Home > data science, hackathon, modeling, open source tools > Crisis Text Line: Using Data to Help Teens in Crisis

Crisis Text Line: Using Data to Help Teens in Crisis

November 16, 2013

This morning I’m helping out at a datadive event set up by DataKind (apologies to Aunt Pythia lovers).

The idea is that we’re analyzing metadata around a texting hotline for teens in crisis. We’re trying to see if we can use the information we have on these texts (timestamps, character length, topic – which is most often suicide – and outcome reported by both the texter and the counselor) to help the counselors improve their responses.

For example, right now counselors can be in up to 5 conversations at a time – is that too many? Can we figure that out from the data? Is there too much waiting between texts? Other questions are listed here.

Our “hackpad” is located here, and will hopefully be updated like a wiki with results and visuals from the exploration of our group. It looks like we have a pretty amazing group of nerds over here looking into this (mostly python users!), and I’m hopeful that we will be helping the good people at Crisis Text Line.

  1. November 16, 2013 at 10:30 pm

    Will Aunt Pythia be posting soon? We were so looking forward to reading her sage advice to the masses.


    • November 17, 2013 at 7:05 am

      Oh! That’s so sweet! Almost nobody seems to really read Aunt Pythia. It’s good to know she has a fan. Please do ask her a question, and feel free to recycle from this advice column, I would love to give my versions!



  2. Lisa
    November 17, 2013 at 12:58 pm

    If this metadata also includes location, would it be possible to analyze over a period (say, 2 years) the frequency of usage in different locales (I don’t know how detailed the dataset is that you are working with)?

    It would be interesting, because comparing that data (if possible) with recent IRS data regarding median income according to zip code would give a general sense of how frequent or infrequent the usage of teen crisis/suicide prevention is in impoverished areas versus high-income areas. Which I think would be pretty useful information, and helpful in that it would provide an idea of where mental health and wellness services for young people are needed most.


  3. a
    November 17, 2013 at 1:12 pm

    I read AP! In fact, when I realize it is Saturday a surge of dopamine gets released through my neurons and I head over to mathbabe.org. It is the highlight of my weekend. It is like Christmas coming every Saturday. It makes life worth living. (For the last two sentences, apologies to Mel Hochster). I came back today just to see if AP had returned. 😦

    P.S. What’s the data behind “almost nobody seems to read AP?” If it’s that not many people comment, it is because AP typically comes up with incisive and keen answers that can’t be topped and stand as the final word on the subject. (In fact, the entire draw for me to AP is to see mathbabe’s piercing analysis of topics besides finance and data). On rare occasions where AP might have overlooked something, people chime in. On the other hand, if the data is site traffic, well she rises on saturdays so we can’t compare it to a weekday.


    • November 17, 2013 at 1:16 pm

      Wow! Blushing!

      Yes it is the traffic and the relative lack of comments versus my time commitment in writing. But now I kinda feel like it’s all worth it.



  1. No trackbacks yet.
Comments are closed.
%d bloggers like this: