Learning with Text research projects

Google AI for Social Impact: The Use of AI to Code Ambulance Data for Suicide Prevention

(Google Grant, 2019-2022)

Project lead: Prof. Wray Buntine

Ambulances are typically the first point of contact with someone who is suicidal. Ambulance clinical records are an important and rich data source, containing details of the nature and background to the attendance, the location of the event, and the clinical outcome. For more than 20 years and in partnership with Ambulance Victoria, Turning Point has been providing a Victorian alcohol, illicit and pharmaceutical drug surveillance system using coded paramedic clinical data. This world-first surveillance system has recently been expanded to include reporting of national data in partnership with jurisdictional ambulance services, and there is an opportunity to apply the same methodology to suicidal behaviour in these datasets.  However, the time and resources needed to code additional suicide-related attendances is prohibitive without significant ongoing funding. We propose using AI to allow us to also code national ambulance data that will establish a cost-effective model that could be adopted globally.

Read the full project report


Social Media Analytics for Social Good

(Research Student Projects, 2018-2022)

Project Lead:  Prof. Wray Buntine

Social media platforms such as Twitter provides a repository of events, news and opinions from broad audiences: companies, organisations, professionals and the public. Tweets offer structured data with formal and informal natural language, useful meta-data like location, mentions and embedded links to relevant content.  Machine learning techniques are to mine these opinions, to provide governments, policymakers and health authorities with information about the public concern on a range of issues. Examples include green energy transition, data privacy, elections, and public health responses to COVID-19.

This project is developing a hybrid machine learning and qualitative analysis methodologies for analysing and interpreting large quantities of social media data. This is an interdisciplinary project combining techniques from the topic modelling research from the Machine Learning Group with Information Systems research from the Department of Human-Centred Computing in FIT.

Read the full project report