Toxic Tweets in the 2019 Australian Federal Election

Kim Doyle1

1University of Melbourne 



The quality of public discourse today is of major concern both to academics and the general public. New social media platforms allow a wider range of voices to enter public discourse, but also lead to little accountability in terms of upholding community standards. This talk discusses the use Google’s Perspective API, primarily a moderation tool, to study toxic language on Twitter. It uses Perspective machine learning models to identify toxic comments and topics and how they impact particular users in a political context of the 2019 Australian federal election.


Kim Doyle is a Research Data Specialist at the Melbourne Data Analytics Platform (MDAP) and a PhD in Media and Communications at the University of Melbourne. Previously, she taught natural language processing and data mining to researchers at the University of Melbourne’s Research Platform Services at the for a number of years. Her research interests include political communication, social media and computational social science.

From 2011 to 2013, Dr Daniel Russo-Batterham worked as a researcher at the Centre d’Études Supérieures de la Renaissance in Tours, France, while completing a Master of Music. Since graduating from his PhD in 2018, Daniel has worked on Digital Humanities projects across Australia and abroad. He has a background in python, data wrangling, relational database design, web scraping, quantitative methods, natural language processing, and a broad range of approaches to visualisation. He is currently working in the Melbourne Data Analytics Platform.


AeRO is the industry association focused on eResearch in Australasia. We play a critical coordination role for our members, who are actively transforming research via Information Technology. Organisations join AeRO to advance their own capabilities and services, to collaborate and to network with peers. AeRO believes researchers and the sector significantly benefit from greater communication, coordination and sharing among the increasingly different and evolving service providers.