Ana Kotarcic
Biographic Data
| ID | 5153126 |
|---|---|
| NAME | Ana Kotarcic |
| GIVEN NAMES | Ana |
| FAMILY NAME | Kotarcic |
| SIGNATURE | KOTARCIC A |
| AFFILIATIONS | University of Zurich |
| VERIFIED | No |
| TOTAL WORKS | 2 |
| TOTAL CITATIONS | 0 |
| WORKS AS AUTHOR | 2 |
| WORKS AS EDITOR | 0 |
| FIRST PUBLICATION YEAR | 2025 |
| LATEST PUBLICATION YEAR | 2026 |
| H-INDEX | 0 |
Improving hate speech detection with large language models
Efforts to curb online hate speech depend on our ability to reliably detect it at scale. Previous studies have highlighted the strong zero-shot classification performance of large language models (LLMs), offering a potential tool to efficiently identify harmful content. Yet for complex and ambivalent tasks like hate speech detection, pre-trained LLMs can be insufficient and carry systemic biases. Domain-specific models fine-tuned for the given ta…
The distribution of hate speech and its implications for content moderation
Hate speech is widely seen as a significant obstacle to constructive online discourse, but the most effective strategies to mitigate its effects remain unclear. We claim that understanding its distribution across users is key to developing and evaluating effective content moderation strategies. We address this missing link by first examining the distribution of hate speech in five original datasets that collect user-generated posts across multipl…
No prominent works on this page.
The distribution of hate speech and its implications for content moderation
Hate speech is widely seen as a significant obstacle to constructive online discourse, but the most effective strategies to mitigate its effects remain unclear. We claim that understanding its distribution across users is key to developing and evaluating effective content moderation strategies. We address this missing link by first examining the distribution of hate speech in five original datasets that collect user-generated posts across multipl…
Improving hate speech detection with large language models
Efforts to curb online hate speech depend on our ability to reliably detect it at scale. Previous studies have highlighted the strong zero-shot classification performance of large language models (LLMs), offering a potential tool to efficiently identify harmful content. Yet for complex and ambivalent tasks like hate speech detection, pre-trained LLMs can be insufficient and carry systemic biases. Domain-specific models fine-tuned for the given ta…
Hate Speech and Cyberbullying Detection (2 works) · Spam and Phishing Detection (2 works) · Annotation (1 work) · Constructive (1 work) · Content (measure theory (1 work) · Context (archaeology (1 work) · Crowdsourcing (1 work) · Distribution (mathematics (1 work) · Field (mathematics (1 work) · Language model (1 work)