Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
The Power of Words: How Languages Shape AI Responses
Published:
Overview
This experiment explores how different language variations impact AI-generated outputs. Using 200 prompts, three bilingual evaluators assessed AI-generated images based on prompts in different languages.
Helpful Reviews
Published:
Overview
This project explores the intersection of Data Science, Machine Learning, and AI Communication, highlighting the importance of effectively conveying AI-driven insights to diverse audiences.
Truthful vs. Deceptive Hotel Reviews Classification
Published:
Overview
This study focuses on the classification of hotel reviews as either truthful or deceptive. Various machine learning models were evaluated to determine their effectiveness in identifying deceptive reviews.
Cross Language Call Sanitization
Published:
Overview
Modern software often integrates multiple programming languages, increasing complexity and security vulnerabilities. This paper investigates how known sanitizers can be adapted to detect and mitigate cross-language call vulnerabilities.
portfolio
How to Disappear Online
This Master thesis explores methodologies for digital erasure, focusing on data privacy, compliance with GDPR, CCPA, and AI regulations, and the use of machine learning to facilitate secure data deletion.
Open-Source Widn Integration with Blackbird.io
As part of my contributions to Widn, I worked on integrating it into Blackbird.io to enhance workflow automation using AI-driven text and file translation. This integration aims to streamline data workflows, optimize automated decision-making, and improve efficiency in real-world applications.
AI-Powered Virtual Fitting with Stable Diffusion
This project uses fine-tuned Stable Diffusion and LoRA models to create photorealistic virtual try-ons by applying specific clothing onto various body types with inpainting and data-driven AI training.
Unbabel Technologies Project
A deep dive into Unbabel’s language processing technologies using AI & Machine Learning.
Truthful vs. Deceptive Hotel Reviews Classification
Utilized a variety of classifiers, including Linear Support Vector Classifier, Gradient Boosting Classifier, K-Nearest Neighbors Classifier, and Multinomial Naive Bayes Classifier to analyze hotel reviews. This project focuses on distinguishing between truthful and deceptive hotel reviews, showcasing my skills in handling complex classification tasks.
Helpful Reviews
Predict the helpfulness of Amazon Fine Food Reviews. The project integrates machine learning models like Naive Bayes and Logistic Regression with a Hugging Face transformer for advanced text analysis. It predicts review helpfulness based on textual content, combining traditional ML models with modern NLP techniques and utilizes sentiment analysis for a nuanced understanding.
Sentiment Analysis Project
Specialized in sentiment analysis, this Python-based project leverages NLTK and pandas for processing and evaluating text emotions. Key steps include data preparation, sentiment scoring, and detailed visualizations. The project effectively parses and analyzes sentiments of ideas and comments, providing insights into public opinion.
publications
How to Disappear Online: Approaches for Digital Erasure and Evaluation Methodologies
Published in Instituto Superior Técnico, University of Lisbon, 2024
This Master thesis explores methodologies for digital erasure, focusing on data privacy, compliance with GDPR, CCPA, and AI regulations, and the use of machine learning to facilitate secure data deletion.
Recommended citation: João Vasco Almeida Sobral Siborro Reis. (2024). "How to Disappear Online: Approaches for Digital Erasure and Evaluation Methodologies." Instituto Superior Técnico, University of Lisbon.
Download Paper | Download Summary
talks
Web Summit 2019 – Exploring as a University Student
Published:
In 2019, as a university student, I had the opportunity to attend Web Summit Lisbon for the first time. This experience was my introduction to the world of major tech conferences, where I explored emerging innovations, listened to industry leaders, and connected with like-minded individuals.
Web Summit 2023 – Experience as a Volunteer
Published:
In November 2023, I had the incredible opportunity to attend Web Summit Lisbon as a volunteer, immersing myself in one of the most dynamic technology and innovation ecosystems in the world. While my role was initially to support the event operations, this experience quickly turned into an invaluable learning journey, shaping my perspective on AI, entrepreneurship, and global tech trends.
Web Summit 2024 – Official Launch of Widn.Ai
Published:
Attending Web Summit Lisbon 2024 marked my third year at this premier global technology conference. This year was particularly special as I attended as a partner with Unbabel, supporting the official launch of Widn.Ai, an innovative AI-powered solution designed to enhance machine translation.
CES 2025 - Conference Attendance
Published:
In January 2025, I had the privilege of attending CES 2025 in Las Vegas, the world’s largest and most influential technology conference. As a representative of Unbabel and Widn.Ai, I had the opportunity to engage with innovaters, connect with industry leaders, and explore the latest advancements in AI, automation, and digital transformation.
teaching
Teaching Assistant Professor
Human-Computer Interaction, University of Lisbon - Instituto Superior Técnico, Computer Science, 2023
Course Overview
- Course: Human-Computer Interaction.
- Diverse Students: Teaching 48 students from five countries.
- Grade: Rated 9/9 by students
- Standards: Delivered lectures and assessed student performance.