Sara Gemelli


2024

pdf bib
GroningenAnnotatesGaza at the FIGNEWS 2024 Shared Task: Analyzing Bias in Conflict Narratives
Khalid Khatib | Sara Gemelli | Saskia Heisterborg | Pritha Majumdar | Gosse Minnema | Arianna Muti | Noa Solissa
Proceedings of The Second Arabic Natural Language Processing Conference

In this paper we report the development of our annotation methodology for the shared task FIGNEWS 2024. The objective of the shared task is to look into the layers of bias in how the war on Gaza is represented in media narrative. Our methodology follows the prescriptive paradigm, in which guidelines are detailed and refined through an iterative process in which edge cases are discussed and converged. Our IAA score (Krippendorff’s đ›Œ) is 0.420, highlighting the challenging and subjective nature of the task. Our results show that 52% of posts were unbiased, 42% biased against Palestine, 5% biased against Israel, and 3% biased against both. 16% were unclear or not applicable.

pdf bib
Manosphrames: exploring an Italian incel community through the lens of NLP and Frame Semantics
Sara Gemelli | Gosse Minnema
Proceedings of the First Workshop on Reference, Framing, and Perspective @ LREC-COLING 2024

We introduce a large corpus of comments extracted from an Italian online incel (‘involuntary incelibate’) forum, a community of men who build a collective identity and anti-feminist ideology centered around their inability to find a sexual or romantic partner and who frequently use explicitly misogynistic language. Our corpus consists of 2.4K comments that have been manually collected, analyzed and annotated with topic labels, and a further 32K threads (300K comments) that have been automatically scraped and automatically annotated with FrameNet annotations. We show how large-scale frame semantic analysis can shed a light on what is discussed in the community, and introduce incel topic classification as a new NLP task and benchmark.

2022

pdf bib
Dead or Murdered? Predicting Responsibility Perception in Femicide News Reports
Gosse Minnema | Sara Gemelli | Chiara Zanchi | Tommaso Caselli | Malvina Nissim
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Different linguistic expressions can conceptualize the same event from different viewpoints by emphasizing certain participants over others. Here, we investigate a case where this has social consequences: how do linguistic expressions of gender-based violence (GBV) influence who we perceive as responsible? We build on previous psycholinguistic research in this area and conduct a large-scale perception survey of GBV descriptions automatically extracted from a corpus of Italian newspapers. We then train regression models that predict the salience of GBV participants with respect to different dimensions of perceived responsibility. Our best model (fine-tuned BERT) shows solid overall performance, with large differences between dimensions and participants: salient _focus_ is more predictable than salient _blame_, and perpetrators’ salience is more predictable than victims’ salience. Experiments with ridge regression models using different representations show that features based on linguistic theory similarly to word-based features. Overall, we show that different linguistic choices do trigger different perceptions of responsibility, and that such perceptions can be modelled automatically. This work can be a core instrument to raise awareness of the consequences of different perspectivizations in the general public and in news producers alike.

pdf bib
SocioFillmore: A Tool for Discovering Perspectives
Gosse Minnema | Sara Gemelli | Chiara Zanchi | Tommaso Caselli | Malvina Nissim
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations

SOCIOFILLMORE is a multilingual tool which helps to bring to the fore the focus or the perspective that a text expresses in depicting an event. Our tool, whose rationale we also support through a large collection of human judgements, is theoretically grounded on frame semantics and cognitive linguistics, and implemented using the LOME frame semantic parser. We describe SOCIOFILLMORE’s development and functionalities, show how non-NLP researchers can easily interact with the tool, and present some example case studies which are already incorporated in the system, together with the kind of analysis that can be visualised.