Joseph Martínez

Graduate Research Assistant - ODU

About Me

Research Assistant with 3 years of experience in Data Science, Machine Learning, and Natural Language Processing. Proficient in training LLMs, and Machine Learning (ML) algorithms. Strong communication skills through academic and professional engagements. Proven ability in large-scale data analytics to derive valuable insights. Collaborative team member with a track record of successful collaboration on international research projects.

Work Experience

VMASC logo ODU Virginia Modeling, Analysis, & Simulation Center (VMASC)
Graduate Research Assistant
[Sep 2022 – Present]

• Created a custom conversational LLM (akin to ChatGPT) fine-tuning Llama2 with a dataset of 330 news.
• Trained Machine Learning models (KNN, RFC) and fine-tuned NLP models (BERT) to classify frustration types.
• Designed and maintained detailed documentation of models, algorithms, and reports on GitHub repositories.
• Presented poster at a research conference in Pittsburgh, and attended others in Arlington, VA, and Oxford, OH.

ODU logo Old Dominion University
Social Media Data Analyst (Consultant)
[Jul 2021 – Jan 2022 ] · 8 mos

• Geolocated, filtered, and estimated the tone of 7.3 million Tweets through fine-tuning fifteen NLP models (spaCy, BERT, RoBERTa) and Statistical Analysis. Models were highly reliable, with a mean accuracy of 72%.
• Extracted, cleaned, and pre-processed 15.5 million Tweets in multiple languages with Twitter’s API and Python.
• Created dashboards with Tableau and Google Data Studio to represent migration data.
• Collaborated with teams from Norway, Colombia, Greece, and the US on a $1.4M Minerva research initiative.

Uninorte logo Universidad del Norte
Social Media Data Analyst (Research Assistant)
[Nov 2020 – Jun 2021] · 7 mos

• Trained a Natural Language Understanding (NLU) model with IBM Watson to semi-automate the identification of actors, factors, and relationships from news articles, achieving a final accuracy of 70%.
• Gathered, filtered, and cleaned geo-tagged 4,680 Tweets on migration using Twitter's API and Python.
• Conducted a lexicon-based Sentiment Analysis of Tweets to spot xenophobic trends.
• Determined key actors of a Twitter conversation about migration through Social Network Analysis with Gephi.

Education

Uninorte logo Old Dominion University

M.Sc. Modeling and Simulation Engineering
Aug 2022 – Dec 2024 (expected)

DS4A logo DS4A Correlation One

Apprenticeship | Data Scientist
Mar 2022 – Jul 2022

Uninorte logo Universidad del Norte

B.S. Industrial Engineering
Jan 2017 – Mar 2022