Team Macaroni at SemEval-2026 Task 10: PsyCoMark: Psycholinguistic Conspiracy Marker Extraction and Detection
Year: 2026
Type: conference-paper
Abstract: This paper describes our submission to SemEval-2026 Task 10: PsyCoMark, which addresses span-level conspiracy marker extraction and document-level conspiracy detection.For conspiracy marker extraction (subtask 1), we fine-tune several pretrained transformer encoders and analyse their behaviour under different training configurations.For conspiracy detection (subtask 2), we develop a hybrid system that combines ModernBERT-large with surfacelevel linguistic features.Our results show that straightforward finetuning of strong pretrained models is more effective than more complex pipelines and that additional handcrafted features do not yield consistent improvements.On the official test set, we rank 18th in conspiracy marker extraction (overlap-based macro F1 = 0.16) and 20th in conspiracy detection (macro F1 = 0.76).
Authors: Rofaida Rabehi, Nicolai Plenk, Miriam Han
Institution: University of Tübingen
Language: English
Subfield: Sociology and Political Science
Field: Social Sciences
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W7166829033