Search

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. [ABSTRACT FROM AUTHOR]

This commentary discusses recent developments in ‘knowledge graph’ technology over the course of the Covid-19 pandemic. Recently experiencing a surge in popularity, knowledge graphs are technologies that assist with data integration through structured metadata modeling. Researchers tag and collate vast amounts of diverse data using knowledge graphs, yet problems related to semantic drift and more salient issues related to the political economy of information and communication technologies persist. Researchers should anticipate that the semantics of these Covid-19 knowledge graphs can change over time. Equally important, researchers should also consider all stakeholders involved, including those stakeholders that might be excluded.