How we can use Twitter and Facebook for predicting mental illnesses and provide intervention.
“17% of adults aged 18-70 in the USA reported being lonely” (Sharath et. al.). In the age of social media, the “social sciences have entered the age of data science” (Schwartz et. al.). We see the effects of what too much internet can do to a person. Too much use of social media can cause us to behave more anxiously and become depressed. More broadly speaking, our cell phones have become conduits for the degradation of interpersonal relationships. However, the negative consequences of these inventions can potentially be reversed using dynamic language analysis of social media profiles.
What We Can Predict
Scholars have researched in depth the extent that social media can predict. We can track how our moods change over time (Golder and Macy). Among other pieces of information, we can accurately predict age, gender, and personality (Schwartz et. al.). We can even use Google search queries to predict epidemics weeks before CDC data confirms it (Ginsberg et. al.). So, what does this mean for the future of social media?
It means that we can finally take the data that social media companies have been using to run invasive ads to help people and intervene in a friendly way to help people rather than use them. This would most likely come in the form of a service that you would pay monthly for and give the software service access to your social media profiles. This would then allow the software to use structured modeling and differential language analysis to accurately predict what someone’s personality is like and how to best help them in reaching omni congruency with their goals. One study found that Twitter could “be used to accurately predict rates of excessive alcohol consumption” (Curtis et. al.). The possibilities are seemingly endless when we allow our dictations to be analyzed in the name of mental health.
Check out these programs for more information:
A World Where We Know Who We Are
A world where we get notified of behavioral patterns would allow us to seek out person to person mental health more objectively. We can make timelines of events in life and how those events affected our mental health which would give therapists a much more effective way to tackle traumas. If we could identify which events caused a change in mood or behavior, we could start scaling therapy and making it more effective. One of the primary issues with therapy is when you feel like you are going in circles and not making any progress. By extending the information provided to the therapist outside their office, we can give a wider gamut of issues to analyze and work on. Continue to think differently.
- Brenda Curtis, Salvatore Giorgi, Anneke E K Buffone, Lyle H Ungar, Robert D Ashford, Jessie Hemmons, . . . H Andrew Schwartz. (2018). Can Twitter be used to predict county excessive alcohol consumption rates? PLoS ONE, 13(4), E0194290.
- Golder, S., & Macy, M. (2011). Diurnal and Seasonal Mood Vary with Work, Sleep, and Daylength Across Diverse Cultures. Science (Washington), 333(6051), 1878-1881.
- Jeremy Ginsberg, Matthew H. Mohebbi, Rajan S. Patel, Lynnette Brammer, Mark S. Smolinski, & Larry Brilliant. (2009). Detecting influenza epidemics using search engine query data. Nature, 457(7232), 1012-104.
- Guntuku, S., Schneider, R., Pelullo, A., Young, J., Wong, V., Ungar, L., . . . Merchant, R. (2019). Studying expressions of loneliness in individuals using twitter: An observational study. BMJ Open, 9(11), E030355.
- Schwartz, H., Eichstaedt, J., Kern, M., Dziurzynski, L., Ramones, S., Agrawal, M., . . . Preis, T. (2013). Personality, Gender, and Age in the Language of Social Media: The Open-Vocabulary Approach. PLoS ONE, 8(9), E73791.