatically by exploiting labeled examples. The shifter patterns include intensification, attenuation/downtoning and inversion/reversal and are developed manually. The second approach exploits a deep neural network, which uses a pre-trained language model. Both approaches were applied to texts on economics and finance domains from newspapers in European Portuguese. We show that the symbolic approach achieves virtually the same performance as the deep neural network. In addition, the symbolic approach provides understandable explanations, and the acquired knowledge can be communicated to others. We release the shifter patterns to motivate future research in this direction.

Název v anglickém jazyce

Semi-Automatic Approaches for Exploiting Shifter Patterns in Domain-Specific Sentiment Analysis

Popis výsledku anglicky

This paper describes two different approaches to sentiment analysis. The first is a form of symbolic approach that exploits a sentiment lexicon together with a set of shifter patterns and rules. The sentiment lexicon includes single words (unigrams) and is developed automatically by exploiting labeled examples. The shifter patterns include intensification, attenuation/downtoning and inversion/reversal and are developed manually. The second approach exploits a deep neural network, which uses a pre-trained language model. Both approaches were applied to texts on economics and finance domains from newspapers in European Portuguese. We show that the symbolic approach achieves virtually the same performance as the deep neural network. In addition, the symbolic approach provides understandable explanations, and the acquired knowledge can be communicated to others. We release the shifter patterns to motivate future research in this direction.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Mathematics [online]

ISSN

2227-7390

e-ISSN

2227-7390

Svazek periodika

10

Číslo periodika v rámci svazku

18

Stát vydavatele periodika

CH - Švýcarská konfederace

Počet stran výsledku

24

Strana od-do

1-24

Kód UT WoS článku

000857610000001

EID výsledku v databázi Scopus

2-s2.0-85138638378