sexism-detection

Custom classifiers to detect sexist language.

Code for EXIST 2025 Task 1.1, 1.2 and 1.3

Explainable Machine Learning in Linguistics and Applied NLP: Two Case Studies of Norwegian Dialectometry and Sexism Detection in French Tweets

Analyze user comments through Natural Language Processing (NLP) techniques and Analyze sexism dataset

Ghast farming addon for Meteor Client

Human Language Technologies (HLT) project. Computer Science Master Degree, University of Pisa. A.Y 2023/2024

Human-centered multimodal sexism detection for EXIST 2026 (CLEF) Task 2: a five-stream FiLM-conditioned cross-attention model that fuses meme text, image, annotator demographics, and biometric signals. Team VANGUARD.

Ordantis @ EXIST 2026 Task 2 — GEMF: Gemini-enriched multimodal fusion for sexism characterization in memes (CLEF 2026).

Natural Language Processing for Sexism Detection

Submission for SemEval 2023 Task 10 EDOS

Proyecto en pareja realizado en Adalab bajo metodologías Agile/Scrum. Exploración de datos (EDA) y visualización en Power BI para analizar la representación y sexualización de personajes femeninos en videojuegos, así como la baja presencia de mujeres en la industria.

A transparent pipeline for identifying sexism in social media, combining explainability with model prediction (Applied Sciences, 2024)

The project focuses on identifying signs of sexism in texts through three tasks: identifying sexism, categorizing sexism, and sub-categorizing sexism. The best model used for completing these tasks is RoBERTa pre-trained on hate speech with the addition of data augmentation and learning rate scheduler techniques.

Sexism detection in social media posts using NLP

Benchmark tool aimed at evaluating biases of large language models

Generated a dataset, built a hybrid model, and deployed a browser extension for K-Pop Sexism Detection

Transformer-based sexism detection in Spanish tweets

NLP course projects on online sexism detection, comparing BiLSTM and transformer models on multilingual tweets and exploring explainable classification using LLM prompting on the SemEval EDOS dataset.

Assignments in the realm of Natural Language Processing for Sexism Detection, developed as part of the NLP course at the University of Bologna.

NLP deep evaluation of sexist tweets w/ both LSTMs and Transformer-based LLMs fine-tuning.