Articles, essays & talks

• Elkins, K.; Chun, J. (2019). “Can Sentiment Analysis Reveal Structure in a Plotless Novel?” arXiv:1910.01441. Introduces middle reading and tests whether sentiment methods survive nonlinear narrative.
• Elkins, K.; Chun, J. (2020). “Can GPT-3 Pass a Writer's Turing Test?” Journal of Cultural Analytics 5(2). doi:10.22148/001c.17212. The first writer's Turing test of a large language model.
• Chun, J. (2021). “SentimentArcs: A Novel Method for Self-Supervised Sentiment Analysis of Time Series Shows SOTA Transformers Can Struggle Finding Narrative Arcs.” arXiv:2110.09454. The ensemble pipeline, and dynamic time warping for arcs of unequal length. Publication page →
• Chun, J.; Elkins, K. (2022). “What the Rise of AI Means for Narrative Studies: A Response to ‘Why Computers Will Never Read (or Write) Literature’ by Angus Fletcher.” Narrative 30(1), 104–113. doi:10.1353/nar.2022.0005
• Chun, J.; Elkins, K. (2023). “eXplainable AI with GPT4 for story analysis and generation: A novel framework for diachronic sentiment analysis.” International Journal of Digital Humanities 5(2-3), 507–532. doi:10.1007/s42803-023-00069-8. Sentence-level story trajectories and comparability across unequal lengths. Publication page →
• Chun, J.; Elkins, K. (2023). “The Crisis of Artificial Intelligence: A New Digital Humanities Curriculum for Human-Centred AI.” International Journal of Humanities and Arts Computing 17(2), 147–167. doi:10.3366/ijhac.2023.0310
• Chun, J. (2024). “MultiSentimentArcs: a novel method to measure coherence in multimodal sentiment analysis for long-form narratives in film.” Frontiers in Computer Science 6:1444549. doi:10.3389/fcomp.2024.1444549. Cross-modal coherence between a film's dialogue and image arcs. Publication page →
• Chun, J.; Schroeder de Witt, C.; Elkins, K. (2024). “Comparative Global AI Regulation: Policy Perspectives from the EU, China, and the US.” arXiv:2410.21279. The three-regime map of AI governance.
• Eiras, F.; et al. incl. Chun, J.; Elkins, K. (2024). “Position: Near to Mid-term Risks and Opportunities of Open-Source Generative AI.” ICML (oral). PMLR v235

The technical lineage behind the narrative work is set out on Narrative trajectories & dynamic time warping. Reception is traced on Reception; the full list is on Research and Google Scholar.