Hate Speech Detection
Hate speech & offensive Language detection a spanish case study.
Overview
Spanish Aggressive Language identification using Deep learning
In my research project, I focused on detecting offensive language in user-generated content on social media platforms. With growing concerns over abusive behavior, technology companies are investing in computational methods to identify aggression and hate speech. Building fron the foundational of hate-speech,my project explores how Deep Learning techniques in Natural Language Processing (NLP) can effectively identify offensive language, particularly in Spanish. The study investigates the characteristics of offensive messages, including disparaging language, derogatory adjectives, and profanity.
The results of this research were published in top AI conferences, and I presented my findings through a papers and posters, contributing to the ongoing dialogue in the field and helping to enhance automated detection methods.
paper & presentations
- Bracis 2021 Paper published you can access on my publication or online editorial
paper_here - Bracis 2021 video presentation| see the video on underline
video_here - Bracis 2021 Poster presentation | see ppt version available
Teaser_Slides - Khipu 2019 Poster presentation | see pdf version available poster_presentation
- Nerurips 2019 Poster presentation | see pdf version available poster_presentation
As part of the conference there is a networking opportunity where scientist and people working in diferent topic talk about their experience i had the opportunity to meet awesome people.
For more details on specific publications and code implementations, please check my publications page.