Evaluating the Effectiveness of GPT Large Language Model for News Classification in the IPTC News Ontology
News classification plays a vital role in newsrooms, as it involves the time-consuming task of categorizing news articles and requires domain knowledge. Effective news classification is essential for categorizing and organizing a constant flow of information, serving as the foundation for subsequent...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10367969/ |
_version_ | 1797373114438385664 |
---|---|
author | Bahareh Fatemi Fazle Rabbi Andreas L. Opdahl |
author_facet | Bahareh Fatemi Fazle Rabbi Andreas L. Opdahl |
author_sort | Bahareh Fatemi |
collection | DOAJ |
description | News classification plays a vital role in newsrooms, as it involves the time-consuming task of categorizing news articles and requires domain knowledge. Effective news classification is essential for categorizing and organizing a constant flow of information, serving as the foundation for subsequent tasks, such as news aggregation, monitoring, filtering, and organization. The automation of this process can significantly benefit newsrooms by saving time and resources. In this study, we explore the potential of the GPT large language model in a zero-shot setting for multi-class classification of news articles within the widely accepted International Press Telecommunications Council (IPTC) news ontology. The IPTC news ontology provides a structured framework for categorizing news, facilitating the efficient organization and retrieval of news content. By investigating the effectiveness of the GPT language model in this classification task, we aimed to understand its capabilities and potential applications in the news domain. This study was conducted as part of our ongoing research in the field of automated journalism. |
first_indexed | 2024-03-08T18:45:42Z |
format | Article |
id | doaj.art-1a4c18ee148a49f9971f8d309aeeeff6 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-03-08T18:45:42Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-1a4c18ee148a49f9971f8d309aeeeff62023-12-29T00:03:56ZengIEEEIEEE Access2169-35362023-01-011114538614539410.1109/ACCESS.2023.334541410367969Evaluating the Effectiveness of GPT Large Language Model for News Classification in the IPTC News OntologyBahareh Fatemi0https://orcid.org/0000-0002-8944-5051Fazle Rabbi1https://orcid.org/0000-0001-5626-0598Andreas L. Opdahl2https://orcid.org/0000-0002-3141-1385Department of Information Science and Media Studies, University of Bergen, Bergen, NorwayDepartment of Information Science and Media Studies, University of Bergen, Bergen, NorwayDepartment of Information Science and Media Studies, University of Bergen, Bergen, NorwayNews classification plays a vital role in newsrooms, as it involves the time-consuming task of categorizing news articles and requires domain knowledge. Effective news classification is essential for categorizing and organizing a constant flow of information, serving as the foundation for subsequent tasks, such as news aggregation, monitoring, filtering, and organization. The automation of this process can significantly benefit newsrooms by saving time and resources. In this study, we explore the potential of the GPT large language model in a zero-shot setting for multi-class classification of news articles within the widely accepted International Press Telecommunications Council (IPTC) news ontology. The IPTC news ontology provides a structured framework for categorizing news, facilitating the efficient organization and retrieval of news content. By investigating the effectiveness of the GPT language model in this classification task, we aimed to understand its capabilities and potential applications in the news domain. This study was conducted as part of our ongoing research in the field of automated journalism.https://ieeexplore.ieee.org/document/10367969/IPTC media topicsjournalismlarge language modelsnews classification |
spellingShingle | Bahareh Fatemi Fazle Rabbi Andreas L. Opdahl Evaluating the Effectiveness of GPT Large Language Model for News Classification in the IPTC News Ontology IEEE Access IPTC media topics journalism large language models news classification |
title | Evaluating the Effectiveness of GPT Large Language Model for News Classification in the IPTC News Ontology |
title_full | Evaluating the Effectiveness of GPT Large Language Model for News Classification in the IPTC News Ontology |
title_fullStr | Evaluating the Effectiveness of GPT Large Language Model for News Classification in the IPTC News Ontology |
title_full_unstemmed | Evaluating the Effectiveness of GPT Large Language Model for News Classification in the IPTC News Ontology |
title_short | Evaluating the Effectiveness of GPT Large Language Model for News Classification in the IPTC News Ontology |
title_sort | evaluating the effectiveness of gpt large language model for news classification in the iptc news ontology |
topic | IPTC media topics journalism large language models news classification |
url | https://ieeexplore.ieee.org/document/10367969/ |
work_keys_str_mv | AT baharehfatemi evaluatingtheeffectivenessofgptlargelanguagemodelfornewsclassificationintheiptcnewsontology AT fazlerabbi evaluatingtheeffectivenessofgptlargelanguagemodelfornewsclassificationintheiptcnewsontology AT andreaslopdahl evaluatingtheeffectivenessofgptlargelanguagemodelfornewsclassificationintheiptcnewsontology |