// Resources & Data
-
Sentiment Analysis for Social Sciences
Italian course on Sentiment Analysis for Social Studies, presented at the 2022 edition of the Paideia Summer School.
-
Board Game Case Study
A case study on the top 100 board games from Board Game Geek, for the Google Data Analytics Professional Certificate. Written in R.
-
Trie structure in Python
My implementation for trie structures, written in Python
-
Notes on Algebra for Applied ML Using Python
My personal notes for the article "Introduction to Linear Algebra for Applied Machine Learning with Python
-
Solving Italian Wordle
Jupyter Notebook in which I go through how to statistically solve the Italian version of Wordle. Loosely based on a fantastic video by 3Blue1Brown.
-
Scraped data from Board Game Geek
Data automatically scraped (almost) daily from the top 100 board games from BoardGameGeek. The data comes into two format: the csv file (containing general information about each game and their ratings) and a json file (containing more details about each game).
-
Graph Codes
GitHub directory containing general codes for graph analysis, written in Python.
-
Graph Algorithms
GitHub directory containing general algorithms for graphs, written mostly in JavaScript.
-
LDA Topic Modeling
Jupyter Notebook walking through LDA for Topic Modeling.
-
NLP with Python Lab
Small course for NLP with Python, in Italian.
-
MELLD
GitHub repository for MELLD; a ttl file containing information regarding several linguistic metadata resources. The data were automatically scraped from the LOD Cloud and annohub, then aligned both manually and automatically. The data thus extracted was then transferred to a ttl file following the META-SHARE ontology.
-
NEAT
NEAT is a database for training of cultural heritage entity recognition and related tasks. The data were extracted from the Europeana Collection, and then automatically annotated using linguistic information extracted from another background corpus.