Python: For the Digital Humanities

Digital Humanities lies at the intersection of traditional Humanities research (close reading) and Computational Methodologies (distant reading). It is an interdisciplinary field currently expanding and overlapping with neighboring areas such as Computational Social Science or Digital Journalism. In this course we will explore how Digital Humanities uses a wide range of computational methodologies with Python that allow users to perform tasks such as data acquisition (webscraping), data analysis (cleaning and pre-processing, POS tagging, NER),  data storage (learning how to save our data (raw and processed) in CSV and txt files), data visualization (Geospatial Analysis), and Network Analysis.

In this introductory course, students will explore the basics of text analytics applied to Digital Humanities using several Python libraries such the Natural Language Toolkit (NLTK), Pandas, or BeautifulSoup (among others). Course content is disseminated over 12 hours through slides, live coding of the instructor and in-class exercises. We will use the Jupyter Notebooks interface provided by the Anaconda Environment.
 

General information

Duration 12 hours
  • Data acquisition (webscraping), data cleaning and pre-processing, data storage
  • Information extraction (POS tagging, Name Entity Recognition)
  • Geospatial analysis
  • Network Analysis
It is necessary to have taken the course "APPB – Python Basics" or have an equivalent level of knowledge. You should feel comfortable working with Python at the introductory level (e.g. data types, data structures, control flow, creating first functions).
This introductory Python course is directed for beginners and is suitable for anyone who wishes to use Python in the field of the Digital Humanities.
By the end of the introductory course, students will be able to:
  • understand the basics of data acquisition for Digital Humanities Projects.
  • apply text pre-processing techniques for cleaning and preparing textual data.
  • understand the basics of POS tagging and Name Entity Recognition (NER)
  • gain a basic understanding of Geospatial Analysis.
  • Introduction to Network Analysis with Python (Sociocentric and Egocentric Networks).
Course materials will be provided by the lecturer.
Course content is disseminated over 12 hours through slides, live coding of the instructor and in-class exercises. We will use the Jupyter Notebooks interface provided by the Anaconda Environment.

Dates

Code Referents Dates Available seats Place
HS24-APPH1 Fernandez Fernandez Elena 07.01.2025 - 28.01.2025 (17:00 - 20:00 o'clock)
6 Online Course Register