eXplainable AI with GPT4 for story analysis and generation: A novel framework for diachronic sentiment analysis

Chun, Jon; Elkins, Katherine

doi:10.1007/s42803-023-00069-8

Cited by 5 publications

(3 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, it comes to life during the advent of large language models (LLM) such as GPT, Llama, Bard, Alpaca, Gemini, and others, which fundamentally change the game on multiple technological and conceptual levels and, at least on paper, promise to consolidate quantitative and qualitative research once and for all. Some of the contributions to the issue, for instance Chun and Elkins (Chun & Elkins, 2023), already reflect this recent and rapid development. We suspect that we will see, at the very least, a more widespread adoption of AI in DH (for instance via LangChain and similar AI stacks and approaches), meaning that the core issues raised by this special issue will only become more relevant in the future.…”

mentioning

confidence: 97%

“…Tobias Blanke, Tommaso Venturini, and Kari De Pryck demonstrate how political concepts like "leadership", which are difficult to operationalize, can be better approximated through XAI techniques (Blanke et al, 2023). Jon Chun and Katherine Elkins propose an advanced XAI approach and workflow for LLM-based research (GPT-4) using diachronic text sentiment analysis and narrative generation (Chun & Elkins, 2023). Hassan El-Hajj, Oliver Eberle, Anika Merklein et al contribute an equally advanced visual XAI approach for historical research on visual primary sources in the history of science (El-Hajj et al, 2023).…”

mentioning

confidence: 99%

“…This special issue, Reproducibility and Explainability in Digital Humanities, was published in two versions: a print version (International Journal of Digital Humanities, 2023a;Burrows, 2023;El-Hajj et al, 2023;Justin & Menon, 2023;Middle, 2023;Schöch, 2023;Siddiqui, 2023;Dobson, 2023;Pandiani et al, 2023;Rudman, 2023;Chun & Elkins, 2023), and an extended online special collection (International Journal of Digital Humanities, 2023b) that features all articles of the print version (a number of them as gold open access publications) plus five additional articles (Joyeux-Prunel, 2023;Huskey, 2023;Blanke et al, 2023;Cooke & Litvack-Katzman, 2023;Hankins, 2023).…”

mentioning

confidence: 99%

See 2 more Smart Citations

Reproducibility and explainability in digital humanities

Ries,

van Dalen-Oskam,

Offert

2024

Int J Digit Humanities

View full text Add to dashboard Cite

This special issue of the International Journal of Digital Humanities (IJDH) focuses on reproducibility and explainability in the Digital Humanities (DH) context, and examines developments and disciplinary efforts to implement, integrate, and recognize reproducibility and explainability as DH research areas and practices (International Journal of Digital Humanities, 2023a, b).The wide disciplinary range of the contributions to this issue points to the relevance of these two deeply interconnected topics for the development of DH as a multidisplinary endeavor that includes significant methodological reflection. The issue features articles conceived from the perspective of Computational Linguistics and Literary Studies, Art History, the History of Science, Sociology, Political Science, and Information Science. At the same time, the articles' data, corpora, and research methods represent the full spectrum of DH research. Data range from corpora of literary novels, historical newspapers, research articles, political processes, and databases of literary awards, to visual sources from art history and the history of science and structured data from research and institutional documentation. Methods include digital editing and publishing, research code and data management, digital archival work, topic modeling, sentiment and network analysis, linked data, knowledge graphs, species models, as well as techniques from explainable artificial intelligence, computer vision, and visual analytics.This special issue was first conceived in the wake of the controversy around Nan Z. Da's article, "The Computational Case against Computational Literary Studies" in a 2019 issue of Critical Inquiry (Da, 2019a, b). While many contributions to the B Thorsten Ries

show abstract

mentioning

confidence: 97%

mentioning

confidence: 99%