Previous Collaborations

2019

 

  • Forecasting global diversity in a changing world, Dr Payal Bal, Science

    Although the effects of threats to biodiversity can be characterised at local scales, linking this highly resolved, local knowledge to emergent patterns at the global scale is a massive conceptual and computational challenge. This collaboration aims to build an integrated data and analysis pipeline that will set a gold standard for the integration of computationally intensive analyses and data in ecology, including alternative climate and socio-economic scenarios at annual, decadal and millennial timescales, thereby identifying current and future hotspots of nature-land use conflict.

  • Using 6 billion social media posts to understand gendered hate speech, domestic violence and mental illness, Dr Khandis Blake, MDHS

    Having already established that social media posts can be used to test predictions about the effects of city, state, and country-level variables (eg. income inequality) on gendered behavior, this collaboration will interrogate an eight-year dataset of ~6 billion geolocated tweets to understand how sentiment on social media can predict and reveal real-world problems through the creation of a database that can be queried by tweet text, username, location, and date.

  • Sixth coupled model inter-comparison project climate model data analysis and visualisation, A/Prof Malte Meinshausen, Science

    The world's most comprehensive climate models are currently making projections of 21st Century climate as part of the Sixth Coupled Model Inter-comparison Project (CMIP6). These projections will inform climate science and decision making over the next decade and beyond. This collaboration aims to reformat this 10PB of specialised binary format data so that it can be easily used with widespread data analysis tools.

  • Ready, set, go LawTech: unleashing the power of information extraction in the legal domain, Prof Jeannie Paterson, Law

    Whilst freely available digital legal information (eg. most Australian court judgments since the 1980s) exists, it is generally not in a machine-readable form. And legal judgments are often very lengthy and its time-consuming to extract the pertinent sections. This forms a barrier to the bulk analysis of judgments that would enable the study of overarching trends and patterns. This collaboration aims to use Natural Language Processing to train a machine learning model to automatically extract information from legal judgments.

  • Vote compass: understanding campaign dynamics and political representation using data from a voter literacy platform, Dr Aaron Martin, Arts

    The voter literacy platform Vote Compass has data collected during the 2013, 2016 and 2019 federal elections in excess of 1 million responses from each election campaign. This collaboration will use this data to conduct in-depth research on campaign dynamics, political representation and political geography.

  • Machine learning for clinical and preclinical diagnosis of neurodegenerative disease using speech data, Dr Benjamin Schultz, MDHS

    Only Speech changes with altered brain function. Acoustic analysis of speech provides objective data on these changes. Acoustic features differ between healthy speakers and individuals with disease and evolve over the course of disease. On this basis, sophisticated speech biometrics can act as a proxy for brain integrity and may assist in optimising diagnostic pathways or identifying symptom onset in neurodegenerative diseases. The role of the Melbourne Data Analytics Platform is to liaise with the Neuroscience of Speech team and facilitate the development of machine learning algorithms using open source software.

  • Supporting Indigenous governance of Indigenous data: The Indigenous Data Network and the Kaiela Institute, Dr James Rose, MDHS

    The Indigenous Data Network (IDN) at the Indigenous Studies Unit, Melbourne School of Population and Global health, is an unprecedented national initiative aimed at providing support to Indigenous-controlled Research Organizations (ICROs) around the Australia. The IDN is assisting ICROs to consolidate, organise and leverage the data assets already in their possession, towards better evidence-based service delivery for the communities that they represent. Among numerous ICROs partnered with the IDN, the Kaiela Institute in Shepparton, Victoria is the first in that state to successful coordinate a practical governance strategy that brings these support streams to an implementation stage. Together with the Kaiela Institute and the IDN, MDAP data stewards and researchers will contribute to the development of a data governance platform for the Kaiela Institute, that will allow its Indigenous researchers to hold, control, and process data in the interests of better service delivery to their communities.