Overview

Partnered with Cisco’s data science team to develop an AI-powered tool that identifies harmful language patterns in suicide-related media coverage. Research shows that articles containing certain language can trigger contagion effects among vulnerable individuals — this tool helps journalists and editors report responsibly.

Collaboration

Technical Approach

Built using machine learning and natural language processing to analyze article text in real-time, flagging language patterns that deviate from WHO-recommended reporting guidelines.

Publication

“Reducing suicide contagion effect by detecting sentences from media reports with explicit methods of suicide” Gerani S, Tissot R, Ying A, Redmon J, Rimando A, Hun R IJCAI 2021 Workshop on AI for Social Good

Read the paper (Harvard CRCS)

Recognition

This project was awarded the Data Science Award, presented by Andrew Ng.