Back to Projects

Team Name:

Eclectic Sheep Society


Team Members:


Evidence of Work

Untold Story

Project Info

Eclectic Sheep Society thumbnail

Team Name


Eclectic Sheep Society


Team Members


Rishi , Brad , AG , Brianna and 1 other member with an unpublished profile.

Project Description


Imgur

Problem Statement:

The untold personal stories of alcohol addiction in Australia lead to gaps in data, hindering a complete approach to tackle the problem.

The alcohol culture in Australia is deeply embedded, and the shame and judgment associated with addiction conceal the true extent of the problem. Often referred to as an "alcohol culture," drinking is woven into the fabric of society, and abstinence can be stigmatized. This complex relationship with alcohol leads to obscured statistics, making it challenging to understand the full scope of the issue. The available data often represents the aftermath of alcoholism rather than the personal experiences that might provide insight into the causes.

Our Solution:

Imgur

Untold Story is an innovative web-hosted platform using GenAI, a human-like machine that offers empathy without judgment. Users share their personal experiences with alcohol, and this information creates a newly formed database. By applying machine learning to this database, users can assess their risks, while health practitioners, researchers, and policymakers gain

App Features:

Chatbot:

The platform features an LLM chatbot pre-loaded with links from ABS and AIHW databases, as well as databases concerning alcohol-related health and mental health issues. Users can submit an alcohol-related query in natural language, which is sent to Amazon Kendra, connecting it to the relevant database. Context is then passed to Sagemaker, which uses its capabilities to return the answer to the user in natural language. Imgur Imgur

User Story:

The user can share their story about alcohol addiction, whether personal or about a loved one. A special filter ensures that the user's input is depersonalised, maintaining anonymity and protecting privacy. These individual stories, filled with vital insights into alcohol addiction, are added to a relational database. This innovative approach contributes to creating a comprehensive snapshot of Australian Alcohol addiction, blending personal experiences with a broader understanding. Imgur

Interactive Snapshot into Australian Alcohol Addiction:

The platform includes a page where users can view a snapshot of the current state of alcoholism addiction in Australia by answering quiz questions. Imgur

Live Statistics:

Users can view live graphs correlating to their own age groups and genders by selecting options from the drop-down menus. These statistics showcase the average amount of alcohol consumed, the favourite types of alcohol, and the most common triggers. By presenting this information in an accessible and personalised way, users may feel connected to a digital community they didn't know about, and possibly gain a better understanding of where they stand in terms of the data. It's another way this platform is innovating user engagement with real-world issues.Imgur

Scalability:

Alcohol is just the start. The platform's design and structure allow for scalability to shine a light into other grey areas of under-reported and misrepresented data.

Data Governance:

Keeping the data within Australia is a priority for the platform, ensuring that the insights and information gathered are utilised to make Australia a better place. Rather than outsourcing or relying on overseas data handling, the platform is committed to national data governance.


#ai #health #ml #predictive learning #addiction #genai #predictivelearning #open data #wellbeing #community

Data Story


The data landscape on alcohol addiction in Australia, gathered from sources like Data.gov.au, AIHW, ABS, and others, has long been constrained by its focus on external indicators such as hospital admissions, doctor visits, and law enforcement reports. While the National Health Survey did attempt to collect more personal information like height, weight, BMI, and pre-existing health conditions, its sample size of just 11,000 is glaringly inadequate for a country with a population of over 25 million. This limitation means that the dataset tends to surface only in the direst of circumstances – late stages of liver cancer, fatalities, and other tragic outcomes.
What's been missing from this data story is the voice of the individual, the firsthand experience of those grappling with addiction. This absence not only hampers our ability to develop accurate predictive models but also underscores a broader failure to understand and engage with addiction at its roots.
The "Untold Story" initiative recognises the need to shift this paradigm. By fostering an environment where self-reporting is encouraged and anonymity is maintained, we can begin to gather data that reflects the true complexity and humanity of alcohol addiction. This richer dataset will not only enhance our predictive capabilities through machine learning but also support a more compassionate and informed approach to addiction policy and treatment.

Anonymity, Privacy, and Security:

The user will be authenticated through Firebase using only an email and password, with email verification completed via a link sent to the user's address. This measure is implemented to ensure data integrity. A data usage statement and user consent is implemented in a separate page, advising users that the data will not identify them in any way and will only be used for the purposes of research. It will be provided in a summarised format to policymakers and health practitioners. The filter for the user story and the chatbot hasn't been put in place yet but will be a part of Gen2. The user story submission will go live once the cyber security measures are implemented to sanitise user input against malicious injections. These steps not only maintain a secure and trustworthy platform but also ensure transparency with users regarding how their information is used, respecting privacy and fostering trust. Imgur

About Us: Eclectic Sheep Society

The Eclectic Sheep Society is more than just a team; it's a vibrant community of energetic, highly motivated individuals who crave positive change in the world. Hailing from all walks of life and spanning across three Australian states and India, we truly embody the definition of eclectic.
Our journey began at university, where our diverse interests in Data Science, Software Development, Web Design, AI and Machine Learning, Cyber Security, and Criminology brought us together. What unites us is not just our passion for technology but our shared values and life experiences.
Many of us are mature-age students who re-discovered our love for tech later in life. This blend of life wisdom and technical expertise sets us apart and fuels our creativity.
At the heart of our mission is the well-being and cohesiveness of our team members. Inclusion, respect, and the freedom to be heard are not just words to us; they are our guiding principles. We build projects inspired by our personal life paths and experiences. Winning is great, but for us, the true victory lies in the learning and the growth we achieve together.Imgur

References

https://docs.google.com/document/d/1T1EISKLzWRbGmhVbECqe38qc3kVv240qTIoU6YId-oo/edit


Evidence of Work

Video

Homepage

Project Image

Team DataSets

Alcohol Consumption 2020-21 Financial Year

Description of Use Used for visualisation and for LLM

Data Set

Types of Alcohol usage Across the Years

Description of Use Used for Interactive Visualisation

Data Set

Snapshot into Alcoholism Addiction within the indigenous communities

Description of Use Loaded into the Amazon Kendra for LLM

Data Set

Ambulance Attendance Alcohol Related

Description of Use Loaded into Amazon Kendra for LLM

Data Set

Alcohol and Other Drug Treatment Services

Description of Use Purposes of Visualisation, and providing information to the user

Data Set

Challenge Entries

Best Creative Use of Data in Response to ESG

How can you showcase data in a creative manner to respond to ESG challenges? How can we present and visualise data to stimulate conversation and promote change?

Eligibility: Must use a least one Australian relevant dataset - combining datasets preferred.

Go to Challenge | 33 teams have entered this challenge.

Using machine learning and generative AI to improve health outcomes

How can machine learning or generative AI be used to help Australians to live longer, healthier, happier lives?

Eligibility: Any submission that uses machine learning or generative AI for the purpose of improving the health and wellbeing of Australians, or provides a use case for using machine learning or generative AI for improving the health and wellbeing of Australians.

Go to Challenge | 14 teams have entered this challenge.

Generative AI: Unleashing the Power of Open Data

Explore the potential of Generative AI in conjunction with Open Data to empower communities and foster positive social impact. This challenge invites participants to leverage Generative AI models to analyse and derive insights from Open Data sourced from government datasets. By combining the power of Generative AI with the wealth of Open Data available, participants can create innovative solutions that address real-world challenges and benefit communities.

Eligibility: Ethical use of a generative AI in your project and at least one Australian or New Zealand data set.

Go to Challenge | 29 teams have entered this challenge.