Knowledge graphs: exploring the potential of language generation models
DOI:
https://doi.org/10.5007/1984-6924.2023.95037Keywords:
Artificial intelligence, Natural Language Processing, Data-Driven JournalismAbstract
An exploratory study is presented on the potential of using language generation models as auxiliary tools in the work of data-driven journalism and automated narratives, through the construction of knowledge graphs, to facilitate the visualization of relationships between detected entities in textual corpus, as well as the possibility of using such models in a more assertive way, based on specific knowledge bases, according to the users' needs. The methodology used was the development of proof of concept, using OPENAI's GPT model, as well as its API (Application Programming Interface). The experiments demonstrated potential for use and the ability to be expanded to operate in larger-scale contexts.
References
BERTOCCHI, D. Dos dados aos formatos: a construção de narrativas no jornalismo digital. São Paulo: Summus, 2016.
BELL, E. J.; OWEN, T.; BROWN, P. D.; HAUKA, C. A Imprensa Nas Plataformas: Como O Vale Silício Reestruturouo Jornalismo. Columbia University Academic Commons, 2017.
BRENEN, J. An industry-led debate: How UK media cover artificial intelligence. Reuters Institute for the Study of Journalism, 2018.
BROUSSARD, M.; DIAKOPOULOS, N. Artificial intelligence and journalism. Journalism & Mass Communication Quarterly, v. 96, n. 3, p. 745-759, 2019.
CONCEIÇÃO, V. A. dos S.; CHAGAS, A. M. O pesquisador e a divulgação científica em contexto de cibercultura e inteligência artificial. Acta Scientiarum. Education, v. 42, e46232, 2020.
DOS SANTOS, M. C.. Data-Driven Journalistic Operation: Reshaping the Idea of News Values with Algorithms, Artificial Intelligence and Increased Personalization. Brazilian journalism research, v. 16, n. 3, p. 458-475, 2020.
GALILY, Y. Artificial intelligence and sports journalism: Is it a sweeping change? Technology in Society, v. 54, p. 28-34, 2018.
GUZMAN, A. L.; LEWIS, S. C.; SCHMIDT, T. R. Automation, journalism, and human–machine communication: Rethinking roles and relationships of humans and machines in news. Digital Journalism, v. 7, n. 6, p. 797-813, 2019.
HANSEN, M.; ROCA-SALES, M.; KEEGAN, J. M.; KING, G. Artificial intelligence: Practice and implications for journalism. Columbia Journalism School, 2017.
KAUFMAN, D. O papel dos algoritmos de inteligência artificial nas redes sociais. Revista Famecos, v. 27, n. 1, p. 1-16, 2020.
KAUFMAN, D. A inteligência artificial irá suplantar a inteligência humana? São Paulo: Alta Books, 2019.
LATAR, N. L. Robot journalism: Can human journalism survive? Social DNA, 2018.
LEWIS, S. C.; GUZMAN, A. L.; SCHMIDT, T. R. Artificial intelligence and communication: A Human–Machine Communication research agenda. New Media & Society, v. 22, n. 8, p. 1368-1387, 2020.
LINDEN, C. G. Algoritmos para Jornalismo: o futuro da produção de notícias. Líbero, v. 21, n. 42, p. 153-163, 2018.
PELLANDA, E. C.; PASE, A. F.; NUNES, A. C. B. Mobilidade e jornalismo digital contemporâneo: fases do jornalismo móvel ubíquo e suas características. Jornalismo Móvel em perspectiva, 2017.
PRADO, M. Fake News e Inteligência Artificial: O poder dos algoritmos na guerra da desinformação. São Paulo: Novatec Editora, 2022.
SANTOS, M. C. Narrativas Automatizadas e a Geração de Textos Jornalísticos: A estrutura de organização do lead traduzida em código. Brazilian Journalism Research, v. 12, n. 2, p. 258-276, 2016.
SANTOS, M. C. Inteligência híbrida e análise de sentimentos: integrando curadoria humana e coleta de dados automatizada para avaliar a comunicação de governo. Revista Conexão - Comunicação e Cultura; v. 17, n. 33, 2018.
Downloads
Published
Issue
Section
License
Authors retain copyright and publication rights over their works without restrictions.
Upon submitting their work, authors grant Estudos em Jornalismo e Mídia the exclusive right of first publication, with the work simultaneously licensed under the Creative Commons Attribution (CC BY) 4.0 International License. This license allows third parties to remix, adapt, and build upon the published work, provided that proper credit is given to the authorship and to the original publication in this journal.
Authors are also permitted to enter into additional contracts, separately, for non-exclusive distribution of the published version of the work in this journal (for example: depositing it in an institutional repository, making it available on a personal website, publishing translations, or including it as a book chapter), provided that authorship and the initial publication in Estudos em Jornalismo e Mídia are acknowledged.
