NLP Researcher | Data Scientist | Statistician
github.com/m-chaves
Google Scholar Profile
CV
Institutional mariana-eugenia.chaves-espinoza@inria.fr
Personal marianach16@gmail.com or mariana.chaves.e@outlook.com
I am a research engineer at CNRS and a member of the WIMMICS team at Inria, where I work on natural language processing (NLP) and argument mining applied to the context of political debates, press articles, and social media. In my 7 years of working experience, I have developed diverse projects involving statistics, data science, machine learning, and artificial intelligence. This includes applications in social media analysis, gender representation in media, explainable AI, supply chain logistics, and money laundering detection.
Key words about me: Natural Language Processing (NLP) Argument Mining Computational Linguistics (Large) Language Models Data Science Fallacious arguments Corpora Creation Explainable AI Statistics Machine Learning
RESEARCH ENGINEER INRIA, CNRS, and I3S laboratory, France | April 2023 - Present
Research in natural language processing (NLP) focused on fallacy detection and classification via argumentation, especially in the context of political debates and social media. Currently analysing press coverage of the war in Ukraine through argument mining techniques.
INTERNSHIP I3S laboratory and INRIA, France | March 2022 - August 2022
Research on prototype-based interpretable neural networks, text classification models, and NLP techniques applied to the understanding of gender representation in visual media.
Read the full work here.
INTERNSHIP Université Côte d’Azur and INRIA, France | April 2021 - July 2021
Research on model agnostic interpretability methods in the ambit of images. More specifically, improving resampling process for local interpretable model-agnostic explanations (LIME).
Read the full work here.
DATA SCIENTIST Walmart Supply Chain Analytics USA, Costa Rica | October 2018 - July 2020
Directed and developed data analysis projects to provide agile solutions to business partners. Main projects included an anomaly detection system, statistical sampling design, and consumption layer design.
DATA ANALYST Walmart Supply Chain Analytics USA, Costa Rica | January 2017 - October 2018
Worked in data extraction, transformation, and visualization. Main projects included statistical process control techniques and KPI development.
DATA ANALYST BAC Credomatic Regional Compliance Management, Costa Rica | April 2016 - December 2016
Developed a money laundering detection system based on bayesian decision trees models applied on banking transactional data.
MSc DATA SCIENCE AND ARTIFICIAL INTELLIGENCE Université Côte d’Azur, France | 2020 - 2022 Honors Graduate (Mention Très Bien)
BACHELOR IN STATISTICS University of Costa Rica, Costa Rica | 2013 - 2017 Honors Graduate
Highest GPA among Statistics majors for three consecutive years : 2013, 2014, 2015. UNIVERSITY OF COSTA RICA
Honorable Mention: 9th place (out of ≈33 000) on National Admission Exam. UNIVERSITY OF COSTA RICA 2012-2013
Honorable Mention: 1st place (out of ≈20 000) on national Admission Exam. TECHNOLOGICAL INSTITUTE OF COSTA RICA 2012-2013
IDEX Scholarship of Academic Excellence 2020-2021 UNIVERSITÉ CÔTE D’AZUR
Academic Excellence Scholarship 2013-2017 UNIVERSITY OF COSTA RICA
Chaves, M., Cabrio, E., & Villata, S. (2025, March). FALCON: A multi-label graph-based dataset for fallacy classification in the COVID-19 infodemic. SAC ’25 - ACM/SIGAPP Symposium on Applied Computing. https://doi.org/10.1145/3672608.3707913
Goffredo, P., Chaves, M., Villata, S., & Cabrio, E. (2023). Argument-based Detection and Classification of Fallacies in Political Debates. In H. Bouamor, J. Pino, & K. Bali (Eds.), Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (pp. 11101–11112). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.emnlp-main.684
python R LaTeX SQL
List of conferences where I have served as a reviewer: