Update: “Your Data Team Should Be Your Company's Conscience” — Forbes Technology Council
Read More
CrisisTextLine

Natural Language Processing to Save More Lives

CrisisTextLine

Natural Language Processing to Save More Lives

Employees
Industry
Nonprofit Organization
Customer Since
2017
Case Studies

Crisis Text Line is a free, confidential, 24/7 text-based crisis intervention service that aims to mitigate crises by connecting people to counselors who are trained to cool down hot moments. The service specializes in short-term crisis intervention and has handled more than 70 million messages to date.

With more than 13,000 trained volunteer counselors, Crisis Text Line was looking for a way to use historical information to spot real-time crisis trends, improve the capacity of its volunteer network and reducing wait time for texters. With a high volume of unstructured data, it was challenging to quickly identify meaningful trends.

Using Periscope Data’s natural language processing and machine learning functionalities, the data science team identified issue trends through topic modeling and built a stack-ranking queue that prioritizes incoming messages based on severity. The team also sets up a self-service data environment that empowers non technical staff to access information to accelerate data-driven decision making across the organization.

Once identified and addressed these issues, Crisis Text Line saw a 10% overall boost in capacity during their highest volume periods, which allowed them to help even more people and only within five minutes of wait time (their operational goal). These initiatives will help Crisis Text Line meet their goals of doubling the number of counselors and 5x the number of conversations over the next two years.

A second phase of this project is to use Periscope Data to analyze conversations based on common keywords and tags to help forecast crisis trends and train counselors to have impactful conversations with texters.