Data storytelling combines communication and visualization techniques with storytelling principles to convey insights meaningfully and engagingly. This paper introduces the AI-DIKW framework, an extension of the Story Data–Information–Knowledge–Wisdom (S-DIKW) hierarchy, designed to support the co-creation of data-driven stories by combining human expertise with Generative AI. The AI-DIKW framework extends the S-DIKW model through the application of the journalistic 5-Ws, which guide Generative AI to provide consistent and contextually relevant outputs. This study describes how Generative AI can contribute to the iterative construction of a story's key components while ensuring alignment with ethical principles. Applying Generative AI at the AI-Data stage involves extracting insights from the data. Applying Generative AI at the AI-Information stage means enriching the insight with relevant context, while at the AI-Knowledge stage, Generative AI helps the data storyteller to enrich the story with meaningful next steps, anchored to a selected ethical framework. Finally, at the AI-Wisdom stage, Generative AI helps the data storyteller to tailor the story to specific audiences. At each stage of the AI-DIKW framework, Generative AI acts as a co-designer that helps the data storyteller to frame and edit the story. The article also describes a case study that applies the concepts described practically.

Using generative AI to co‐design data‐driven stories

Angelica Lo Duca
2025

Abstract

Data storytelling combines communication and visualization techniques with storytelling principles to convey insights meaningfully and engagingly. This paper introduces the AI-DIKW framework, an extension of the Story Data–Information–Knowledge–Wisdom (S-DIKW) hierarchy, designed to support the co-creation of data-driven stories by combining human expertise with Generative AI. The AI-DIKW framework extends the S-DIKW model through the application of the journalistic 5-Ws, which guide Generative AI to provide consistent and contextually relevant outputs. This study describes how Generative AI can contribute to the iterative construction of a story's key components while ensuring alignment with ethical principles. Applying Generative AI at the AI-Data stage involves extracting insights from the data. Applying Generative AI at the AI-Information stage means enriching the insight with relevant context, while at the AI-Knowledge stage, Generative AI helps the data storyteller to enrich the story with meaningful next steps, anchored to a selected ethical framework. Finally, at the AI-Wisdom stage, Generative AI helps the data storyteller to tailor the story to specific audiences. At each stage of the AI-DIKW framework, Generative AI acts as a co-designer that helps the data storyteller to frame and edit the story. The article also describes a case study that applies the concepts described practically.
2025
Istituto di informatica e telematica - IIT
data storytelling
generative artificial intelligence
File in questo prodotto:
File Dimensione Formato  
LoDuca_JASIST2025.pdf

accesso aperto

Licenza: Creative commons
Dimensione 2.13 MB
Formato Adobe PDF
2.13 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.14243/597643
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? ND
social impact