Flor Plaza

Hello 👋! I’m a Postdoctoral Research Fellow in Dirk Hovy‘s MilaNLP lab at Bocconi University. My research interests mainly focus on the interplay between language, computation, and society, primarily through the lens of emotions and harmful language —endeavors aligned with the vision of Natural Language Processing for social good. I am passionate about actively using my expertise and the potential of NLP to drive a positive impact on society.
In January 2023 I obtained my Ph.D., awarded with the highest honors (summa cum laude), from the SINAI lab at the University of Jaén (Spain) where I made significant contributions to the detection of hate speech and the identification of emotions, especially in Spanish.
Notably, I have actively contributed to the academic community by co-organizing the EmoEvalEs, MeOffendES and MentalRiskES shared tasks at the IberLEF 2021 and 2023 events. I have also co-organized the 36th, 37th, and 39th editions of the Spanish Society for Natural Language Processing Conference (SEPLN). Currently, I am co-organizing The 8th Workshop on Online Abuse and Harms at NAACL 2024 and the Tutorial on countering hateful and offensive speech online at EMNLP 2024.

News

March 2024 – I’m going to give a talk (w/ Amanda Cercas Curry) about gender stereotypes and ethical issues in LLMs at T3chFest (Madrid).

Feb 2024 – Two new papers at LREC-COLING 2024! Preprints, coming soon!
(1) Emotion Analysis in NLP. Trends, Gaps and Roadmap for Future Directions.
(2) A New Corpus for Early Detection of Mental Disorders in Spanish.

Jan 2024 – PhD committee member. Miguel Anxo Pérez Vila (University of A Coruña).

Dec 2023 – New paper at EMNLP 2023! A Tale of Pronouns. Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation

Nov 2023 - Talk “Más Allá de las Palabras. Un Viaje en la Intersección del Lenguaje, Modelos Computacionales y Sociedad”. Università di Bologna (Bolonia, Italy). November 2023.

Oct 2023 - Talk “Are Instruction-Tuned Language Models Suitable as Annotators? Exploring Model Label Variation for Text Classification” at EPFL (Lausanne, Switzerland).

Oct 2023 - Accepted tutorial at EMNLP 2024. Countering Hateful and Offensive Speech Online-Open Challenges with Leon Derczynski, Marco Guerini, Debora Nozza, Jeffrey Sorensen and Marcos Zampieri

Oct 2023 - I’m going to co-organize the 8th Workshop on Online Abuse and Harms (WOAH) at NAACL 2024

Sep 2023 - I am at the IberLEF Workshop within the SEPLN conference presenting the co-organized MentalRiskES shared task! Overview of MentalRiskES at IberLEF 2023. Early Detection of Mental Disorders Risk in Spanish

Jul 2023 – At ACL 2023 in Toronto, I’m presenting the co-authored WOAH paper

Jun 2023 – New paper on Respectful or Toxic? Using Zero-Shot Learning with Language Models to Detect Hate Speech published at WOAH workshop at ACL 2023.

Education

February 2023 - Present
Postdoctoral Research Fellow
MilaNLP, Bocconi University, Italy
May 2022 - July 2022
Visiting PHD Student
Fondazione Bruno Kessler, Trento, Italy
May 2021 - July 2021
Visiting PHD Student
University of Stuttgart
April 2019 - June 2019
Visiting PHD Student
Fondazione Bruno Kessler, Trento, Italy
2018 - January 2023
PhD in Computer Science
SINAI, University of Jaén, Spain

PhD Thesis

  • Detecting offensive language by combining multiple linguistic phenomena
2016 - 2018
Master in Computer Science
University of Jaén, Spain

Master Thesis

  • Análisis computacional de emociones en las redes sociales (Computational analysis of emotions on social media)
2012 - 2016
Bachelor in Computer Science
University of Jaén, Spain

Bachelor Thesis

  • Análisis de opiniones de pacientes en la Web 2.0 (Analysis of patient opinions on Web 2.0)

Get in Touch

flor.plaza[at]unibocconi.it