Skip to content

Local Chapter project

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

NLP
Start date
October 1, 2022
Finish date
October 29, 2022
Project status
completed
Natural Language Processing: Predicting Self-Harm in London’s Young Adult Population

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

  1. 1

    Week 1

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

  2. 2

    Week 2

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

  3. 3

    Week 3

    -ID Sentiment Analysis Models - Fine Tune & compare models

  4. 4

    Week 4

    -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.

Get involved

What to expect from a Local Chapter project

First project

  • Welcomes beginners and experienced practitioners.
  • Focuses on education and collaborative delivery.
  • Produces open-source project work.

Benefits

  • Address a significant real-world problem with your skills.
  • Build your project portfolio.
  • Demonstrate your work to organizations and project partners.

Requirements

  • Working English communication.
  • A learning mindset.
  • Commitment to collaborative project work.

This challenge is hosted by

No public hosting chapter is linked to this project.