Natural Language Processing and Text-Mining - 4GMC14C1

Goal(s)

The course introduces the first tools for processing textual data.
Students will learn how to manipulate textual data in order to prepare it for analysis.
The analysis methods that will be learned allow students to match strings and vocabulary; to explore texts and identify their characteristics (mutual information, similar or complementary information); to classify texts and identify typologies.

Content(s)

1. Introduction to NLP (Natural Language Processing) and TM (Text-Mining) (1 C-TD)
2. Pre-processing (2 C-TD): Parsing, tokenization, case folding, lemmatisation, stemming, POS-tagging, sentence splitting, stop words removal…
3. Text representations (1 C-TD): Vector Space Model, Bag-of-words model, TF, TF-IDF, Word2vec, GLOVE…
4. Feature selection (1 C-TD): X², mutual information, information gain…
5. Text classification (2 C-TD): One VS. Multi class, Bias VS. Variance, Kappa test, training set, validation set, testing set, accuracy, validation set, leave-one-out cross-validation, K-fold cross validation, precision, recall, F-Measure, confusion matrix…

Students will have taken and validated the following courses: Probability and Statistics; Programming with R