Projects

The source code and all the supplementary material used for my Master Thesis final project is hosted on GitHub.

Abstract

Ideological polarization on social media reflects a crucial issue of contemporary societies. Several studies within social sciences and psychology tried to investigate the root causes and formulated theories to describe this phenomenon. Information retrieval through social media platforms like Twitter has the means to hinder a democratic approach towards political debates. This aspect fosters the creation of echo chambers that enhance the spreading and reinforcement of polarized opinions among ideologically similar individuals. The aim of this study was to find a scientific way to measure the impact of controversial topics on Twitter users’ behavior from a temporal perspective. By relying on third-party software and the Twitter Developer API, I collected a set of raw tweets from Twitter related to political controversies that took place between September 2013 and December 2016. Each controversy was related to a set of hashtags conventionally adopted by the users to express their political affiliation. A large network of Twitter users, mutually interacting in the same time window, along with the collection of tweets designated the subject of the study. I revealed evidence of a positive bonding effect on Twitter users mutually communicating as part of the global conversations represented by such controversial hashtags. This reflected into an increase of the mutual interaction consistency in both the short and long term, fostered by the online controversies. I further discovered that the mutual interactions network obeyed the laws of a precise topological structure which highlighted the presence of community clusters growing around the most influential users. The obtained results hinted the existence of the echo chamber phenomenon. The role of the community hubs and the high in-community communication suggests a clear resemblance of a realistic political debate between opposing groups. Further investigation within NLP suggested that predicting tweets’ political leaning is a viable task.

As part of the Artificial Intelligence and Multi-Agent Systems course offered by DTU during the A.Y. 2017/18, a mandatory final project involved the design and development of a Sokoban puzzle solver leveraging commonly known A.I. principles, both for Single and Multi-Agent systems. My group mates and I worked together to create a solver in Java using a combination of HTN planning, optimization heuristics and the Belief-Desire-Intention model, resulting in a fully autonomous system able to solve levels (i.e. maps) of different complexity.

The below videos show a running demo of our solver for two different levels. The source code of the application is hosted on GitHub.

A prototype of a digital rehabilitation tool for patients with impaired balance and motion control, achieved by combining the potential offered by the Unity Game Engine and the Microsoft Kinect V2. In detail, the purpose of this game-oriented application, named Hell of Balance, is to assess balance improvement and rehabilitation, by letting the patients practice in an efficient and motivational way.

This application was developed as part of the final project for the Healthcare Technology course offered by DTU during the A.Y. 2017/18. Check out the demo below!

Another cool exercise carried out to practice with the Unity – Kinect integration was developing a revised version of the famous retro game Space Shooter, where hand gestures fully replaced the keyboard to control the space ship.

Applying Data Analysis, Machine Learning and Data Visualization on a large dataset using Python and Javascript D3 library.

Read more and check out the source code on the amazing official web page, which will interactively walk you through the results. This was the final project of the Social Data Analysis and Visualization course offered by DTU, A.Y. 2017/18.

Phrasebook is a mobile application for Android devices to help people memorize foreign language vocabulary. The app has been published on Google Play Store and it’s available for free to all Android users, you should definitely give it a try!

The application has been developed as part of the final project of the Personal Data Interaction for Mobile and Wearables in DTU, A.Y. 2016/17. Check out the demo below to get a feeling of how it works:

Data Mining on Amazon Product Reviews Dataset. This work was part of the final project for the Computational Tools for Big Data course offered by DTU, A.Y. 2016/17. By leveraging big data technologies such as Apache Spark, Neo4j, Pandas DataFrames, SQL, the overall goal was to exploit the potential of such tools to carry out an extensive analysis on an inconveniently large dataset, with all the drawbacks that kick in when it comes to storing, handling and processing the data.

The results of the analysis and the related source code were published on a PDF report.

Analyzing the social networks obtained from the Lord of the Rings universe to study the most common patterns and behaviors when it comes to network theory and Natural Language Processing. This work was part of the final project for the Social Graphs & Interactions course offered by DTU, A.Y. 2016/17. Python NetworkX library for network analysis and the NLTK (Natural Language ToolKit) were the core tools used to carry out the analysis.

Find out more by checking out the website, used as the official delivery format of the results, and the video trailer of the project below!

The project involved the design and the development of a website by focusing on state of the art design principles and web development cutting-edge technologies, such as HTML5, CSS3, Javascript, PHP, AJAX and MySQL, resulting in a highly dynamic and responsive interface. Check it out here!

This work was carried out as part of the final project for the Hypermedia Applications course, offered by Politecnico di Milano, A.Y. 2015/16.

TIM (Telecom Italia Mobile) is one of the leading Internet providers for mobile phones and home ADSL in Italy.

A complete Java Online Multiplayer Board Game, developed in a team project and presented as the final hand-in of my Bachelor’s Degree at Politecnico di Milano. The game is inspired by the official board game named Council of Four (Cranio Creations).

The game features both a CLI and GUI (JavaFX). It supports both Socket and RMI connection to the server engine. The game map is completely configurable via the built-in map editor. In-game chat is also available. Development framework: Java 8 SE.

The official repository is currently private.