Dr. Robert Morris chats with #SPSM about Koko, 3/19/17, 3pCT.
What is Koko, what is an “empathy layer,” and what does it have to do with suicide prevention? Well, you might want to read this Verge article for starters…
Watch us LIVE here:
Dr. Robert Morris is co-founder of Koko, a social network for mental health and emotional well-being.
Robert earned his AB in psychology from Princeton University, summa cum laude, and his master’s and PhD in media arts and sciences from the Massachusetts Institute of Technology.
His interests lie at the intersection of crowdsourcing, artificial intelligence, and digital interventions for mental health. He is an award winning designer and his work has been featured in Wired, NPR, Fast Company, and the The Huffington Post, among others.
SPSM guest expert Dr. Glen Coppersmith chats with us about uses and limitations of algorithms in predicting suicide attempts and death, 3/12/17 9pCT.
There’s been a lot of conversation lately about the potential of data science to predict suicide attempts and deaths. Experts differ on their opinions about the relative promise and merits of “artificial intelligence,” “machine learning,” and “algorithms” in suicide prevention.
SPSM will be orienting you to the basic issues underlying these concepts and application, so that you can evaluate different approaches for yourself.
Watch us LIVE here:
Dr. Meredith Gould joins #SPSM to chat about the relationship between suicide and spirituality, 3/5/17, 9pCT.
SPSM has never shied away from controversial topics (this is a weekly chat about suicide, after all). We’ll be discussing how one’s spiritual orientation might impact one’s view of suicide, and perhaps even how one uses social media in the aftermath or an attempt or death.
Watch us LIVE here:
Meredith Gould, PhD is a sociologist, digital communications consultant, online community manager, and longtime spiritual seeker. She’s an award-winning author of eleven books, including Desperately Seeking Spirituality. An updated edition of Deliberate Acts of Kindness: A Guide to Service as a Spiritual Practice will be available mid-March 2017. Dr. Gould is internationally known for her passionate advocacy of using digital tools for ministry and to encourage practical spirituality in daily life. A Platinum Fellow of the Mayo Clinic Social Media Health Network, she has also been involved with health, wellness, and healthcare education for decades. For more information visit: www.meredithgould.com.
#SPSM will be discussing our suicide prevention manifesto, 2/26/17, 9pCT.
What’s our manifesto, and why do one now?
SPSM has always had a point of view. We aim to use social media to have an expert to expert conversation about suicide prevention, social media, digital technology, and innovation…at the speed of technology and innovation, and not years behind it (the pre-SPSM speed of traditional expert to expert media in suicide prevention).
This was a bold undertaking…and in the last four years we feel our community is living this mission, and having an impact on accelerating and elevating the conversation on suicide prevention. In the meantime, our community has learned a few things, and is starting to crystallize a clear point of view about a possible future free of the blight of suicide, along with the challenges that must be undertaken to get there. This is *our* “suicide prevention moonshot.”
Here is our SPSM Manifesto
- Suicide is an enormous, global blight on humanity, and years of doing what we’ve been doing has not moved the needle on this problem in a powerful way. It’s time for radical solutions.
- “Radical solutions” will require a passionate, unapologetic quest for the resources (financial, institutional, political, and technical) to address this problem at scale.
- “Radical solutions” will require “suicidologists” to reach out and collaborate effectively with people in a number of science, technology, and media disciplines we’ve never worked with before.
- Because “radical solutions” will inevitably require use of “breakthrough technology” to address suicide at the scale of the problem, it is likely we will have to build things that do not yet exist, and we probably do not know, at this moment in time, what that is. We need to start dreaming big, taking risks, and proposing designs for suicide prevention at the scale of the problem. Then we need to start doing what it takes to actually attempt these designs, with a focus on tracking outcomes.
- We must become unattached to suicide prevention “solutions” that do not deliver results at scale. This will require a real realignment of motivations.
- Because we will be trying radical, multidisciplinary solutions to suicide prevention we need to solve the research and development process problems that consistently interfere with innovation at scale.
- Ethics writing, standards/practices benchmarks, and policy work needs to be funded and incentivized to keep pace with innovation. Without these important system elements, no innovation could be responsibly implemented.
Watch us nail our theses to the front door of YouTube, LIVE:
SPSMer chat about suicide risk assessment apps, 2/19/17, 9pCT.
In the years since SPSM started (we can’t believe we are writing this sentence) there has been an explosion of app development in the suicide prevention space. And, interestingly enough, there has been very little scientific review for this. There has been an very interesting review of these, and you should read it, here.
And, in recent months, there is even one digital tool (when combined with a blood test) that developers suggest may be able to predict your likelihood of suicide risk with high accuracy.
One area of particular controversy are apps that propose to identify your level of suicide risk. Given that assigning “low/medium/high” risk levels is a somewhat common clinical activity, that also has some controversial empiric basis, and the possible implications of having a digital tool that does this, SPSM will be discussing the implications and issues surrounding these apps.
Watch us LIVE here:
SPSM chats about supporting social media communities that are surviving a suicide, 2/12/17, 9pCT.
As social media plays an increasingly larger role in creating community and support for everyone (including suicide attempt survivors) there are likely to be social media-based communities that will experience suicide losses, and at the same time consist of many members with lived experience of suicide attempt and risk.
Responding to a suicide loss sensitively, and effectively, however may not have “hard and fast rules” or one “right way” for influencers or group members to react. SPSM alum, Dese’Rae Stage joins SPSM to discuss her experience and wisdom in this area.
Watch the conversation LIVE here, and participate in the twitter chat at hashtag #SPSM:
Dr. Dirk Hovy chats with #SPSM about the important differences between predictive versus explanatory models (from a data science perspective), and we’ll discuss how this applies to suicidology, 2/5/17, at a special time, 2pCT.
Why is this important? Well, it turns out that explanatory models are focused on explaining the causes of a phenomena (identifying risk factors, for example). Predictive models just predict that phenomena. A model that *explains* something may not necessarily be good at *predicting* it. And, when it comes to suicide prevention this is a big deal. These models are often confused, and actually use different kinds of statistical modeling.
Explanatory models on suicide, such as Joiner’s Interpersonal Theory, or other models that aim to identify risk factors have never really been successful at predicting a suicide. However, we really haven’t taken good advantage of data science and possible predictive modeling. If we still struggle with the math for identifying who is likely to die by suicide, perhaps it’s time to try a different approach. Let’s chat about this! For more reading about applications of this approach in psychology and suicide prevention, check out these articles:
You can watch Dr. Hovy LIVE here:
Dr. Hovey works in Natural Language Processing (NLP), a subfield of artificial intelligence. His research focuses on computational sociolinguistics, i.e., the intersection of sociolinguistics and statistical natural language processing (NLP). The goal of his research is to integrate sociolinguistic knowledge into NLP models. He uses large-scale statistics to detect and model the interaction between people’s demographic profile and their language use (see here or here). He is also interested in semantics (modeling what words mean in context), and non-standard language. He works as an associate professor at the computer science department (DIKU) at the University of Copenhagen.