Covering Disruptive Technology Powering Business in The Digital Age

Home > Archives > News > A Big Data Friend In Need
A Big Data Friend In Need
August 9, 2016 News

Having someone to be there during a trying time might be just the job for …. Big Data. How? Since 2013 Crisis Text Line have been successfully using big data and machine learning to address texters who are in need by feeding the messages into their system and having it bring up the ones needing immediate attention, therefore getting help to where help is needed urgently.

Born out of DoSomething,org, the largest organisation for young people and social change, Crisis Text Line was the brain child of Nancy Lublin. They were getting dozens of text messages from members for personal help. Which was where the inspiration to start Crisis Text Line came from.

Since its inception, they have received 20 over million messages. Out of the 50k texters a month, 30% make up high level messages about depression and suicide. They average 8 active rescue calls a day with 1,541 trained Crisis Counselors (and growing).

Being the largest mental health data set in the world, they are able to leverage off the technology to create a faster, better and cheaper service. Although their data collection and retrieval is using the latest technology, they have a human-first approach to their texters.

There are three levels of research starting from the conversation, actor and message levels – with each level increasing in detail. The conversation level dataset will allow researchers to explore questions such as, “crisis issues occur most on holidays, such as Christmas and Valentine’s Day?” and “how are bullying and depression related?” The actor level dataset will allow researchers to answer questions like “For a texter experiencing depression, how do issues fluctuate over time?” The message level, will allow researchers to dive deep into interactions, and uncover patterns such as how texters struggling with self-harm describe their experience.

In the beginning, counsellors would address in order of appearance. Then they decided to look at severity just like an emergency room. That was where the power of big data really shone through. By feeding every SMS into a database with computer algorithms in place to make sense of phrases and trends, the machine learning is then able to recognise the new trends and bring up priority cases such as suicide or depression texts.

Nancy Lublin, is making good on a promise she made publicly from the start that the data itself could save lives. “From day one, this was the goal. To help people one-on-one and leverage the data for smart system change on a broad scale, I’m pretty darn excited that we’re making it happen.”

John Wilbanks, Chief Commons Officer, Sage Bionetworks says, “Crisis Text Line is working to share data with empathy and compassion. I’ve been engaged with this application over the last year, and it meets or exceeds the way that most leading research institutions share data.”

Robert J. Levine, MD. Professor of Internal Medicine, Chair, Executive Committee, Center for Bioethics, Yale University adds “In harmony with the nation’s leading research ethicists, we have created an application that follows best practices for sharing the results of mental health research.”

With more than 7 billion mobile phone users in the world, big data will be able to focus on the individual as well as drive resources to where its needed most in crisis. Using a cell tower as an approximate location, information on call details and SMS records can be collected anonymously, encrypted and aggregated to be used as a sensor to monitor activity and save lives.