Progetto di Linguistica Computazionale per la tesi di laurea triennale in Informatica Umanistica

NLP (KhNURE lections)

Sentiment Analysis module created in Python using nltk, connected to Twitter

A simple Regex based chatbot

This is an experiment on text classification using different supervised learning classifiers and their variants conducted on the Reuters-21578 dataset. The aim is to evaluate the best performance for each of the classifiers by properly tuning the parameters of each classifier so that the least error is recorded during the classification.

During disaster events, sending messages to appropriate disaster relief agencies on a timely manner is critical. Using natural language processing and machine learning, I built a model for an API that classifies disaster messages and also a webapp for emergency works.

Tweet Sentiment Analysis using nltk library and N-gram models

A simple chatbot just to make use of interaction with human users

This project aims to reduce string redundancy by utilizing some of the string similarity concepts of NLP .

A NLP project where I tried to classify emails on whether they are spam or "ham" (i.e. not spam) using different features for my model.

Estudo de Caso - Previsão de Palavras com Base no Contexto e Visualização com PCA

Parse English language sentences to find the nouns and verbs

Practice of the book about the Python's module Natural Language Toolkit

NLP on American workplace comedy TV pilot transcripts using multiple NLP libraries in Python.

Search Engine for querying movie names to search movies based on summaries using PySpark, Map-Reduce and tf-idf, cosine similarity.

Mine Tweets, Clean Data, Preprocess the data, Analyze Twitter sentiment

Repository for NLTK Exercises as a part of a Data Science Course