Andrea Esuli (andrea.esuli@isti.cnr.it)

Office hours: by appointment, send email.

Lectures will be given using Microsoft Teams. Join the Text Analytics Team here.

Lecture recording is available on Microsoft Teams for delayed viewing.

The course targets text analytics systems and applications to respond to business problems by discovering and presenting knowledge that is otherwise locked in textual form. The objective is to learn to recognize situations in which text analytics techniques can solve information processing needs, to identify the analytic task/process that best models the business problem, to select the most appropriate resources methods and tools, to collect text data and apply such methods to them. Several applications context will be presented: information extraction, sentiment analysis (what is the nature of commentary on an issue), spam and fake posts detection, quantification problems, summarization, etc.

1. Disciplinary background: Natural Language Processing, Information Retrieval and Machine Learning
2. Mathematical background: Probability, Statistics and Algebra
3. Linguistic essentials: words, lemmas, morphology, PoS, syntax
4. Basic text processing: regular expression, tokenisation
5. Data collection: twitter API, scraping
6. Basic modelling: collocations, language models
7. Introduction to Machine Learning: theory and practical tips
8. Libraries and tools: NLTK, Spacy, Keras, pytorch
9. Classification/Clustering
10. Sentiment Analysis/Opinion Mining
11. Information Extraction/Relation Extraction/Entity Linking
12. Transfer learning
13. Quantification

Exam will consist in a project to be agreed with the teacher and an oral exam. The outcome of the project will be some code and a report of the activity (4-10 pages is the typical length range). Oral exam will consist in the presentation and discussion of the project.

The purpose of the project is to let you have some hands on experience on applying the concepts and methods seen during the course to practical text analytics problems.

Projects may be based on challenges proposed in either research forums (Semeval, Evalita) or other platforms (Kaggle). Students are also invited to propose a project on problem based on other sources (e.g., recent papers on ArXiv CL or AI), or their own interests.

Students may work solo or in groups up to three persons.

Before starting working on the project students must contact the teacher so as to agree on the contents of the project and get a go ahead.

1. D. Jurafsky, J.H. Martin, Speech and Language Processing. 3nd edition, Prentice-Hall, 2018.
2. B. Liu, Sentiment Analysis and Opinion Mining. Morgan & Claypool Publishers, 2012.
3. S. Bird, E. Klein, E. Loper. Natural Language Processing with Python.

• 2019-2020
• 2018-2019
• 2017-2018