Text Analytics A.Y. 2018/19

Teachers

Schedule
Day	Hour	Room
Monday	11-13	X1, Polo Fibonacci
Tuesday	9-11	X1, Polo Fibonacci

Forum

Forum on Piazza

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 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.

Disciplinary background: Natural Language Processing, Information Retrieval and Machine Learning
Mathematical background: Probability, Statistics and Algebra
Linguistic essentials: words, lemmas, morphology, PoS, syntax
Basic text processing: regular expression, tokenisation
Data gathering: twitter API, scraping
Basic modelling: collocations, language models
Introduction to Machine Learning: theory and practical tips
Libraries and tools: NLTK, Keras
Applications:
- Classification/Clustering
- Sentiment Analysis/Opinion Mining
- Information Extraction/Relation Extraction
- Entity Linking
- Spam Detection: mail spam & phishing, blog spam, review spam

Jupyter Notebook Server

A server has been setup for running Jupyter Notebooks. In order to log into the server, you must get credentials for a Google Suite account:go to this page and register with your University credentials to activate your free account.

Lecture Notes

Date	Lecture	Notes
17/9/2018	Introduction	Text Analytics
18/9/2018	Introduction to Probability	Probability
24/9/2018	Language Modeling	Language Modeling
25/9/2018	Introduction to Python	See notebooks “Introduction to Python” in folder “Text Analytics” on http://attardi-4.di.unipi.it:8000/“
1/10/2018	Introduction to Python	See notebooks “Introduction to Python 2” and “RegEx” in folder “Text Analytics” on http://attardi-4.di.unipi.it:8000/“
2/10/2018	Introduction to NLTK	See notebooks “Introduction to NLTK” in folder “Text Analytics” on http://attardi-4.di.unipi.it:8000/“
8/10/2018	Preprocessing and tokenization	Tokenization
9/10/2018	Word Similarity	Tokenization Homework 1 (deadline 15/10)
15/10/2018	Correction of Homework 1, Text Classification	Text Classification
16/10/2018	Classifiers	Classifiers
22/10/2018	Hidden Markov Models	HMM
23/10/2018	POS Tagging	HMM
29/10/2018		HomeWork 2
5/11/2018	Named Entity Tagging	NER
06/11/2018	Universal Dependencies
12/11/2018	Dependency Parsing
13/11/2018	Neural Language Models: PCA, Word2Vec	LM See notebooks “LanguageModels.ipynb” on http://attardi-4.di.unipi.it:8000/
20/11/2018	NLM: FastText, Doc2Vec	LM See notebooks “docEmbeddings.ipynb” on http://attardi-4.di.unipi.it:8000/
26/11/2018	NLM: Text Generation, ELMo, BERT	LM See notebooks “TextGeneration.ipynb” on http://attardi-4.di.unipi.it:8000/
27/11/2018	Sentiment Analysis	SA
3/12/2018	Lexical Resources	LR See notebooks “pmi-lex.ipynb” and “pmi-lex-IMDB.ipynb” on http://attardi-4.di.unipi.it:8000/
4/12/2018	Sentiment Classification	SC See notebooks “VADER.ipynb”, “sklearn.ipynb”, “lstmNet.ipynb” and “cnnNet.ipynb” on http://attardi-4.di.unipi.it:8000/
10/12/2018	Quantification
11/12/2018	Spam, Scam, Phishing, Fake reviews, Clickbaits, Fake News

Textbooks

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

Previous editions

2017-2018

DidaWiki

Strumenti Utente

Strumenti Sito

Indice