Natural Language Processing: Predicting Self-Harm in London’s Young Adult Population

Start Date: October 1, 2022 | 4 years ago

Challenge Background

Self-harm in Children and Young Persons (CYP) aged between 10-24 increased during the Covid pandemic (ONS 2022). More broadly the incidence of mental health conditions in the CYP population has increased from 1-in-9 pre-pandemic to 1-in-6. As such the most recent Global Burden of Disease study published in the Lancet (2022) recommended urgent policy action to address this crisis. Data indicates young girls/adults are particularly vulnerable. A 2018-20 study of ambulance data in wales indicates only 63% of ambulance call-outs related to mental health conditions actually presented to an A&E department. Only 23% of those presenting to A&E were actually admitted. Does this highlight the tip of the iceberg?

Project Timeline

– Brainstorm social media sources, e.g. - Hashtag, keyword extraction etc - map: London Inner Boroughs

– Exploratory Data Analysis(Topic Modelling) -text data preprocessing

-ID Sentiment Analysis Models - Fine Tune & compare models

-Topic Classification model based on Self-Harm Injuries.

What you'll learn

Project Output Project team envisage a set of time-series sentiment scores by topic where the central theme is eating disorder mapped to Central and Northwest London ambulance call-out data for self-harm/injury.

First Omdena Local Chapter Project?

Beginner-friendly, but also welcomes experts

Education-focused

Duration: 4 to 8 weeks

Open-source

Your Benefits

Address a significant real-world problem with your skills

Build your project portfolio

Access paid projects (as an Omdena Top Talent)

Get hired at top organizations

Requirements

Good English

Suitable for AI/ Data Science beginners but also more senior collaborators

Learning mindset

Application Form

Application Closed.