|
|
|
||
|
Artificial intelligence helps us in various ways in the legal field from conducting legal research to analyzing court decisions and even predicting the outcome of court cases. The goal of this course is to provide the students with the basic computational methods of analysis that can be utilized in legal research, such as Natural Language Processing and Machine Learning. First, we will begin by understanding the basic data structures and libraries in Python. Then, we will focus on how we can collect data and process it. Finally, we will work on how we can classify data through machine learning and natural language processing. The course is based on practical exercises on available legal data sets such as court decisions, legislation, and other regulations.
Learning Outcomes: Upon completing this course, students will be able to 1.describe how data analytics supports legal research, decision-making and policy analysis. 2. identify and work with legal data sources (i.e. court decisions, contracts and regulations) 3.explain basic data concepts; data types such as structured and unstructured data. 4. use python to load, clean, manipulate and visualize data. 5. apply basic natural language processing techniques to analyze legal texts like court opinions and contracts. 6.use machine learning algorithms to classify legal texts. Last update: Šicnerová Barbora, Mgr. (22.08.2025)
|
|
||
|
The course requires students to take weekly in- class mini quizzes as well as bi-weekly (every two weeks) take home exercises. Alongside these assessment methods, they need to provide two projects (one small and one relatively bigger). 1.Quizzes comprise the 10% of the overall grade. They will contain short multiple choice questions to measure to what extent the students understand the relavant data structures and concepts. 2. Weekly exercises on data cleaning, and visualisations comprise 20% of the overall grade of the course. 3.Mini-project involves 30% of the overall grade, and it requires students to work on a small legal data set for simple data visualisations. 4. Final project comprises 40% of the overall grade. This will be a data analysis project involving either NLP tecniques or ML classification. The data set will be rather larger than the mini project. Last update: Šicnerová Barbora, Mgr. (22.08.2025)
|
|
||
|
The course covers following topics: -Python for Legal Studies (basic syntax, data structures and libraries) -Collecting legal data by using AI -Collecting legal data by webscaping -Using APIs for data collection -Legal text Processing (Tokennization, Stemming, TF-IDF) -Natural Language Processing- Topic modelling -Natural Language Processing- Sentiment analysis and Named entity recognition -Classifying legal data through non-supervised Machine learning classification -Classifying legal data through supervised Machine learning classification Last update: Šicnerová Barbora, Mgr. (22.08.2025)
|
|
||
|
Základní literatura: 1. Kevin D. Ashley, Artificial Intelligence and Legal Analytics, Cambridge University Press, 2017 (Part 1, chapter 1, pp 3-37) 2. Wes Mckinney, Python for Data Analysis, 2022 Ostatní literatura: 1.Jake Vanderplas, Python Data Science Handbook- Essential Tools for Working With Data, 2 2.Dipanjan Sarkar, Text Analytics with Python, A Practitioner’s Guide to Natural Language Processing, 2029 (Chapter 3) Last update: Šicnerová Barbora, Mgr. (22.08.2025)
|