Real-time Extensible English Language Racism Monitor and Research Tool
2021 Project - Call for Expression of Interest
- A data input unit which will return 'statement' objects enhanced with relevant metadata
- A data pre-processing and classification unit which will prepare data for classification and return a classification (e.g. return a classification of statements as racist or not-racist)
- A machine learning unit that will assist the data processing and classification unit with classification
- A database for storing data necessary for functionality of the research tool
- A time series unit which will undertake time series related tasks such as representation of a series of statements as a time series and which will provide time series analysis tools (e.g. spikes and discontinuities), and visualisation
- A geographic unit which will enable visualisation of statements in both time and in terms of a geographic visualisation
- A web-based visualisation unit that will enable interactive visualisation of data in both real-time and over specified periods
- A web-based firewall protected research tool for racism researchers focussing on fine grained investigation of racist content and providing natural language - corpus, concordance and similar tools
- A one paragraph description of yourself, including also reference to the subject you would be enrolled in if doing the project.
- A one to two paragraph description of the contribution you would envisage making to the project, including prior experience relevant to the proposed contribution.
- A copy of your cv and academic transcript.
Broader Goals and Description of this Project
This project seeks to apply and/or advance the state of the art in computer science in the detection and prevention of use of information technology for racist purposes and for the purpose of developing and demonstrating computational tools for the study of racism, particularly in application to online data. The project may involve basic research, applied research or a combination of both. It is likely that existing methods addressing other online threats will be relevant to the problem domain including methods to address online misogyny, bullying, terrorist networks and their identification and disruption (as examples). The project is likely to involve use of natural language processing, machine learning and network analysis as existing technologies deployed in this problem domain.
The project may involve working with government and non-government external stakeholders concerned with the problem of online racism to assist them in responding to online racism. Research by publication is encouraged as part of this project.
Dr Michael Curtotti will be the primary supervisor for this project and would provide the main source of supervision during the project. Dr Eric McCreath would also provide some supervisory direction and act as the chair for the panel of supervisors. If you are interested in this project in the first instance please contact Michael.
Previous Student Projects
- Racism Detection by using BERT-Based Transfer Learning Approach in Twitter. Zixin Wang (COMP4560 Advanced Computing Projects - 2020 Semester 2)
- The Detection and Prediction of Trigger Events in Racist Chatter in Twitter Streams. Erin Qin (ENGN2706 Research Methods – 2020 Semester 1)
- Sentiment Analysis and Mapping of the “White Australia” Concept in Australian Newspaper Archives. Angus Wickham (COMP4560 Advanced Computing Projects – 2020 Semesters 1 & 2)
- Develop technologies that support the best in humanity and challenge the worst
- So the web really is a public good that puts people first.
Eugenia Siapera, Elena Moreo, Jiang Zhou. Hate Track Tracking And Monitoring Racist Speech Online
Tina Besley & Michael A. Peters (2019) Terrorism, trauma, tolerance: Bearing witness to white supremacist attack on Muslims in Christchurch, New Zealand, Educational Philosophy and Theory
Karsten Muller and Carlo Schwarz, Fanning the Flames of Hate: Social Media and Hate Crime
Jacob Davey and Julia Ebner (2019), The Great Replacement: The Violent Consequences of
Extremism, the Institute for Strategic Dialogue
Joint open letter on concerns about the global increase in hate speech (25 UN human rights rapporteurs and experts)
Requiem for online harassers: Identifying racism from political tweetshttps://ieeexplore.ieee.org/abstract/document/7962526
Multilingual Cross-domain Perspectives on Online Hate Speech https://arxiv.org/ftp/arxiv/papers/1809/1809.03944.pdf
Mining communities and their relationships in blogs: A study of online hate groupshttps://www.sciencedirect.com/science/article/abs/pii/S1071581906001248
Platformed racism: The mediation and circulation of an Australian race-based controversy on Twitter, Facebook and YouTubehttp://eprints.qut.edu.au/101370/
Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter
Platformed racism: The mediation and circulation of an Australian race-based controversy on Twitter, Facebook and YouTube | QUT ePrints
A Unified Deep Learning Architecture for Abuse Detectionhttps://arxiv.org/abs/1802.00385
Deep Learning for Hate Speech Detection in Tweets https://dl.acm.org/citation.cfm?id=3054223
Cyberbullying Detection and Classification Using Information Retrieval Algorithmhttps://dl.acm.org/citation.cfm?id=2743085
Social media and digital technology use among Indigenous young people in Australia: a literature review https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4881203/