Data Science: Applied Text Mining and Natural Language Processing

Description

In this course, students will learn how to apply text mining and NLP methods on text data and analyse them in a pipeline with machine learning and deep learning algorithms. The course has a strongly practical hands-on focus, and students will gain experience in using text mining on real data from social sciences, humanities, and healthcare, and interpreting the results.

Given the rapid rate at which text data are being digitally gathered in many domains of science, there is a growing need for automated tools that can analyze, classify, and interpret these kinds of data. Text mining and NLP techniques can be applied to create a structured representation of text, making its content more accessible for researchers. Applications of text mining are everywhere: social media, web search, advertising, emails, customer service, healthcare, marketing, etc. This course offers an extensive exploration into text mining with Python. The course has a strongly practical hands-on focus, and students will gain experience in using text mining on real data from for example social sciences and healthcare and interpreting the results. Through lectures and practicals, the students will learn the necessary skills to design, implement, and understand their own text mining pipeline. The topics in this course include preprocessing text, text classification, topic modeling, word embedding, deep learning models, large language models, promoting, and responsible text mining.

The course deals with:

• Reviewing the fundamental approaches to text mining;
• Understanding and applying current methods for analyzing texts;
• Defining a text mining pipeline given a practical data science problem;
• Implementing all steps in a text mining pipeline: feature extraction, feature selection, model learning, model evaluation;
• Understanding and applying state-of-the-art methods in text mining;
• Implementing word embedding and advanced deep learning techniques;
• Understanding, employing, and promoting large language models with responsible text mining.

The course starts with reviewing basic concepts of text mining and implementing advanced concepts in natural language processing. At the end of the week, participants will master advanced skills of text mining with Python.

Participants should have a basic knowledge and a motivation of scripting and programming in Python..
 

Participants are requested to bring their own laptop. Software will be available online.

Lecturers

• Dr. Ayoub Bagheri
• Dr. Dong Nguyen
• Dr. Pablo Mosteiro

Target audience

This course works best for learners who are comfortable programming in Python, who want to acquire skills in text mining approaches, and who have a basic knowledge of machine learning.

Participants should also have a basic knowledge and a motivation of scripting and programming in Python. Participants from computer science and related disciplines, as well as diverse fields such as sociology, psychology, education, medicine, statistics, and beyond, will benefit from the course. 

 Please note that the selection for this course will be done on a first-come-first-served basis.

There are no restrictions on who can participate beyond the prerequisites; academics, researchers, and professional participants are all welcome to register for the course.

For an overview of all our summer courses offered by the Department of Methodology and Statistics, please click here.

We also offer tailor-made M&S courses and in-house M&S training. If you want to look at the possibilities, please contact Dr. Laurence Frank at pe.dsai@uu.nl. 

Aim of the course

The course teaches students the basic and advanced text mining techniques using Python on a variety of applications in many domains of science. The skills addressed in this course are:

• Python environment
• Preprocessing text and feature extraction
• Python NLP packages: NLTK, Gensim, spaCy and more
• Text classification
• Sentiment classification
• Text clustering
• Topic modeling
• Word embedding
• CBOW vs Skip-gram
• Contextual word embedding
• Convolutional neural networks
• Recurrent neural networks
• Attention models
• Responsible text mining
• Large language models
• BERT, GPT and other Transformers from the package
• LLMs: pre-training, prompting, and learning from human feedback
• Applications

Study load

Five full days. A typical course day starts at 9.00 hours and ends at 17.00 hours. Each day includes breaks for coffee and tea, lunch, as well as drinks and snacks.

You will receive a certificate upon course completion. Please be aware that this course does not include graded activities, and therefore we cannot provide a transcript of grades.

Tags

• Data Science
• DEEP
• M&S
• machine
• natural language processing
• Python
• Recurrent Neutral Network
• text classification
• text mining
• topic modeling
• word embedding
• large language models