BibTeX

@inProceedings{francis-2026-grieve-366791,
	title        = {Grieve-JA: A Psycholinguistic Dictionary for Grievance-Fuelled Language in Japanese},
	abstract     = {Since the early 2010s, internet nationalists have been active on Japanese forums, blogs, and social networking services, spreading hate speech and conspiracy. At the same, the involuntary celibate community has gained international notoriety due to acts of mass violence committed by self-identified members. Despite several instances of misogyny motivated violence in Japan, there is little known about Japanese involuntary celibate culture and identity. This paper introduces Grieve-JA, a psycholinguistic dictionary for the analysis of violence, threat, and grievance in Japanese text. The paper outlines the process of developing the dictionary and evaluating it across different corpora representing both neutral and grievance-filled language. As a final measure, the dictionary is used to compare comments from two forums on the Japanese anonymous message board 5channel with comments from Bluesky. Results indicate that Grieve-JA is a useful tool for analyzing extreme language in Japanese as a complement to other psycholinguistic measures.},
	booktitle    = {Proceedings of the Second International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security (NLPAICS)},
	author       = {Francis, Emilie},
	year         = {2026},
	publisher    = {Department of Languages and Information Systems, University of Alicante},
	address      = {Alicante, Spain},
	pages        = {11--24},
}

@inProceedings{francis-etal-2026-chatgpt-364799,
	title        = {ChatGPT, why can’t anyone afford a house? On the Effects of LLM pre-annotation on Annotator Subjectivity},
	abstract     = {Large language models (LLMs) have often been proposed as substitutes for human annotators in a variety of tasks. At the same time, there has been increased focus on the role that human subjectivity and perspective plays in data annotation. To avoid eliminating the human role in annotation entirely, the use of LLMs for pre-annotation has been suggested as an alternative approach. In this paper, we explore to which degree this approach affects subjectivity of social media annotation in English. We focus on comments regarding the current status of the housing market and label them for concern level, factors affecting housing affordability, and aspects that authors claim either exacerbate or improve the situation. To investigate this, we design an experiment involving two rounds of annotation: the first, a dataset annotated by humans only; and the second, a dataset with LLM pre-annotations curated by the same human annotators. We observe that the second setting leads to much higher agreement, as well as significant changes in label distribution and co-occurrence. Similar shifts do not appear in the LLM labels. Our findings show that use of LLMs in the annotation process leads to convergence in annotations and, thus, to an erosion of human subjectivity.},
	booktitle    = {Proceedings of the the fifth edition of NLPerspectives 11-16 May 2026, Palma, Mallorca, Spain},
	author       = {Francis, Emilie and Leuzinger, Celine and Muñoz Sánchez, Ricardo and Gauthier, Lee D.},
	year         = {2026},
	publisher    = {ELRA Language Resources Association (ELRA)},
	pages        = {98--111},
}