Text Mining with tf-idf

How can computational methods help to distinguish between documents in large text corpora? In this workshop we will explore how to use tf-idf (term frequency - inversed document frequency) for text mining. Tf-idf is an information retrieval method to extract distinctive keywords from documents. In this interactive workshop we will explore the possibilities and limitations of the technique. The 2 hours workshop will cover:

- Introduction to tf-idf.
- Hands-on exercise with Google Labs Notebook
- Discussion and reflection

The workshop is aimed at anyone interested in using tf-idf for research in the arts and humanities. Attendees should have some familiarity with programming languages (e.g. Python) and working with data, but no extensive experience is required. We encourage to bring own data to the workshop. Please bring your own laptop and ensure you have access to UCL Wifi (https://www.ucl.ac.uk/isd/services/get-connected/wi-fi/uclguest)

Participation is free but registration is required: https://ucldh-textmining.eventbrite.co.uk

The workshop is facilitated by Dr Marco Humbel (UCLDH/TU Darmstadt) and Dr Jiajie Zhang (UCL DIS).

This event is organised by UCL Centre for Digital Humanities (UCLDH), part of the UCL Institute of Advanced Studies. In 2025, UCLDH is celebrating its 15th anniversary.

UCLDH draws on UCL's world-class research strength especially in information studies, computing science, and the arts and humanities. It supports and coordinates work in many institutional settings throughout the university, including the library services, museums and collections. The research facilitated by UCLDH takes place at the intersection of digital technologies and humanities. It produces applications and models that make possible new kinds of research, both in the humanities disciplines and in computer science and its applied technologies. It also studies the impact of these techniques on cultural heritage, museums, libraries, archives, and culture at large.