Tune into the #aBitOfCCS Podcast as we explore how large language models classify online political speech about sexism. Aditi Dutta, a doctoral researcher at the University of Exeter, joins us to discuss her study on how automated moderation systems often misclassify anti-sexist speech as harmful—raising important questions about fairness, resistance, and digital democracy.

CONTENT WARNING: This episode includes discussions and examples of sexist language online, which may be offensive or upsetting to some listeners.

Read the paper here: https://arxiv.org/abs/2508.11434v1

Reach out to Aditi at ad882@exeter.ac.uk for more insights into her research.

In this episode, we’re joined by Dr. Valerie Hasse from LMU Munich to demystify one of the most widely used tools in computational text analysis: the dictionary. Valerie explains how computational dictionaries relate (or don’t!) to the everyday dictionaries we know, and breaks down how they actually work behind the scenes. We explore what dictionaries are good for, when to build your own versus using ready-made ones, and where they shine — especially for studying opinions, emotions, and media narratives. Valerie also opens up about the real challenges that come with using dictionaries, from biases to technical hurdles, and whether they still matter in the age of large language models. She gives clear answers and practical insights into a tool that helps researchers decode massive amounts of text.

In this episode, Prof. Jamal Abdul Nasir from the University of Galway reveals why pre-processing is the backbone of all text analysis. He breaks down key steps like defining documents, tokenization, removing stop words, unification, and stemming vs. lemmatization. Jamal also explains unigrams vs. bigrams and how modern NLP techniques like byte-pair encoding are changing the game. Plus, he shares practical tips for making your pre-processing transparent and reproducible, helping your research stand strong and scale up.