Text Analytics 2025/2026

TXA (635AA), 6 CFU
Graduate Programs in Data Science & Business Informatics and in Digital Humanities WDB-LM, WFU-LM

General Information

Academic Year 2025-2026, first semester

WHERE: Polo Didattico "L. Fibonacci", Via F. Buonarroti 4, Pisa
WHEN:
- Thursday, 14:00-16:00 - Fib M1 (Polo Fibonacci B)
- Friday, 11:00-13:00 - Fib L1 (Polo Fibonacci B)
OFFICE HOURS: Tuesday 14:00-16:00 - room 288 @ Dpt. Computer Science (by appointment)
WHAT: Catalogue: TXA Programme 2025-2026 - 635AA.

Objectives

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 main objectives of the course are:

Learning essential techniques, algorithms, and models used in natural language processing.
Understanding of the architectures of typical text analytics applications and of libraries for building them.
Expertise in design, implementation, and evaluation of applications that exploit analysis, interpretation, and transformation of texts.

Exam modalities

Students will be assessed through a written exam and an oral exam. Each student will be evaluated based on their ability to discuss the course content using appropriate terminology and to practically apply natural language processing techniques.

Attending Students

The exam consists of a written test and an oral test. The exam consists of a written test and an oral test. For the written part, attending students can choose between a traditional written exam, with questions on the topics covered in the course, or a group project carried out during the course period, designed to assess the ability to plan and implement a text analysis task agreed upon with the instructor. In both cases, the oral test follows: students who have completed the project are required to present and discuss it, including individual questions to verify each member’s understanding, and all students, regardless of the chosen option, are further examined on the remaining topics of the course.

Non-Attending Students

The exam consists of a written test and an oral test. Non-attending students will be required to answer questions and solve exercises during a written exam.
No materials other than the slides, notebook experimentation, and the selected chapters from the books are required.

Slides & Materials

Students are required to study the slides, actively work through and experiment with the notebooks, and read the selected chapters from:

D. Jurafsky, J.H. Martin, Speech and Language Processing. 3nd edition, Prentice-Hall, 2018.
S. Bird, E. Klein, E. Loper. Natural Language Processing with Python.
J. Eisenstein. Introduction to Natural Language Processing. MIT Press, 2019.
Zhai and Massung. Text Data Management and Analysis. Morgan & Claypool Publishers, 2016.

Date	Lecture	Slides	Material / Reference
25/09/2025	Introduction to the course, NLP & Text Analytics.	1 - Introduction to the Text Analytics course	J. Eisenstein. Introduction to Natural Language Processing. MIT Press. Chp. 1.
26/09/2024	Introduction to Python Text Indexing Regex	2- Introduction to Python & Text Indexing	Notebook Python basics Notebook Strings basics Notebook Regular expressions D. Jurafsky, J.H. Martin, Ch. 2.
2/10/2025	Reminds on Probability	3 - Reminds on Probability
9/10/2025	Probabilistic Language Models	4 - Probabilistic Language Models	Notebook Probabilistic Language Models
10/10/2025	Probabilistic Language Models	5 - Practice on Probabilistic Language Models	D. Jurafsky, J.H. Martin, Ch. 3. Notebook Probabilistic Language Models (part 2)
16/10/2025	Text Indexing	6 - Text Indexing (part. 2)	Notebook Collocations (NLTK, Gensim)
17/10/2025	Text Indexing	7 - Text Indexing (part. 3)	D. Jurafsky, J.H. Martin. Chps. 17 (excluding chs. 17.4 and 17.5), 19 (Introduction and ch. 19.1 only), 22 (excluding chapters 22.4 and 22.5.19)
23/10/2025	Text Indexing	8 - Text Indexing (part. 4)
24/10/2025	Lesson Cancelled
30/10/2025	Text Indexing	9 - Text Indexing (part. 5)	Notebook Text Processing to Vectorization D. Jurafsky, J.H. Martin. Chp. J (PMI)
31/10/2025	Vector Space Models	10 - VSM (Correct Version)	Notebook VSM D. Jurafsky, J.H. Martin. Chp. 6
6/11/2025	Machine Learning for Text Analytics	11 - Machine Learning for Text Analytics (part. 1)	(Recommended reading, but not required: D. Jurafsky, J.H. Martin. Chp. 4)
7/11/2025	Machine Learning for Text Analytics	12 - Machine Learning for Text Analytics (part. 2) (correct version)	Notebook Supervised Classification
13/11/2024	Student project presentations	First presentation: How to
14/11/2025	Topic Modeling	13 - Topic Modeling	Zhai and Massung (2016) Text Data Management and Analysis. Ch. 17. Notebooks Topic Modeling (Gensim & Sklearn)
20/11/2025	Topic Modeling and Optimization	13.1 - Practice on Topic Modeling and Optimization	Notebook Optimization
21/11/2025	A primer on Neural Networks	14 - A primer on Neural Networks	Forward and backward pass in a neural network by Andrea Esuli (September 3, 2020) Helper resource (optional): Neural Networks and Deep Learning by Michael Nielsen (2019)
27/11/2025	NNs Types and Characteristics	15 - NNs Types and Characteristics	Notebooks From SVM to NN Classification - cnnNet
28/11/2025	(Static) Embeddings	16 - (Static) Embeddings	Notebook Classification - LSTMNet D. Jurafsky, J.H. Martin. Chps. 7, 13, 5
4/12/2025	Student project presentations	Second presentation: How to
5/12/2025	Contextual Embeddings & Neural Language Models	17 - Contextual Embeddings & Neural Language Models	D. Jurafsky, J.H. Martin. Chp. 8, Notebook Word2Vec & FastText
9/12/2025	Neural Language Models & Transformer	18 - Neural Language Models - Transformer	D. Jurafsky, J.H. Martin. Chp. 11,
11/12/2025	Dialogue Systems	19 - Dialogue Systems	D. Jurafsky, J.H. Martin. Chps. 24 Notebook Chatbot Notebook Task-Oriented Chatbot
12/12/2025	Practice on BERT - Instructions for Final Exam [Teacher present, but classrooms closed due to strike]	Final Exam: How to	Notebook Bert (Binary) Notebook Bert (Multi-class)