Flip | Devpost

Inspiration

Suicide hurts.

Beyond being the third-leading cause of death in young populations, suicide rates across the lifespan have risen 25% in the past seventeen years. This upswing in suicidality has been paralleled by a steady increase in how negative information is portrayed by the media industry. Specifically, large-scale spikes in suicide rates have been observed following prominent suicides events (such as those involving public figures), and localized swells in suicides are known to occur at the community level in a similar manner. This kind of social contagion capitalizes on information carried through social media platforms, webpages, and many other sources. Existing solutions want to block this content; we want to talk about it. Drawing inspiration from reappraisal and reattribution theory, as well as powerful machine learning technology, we're excited to introduce Flip, a dynamic browser extension aimed at changing this narrative.

What it does

Flip works by flagging web content that contains information known to support social contagion effects. Once this content has been identified, Flip uses natural language processing to characterize its semantic makeup and find relevant articles that offer a more productive take on the same issue. Finally, Flip presents these alternative options in the form of a browser notification, suggesting a way to flip the script on how we talk about suicide.

How we built it

Our team started by writing scripts to parse and flag web content that could then be sent to Google Cloud for linguistic analysis. Next, Google Cloud's output is fed into a semantic similarity algorithm to identify related articles from a curated database, and the most similar alternative option is presented to the user through a browser extension interface.

What's next for Flip

We're excited to continue working on this project by incorporating additional features that can cater to both individual users and larger institutions. Our team is also looking forward to applying our framework to content creators themselves, thereby allowing for early production-side interventions and a potentially greater impact.

Thanks for checking us out!