The Sentiment is in the Details: A Language-agnostic Approach to Dictionary Expansion and Sentence-level Sentiment Analysis in News Media

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3A7FQX4GL6" target="_blank" >RIV/00216208:11320/22:7FQX4GL6 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.aup-online.com/content/journals/10.5117/CCR2022.2.003.VRIE" target="_blank" >https://www.aup-online.com/content/journals/10.5117/CCR2022.2.003.VRIE</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.5117/CCR2022.2.003.VRIE" target="_blank" >10.5117/CCR2022.2.003.VRIE</a>

Jazyk výsledku

angličtina

Název v původním jazyce

The Sentiment is in the Details: A Language-agnostic Approach to Dictionary Expansion and Sentence-level Sentiment Analysis in News Media

Popis výsledku v původním jazyce

Abstract Determining the sentiment in the individual sentences of a newspaper article in an automated fashion is a major challenge. Manually created sentiment dictionaries often fail to meet the required standards. And while computer-generated dictionaries show promise, they are often limited by the availability of suitable linguistic resources. I propose and test a novel, language-agnostic and resource-efficient way of constructing sentiment dictionaries, based on word embedding models. The dictionaries are constructed and evaluated based on four corpora containing two decades of Danish, Dutch (Flanders and the Netherlands), English, and Norwegian newspaper articles, which are cleaned and parsed using Natural Language Processing. Concurrent validity is evaluated using a dataset of human-coded newspaper sentences, and compared to the performance of the Polyglot sentiment dictionaries. Predictive validity is tested through two long-standing hypotheses on the negativity bias in political news. Results show that both the concurrent validity and predictive validity is good. The dictionaries outperform their Polyglot counterparts, and are able to correctly detect a negativity bias, which is stronger for tabloids. The method is resource-efficient in terms of manual labor when compared to manually constructed dictionaries, and requires a limited amount of computational power.

Název v anglickém jazyce

The Sentiment is in the Details: A Language-agnostic Approach to Dictionary Expansion and Sentence-level Sentiment Analysis in News Media

Popis výsledku anglicky

Abstract Determining the sentiment in the individual sentences of a newspaper article in an automated fashion is a major challenge. Manually created sentiment dictionaries often fail to meet the required standards. And while computer-generated dictionaries show promise, they are often limited by the availability of suitable linguistic resources. I propose and test a novel, language-agnostic and resource-efficient way of constructing sentiment dictionaries, based on word embedding models. The dictionaries are constructed and evaluated based on four corpora containing two decades of Danish, Dutch (Flanders and the Netherlands), English, and Norwegian newspaper articles, which are cleaned and parsed using Natural Language Processing. Concurrent validity is evaluated using a dataset of human-coded newspaper sentences, and compared to the performance of the Polyglot sentiment dictionaries. Predictive validity is tested through two long-standing hypotheses on the negativity bias in political news. Results show that both the concurrent validity and predictive validity is good. The dictionaries outperform their Polyglot counterparts, and are able to correctly detect a negativity bias, which is stronger for tabloids. The method is resource-efficient in terms of manual labor when compared to manually constructed dictionaries, and requires a limited amount of computational power.

Druh

J_ost - Ostatní články v recenzovaných periodicích

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

Computational Communication Research [online]

ISSN

2665-9085

e-ISSN

1573-7462

Svazek periodika

4

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

39

Strana od-do

424-462

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—