Skip to main content

We use necessary cookies that allow our site to work. We also set optional cookies that help us improve our website. For more information about the types of cookies we use, visit our Cookies policy.

Cookie settings

How we work with partners

We’re committed to collaborating with research leaders to extract impactful scientific insights from our data. Our aim is to use cutting-edge approaches to improve our services and benefit the wider sector. We’re building partnerships across fields such as mental health, psychology, psychiatry, neuroscience, data science, artificial intelligence, linguistics, and public engagement.

We believe breakthroughs happen when researchers from different disciplines collaborate, especially in mental health research involving large datasets that require computational expertise. That's why we’re focused on fostering cross-disciplinary partnerships as our work evolves.

We currently partner with the Institute of Global Health Innovation (IGHI) at Imperial College London, as well as Imperial’s EPSRC Centre for Mathematics of Precision Healthcare. We're expanding these partnerships with institutions and researchers in multiple fields.

“The exciting partnership between the Institute of Global Health Innovation and Mental Health Innovations provides a unique opportunity to identify trends and harness the power of these digital tools to help shape the provision of these critical services.”

Professor the Lord Ara Darzi

Co-Director, Institute of Global Health Innovation
Imperial College London.jpg

Since launching Shout in 2019, we’ve expanded our academic partnership with the IGHI, led by Lord Ara Darzi. The partnership now also includes Imperial’s EPSRC Centre for Mathematics of Precision Healthcare. Several ongoing projects focus on using Natural Language Processing and machine learning, including deep learning, to analyse Shout 85258 conversations at scale. These cutting-edge methods are crucial for understanding our large dataset of hundreds of thousands of text-based conversations.

Early results show that these approaches can accurately identify conversation topics (e.g., suicide, self-harm, anxiety), texter demographics (e.g., age, gender) and conversation stages (e.g., rapport-building, problem-solving). This helps us better understand who uses Shout and their reasons for doing so.

Building on this, we’re exploring how deep neural networks predict these conversation features and what it reveals about texters' mental health.

We’re committed to publishing our findings in peer-reviewed journals and sharing them in accessible formats. With our growing dataset, we’re expanding academic partnerships to bring even more expertise to our work in understanding mental health.

Hands on phone.png

Explore more