Research Interests
One tablespoon of uncertainty for large language models, with a pinch of computational social science.
Publications
Target Two Birds With One SToNe: Entity-Level Sentiment and Tone Analysis in Croatian News Headlines
Ana Barić, Laura Majer, David Dukić, Marijana Grbeša-Zenzerović, and Jan Snajder.
In Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023), pages 78–85, Dubrovnik, Croatia. Association for Computational Linguistics.
Sentiment analysis is often used to examine how different actors are portrayed in the media, and analysis of news headlines is of particular interest due to their attention-grabbing role. We address the task of entity-level sentiment analysis from Croatian news headlines. We frame the task as targeted sentiment analysis (TSA), explicitly differentiating between sentiment toward a named entity and the overall tone of the headline. We describe SToNe, a new dataset for this task with sentiment and tone labels. We implement several neural benchmark models, utilizing single- and multi-task training, and show that TSA can benefit from tone information. Finally, we gauge the difficulty of this task by leveraging dataset cartography.
