How your social media data can become a ‘mental health X-ray’
In the future, you might voluntarily share your social media data with your psychiatrist to inform a more accurate diagnosis.
Stephen Johnson is a St. Louis-based writer whose work has been published by outlets including PBS Digital Studios, HuffPost, MSN, U.S. News & World Report, Eleven Magazine and The Missourian.
- About one in five people suffer from a psychiatric disorder, and many go years without treatment, if they receive it at all.
- In a new study, researchers developed machine-learning algorithms that analyzed the relationship between psychiatric disorders and Facebook messages.
- The algorithms were able to correctly predict the diagnosis of psychiatric disorders with statistical accuracy, suggesting digital tools may someday help clinicians identify mental illnesses in early stages.
For the 20 percent of people with a mental illness, early identification of the condition is key to getting the best treatment. But people often suffer symptoms for months, even years, without receiving clinical attention. Part of the problem is that psychiatrists have few tools to identify mental illnesses; they rely mostly on self-reported data and observations from friends and family.
The field is, in some ways, "stuck in the prehistoric age," according to Michael Birnbaum, MD, an assistant professor at the Feinstein Institutes for Medical Research and an attending physician at Zucker Hillside Hospital and Lenox Hill Hospital at Northwell Health.
But digital tools could help bring psychiatry into the modern age.
"It became apparent, in my work with young folks, that social media was ubiquitous," Dr. Birnbaum told Big Think. "So, we started to think about ways that we could potentially explore the utility of the internet and social media in the way we diagnose our patients and the care that we provide."
The results of a recent study, conducted by Feinstein Institutes researchers and IBM Research, suggest that social media activity can provide useful insights into who's at risk of developing mental illnesses like mood disorders and schizophrenia spectrum disorders.
Published in the journal njp Schizophrenia, the study used machine-learning algorithms to analyze millions of Facebook messages and images, which were provided voluntarily by participants, ages 15 to 35. The data represented participants' Facebook activity for 18 months prior to hospitalization.
...the health disparity between people with mental illness and those without is larger than disparities attributable to race, ethnicity, geography or socioeconomic status.
Identifying psychiatric disorders
The goal was for the algorithms to analyze patterns in these datasets, then predict which group participants belonged to: schizophrenia spectrum disorders (SSD), mood disorders (MD), or healthy volunteers (HV). The results were promising, showing that the algorithms correctly identified:
- The SDD group with an accuracy of 52% (chance was 33%)
- The MD group with an accuracy of 57% (chance was 37%)
- The HV group with an accuracy of 56% (chance was 29%)
The study also showed interesting differences in Facebook activity among the groups, such as:
- The SSD group was more likely to use language related to perception (hear, see, feel).
- The MD and SSD groups were far more likely to use swear words and anger-related language.
- The MD group was more likely to use language related to biological processes (blood, pain).
- The SSD group was more likely to express negative emotions, use second-person pronouns and write in netspeak (lol, btw, thx).
- The MD group was more likely to post photos containing more blues and less yellows.
These differences tended to become more apparent in the months before a patient was hospitalized. But even 18 months before hospitalization, the results revealed signals that hinted participants might be on the path to developing a psychiatric disorder. That's where these tools may someday help improve early-identification efforts.
"In psychiatry, we often get a snapshot of somebody's life, for 30 minutes once a month or so," he said. "There's the potential to get much greater granularity with some of these new assessment tools. Facebook, for example, can allow us to understand somebody's thoughts and behaviors in a more real-time, longitudinal fashion, as opposed to cross-sectional moments in time."
Dr. Birnbaum noted that everyone has a unique style of online behavior and that certain behavioral changes may contain clues about mental health.
"The way that we're understanding this is that everybody has a digital baseline, a way they typically act and behave on social media and the internet," he said. "So, ultimately here we would want to identify this baseline for each individual—a fingerprint—and then monitor for changes over time, and identify which changes are concerning, and which are not."
Using digital tools to better identify psychiatric conditions could someday reduce the number of people who suffer without treatment.
"There's an alarming gap between the number of people who experience mental illness and those who receive care," said Michael Dowling, president and CEO of Northwell Health. "It's especially troubling when you consider that the health disparity between people with mental illness and those without is larger than disparities attributable to race, ethnicity, geography or socioeconomic status."
A step toward the future of psychiatry
Credit: Jewel Samad/AFP via Getty Images
Although previous research has examined the relationship between online activity and psychiatric disorders, the new study is unique because it paired online behavior with clinically confirmed cases of psychiatric disorders.
"The vast majority of the data thus far has been extracted from anonymous, or semi-anonymous individuals online, without any real way to validate the diagnosis or confirm the authenticity of the symptoms," Dr. Birnbaum said.
But before clinicians can use these kinds of digital approaches, researchers have more work to do.
"I think that we need much larger datasets," Dr. Birnbaum said. "We need to repeat these findings. We need to better understand how demographic differences, like age, ethnicity and gender, can play a role."
Privacy is another consideration. Dr. Birnbaum emphasized that these kinds of approaches would only be conducted on a voluntary basis, and that the Facebook data used in the recent study was anonymized, and the algorithms examined only individual words, not the context or meaning of sentences.
"This isn't about surveillance, or that Facebook should somehow be monitoring us," Dr. Birnbaum said. "It's about giving the power to the patient. I imagine a world where patients could come into the doctor's office and express their concerns, but also provide some additional clinically meaningful information that they own."
Dr. Birnbaum said the long-term goal isn't for algorithms to make official diagnoses or replace physicians, but rather to serve as supplementary tools. He added that these tools would be used only for people seeking help or information about their risk of developing a psychiatric condition, or suffering a relapse.
"Hopefully one day, we'll be able to incorporate this and other information to inform what we do, the same way you go to a doctor and you get an X-ray or a blood test to inform the diagnosis," he said. "It doesn't make the diagnosis, but it informs the doctor. That is where psychiatry is heading, and hopefully this is a step in that direction."
A new paper reveals that the Voyager 1 spacecraft detected a constant hum coming from outside our Solar System.
Voyager 1, humanity's most faraway spacecraft, has detected an unusual "hum" coming from outside our solar system. Fourteen billion miles away from Earth, the Voyager's instruments picked up a droning sound that may be caused by plasma (ionized gas) in the vast emptiness of interstellar space.
Launched in 1977, the Voyager 1 space probe — along with its twin Voyager 2 — has been traveling farther and farther into space for over 44 years. It has now breached the edge of our solar system, exiting the heliosphere, the bubble-like region of space influenced by the sun. Now, the spacecraft is moving through the "interstellar medium," where it recorded the peculiar sound.
Stella Koch Ocker, a doctoral student in astronomy at Cornell University, discovered the sound in the data from the Voyager's Plasma Wave System (PWS), which measures electron density. Ocker called the drone coming from plasma shock waves "very faint and monotone," likely due to the narrow bandwidth of its frequency.
While they think the persistent background hum may be coming from interstellar gas, the researchers don't yet know what exactly is causing it. It might be produced by "thermally excited plasma oscillations and quasi-thermal noise."
The new paper from Ocker and her colleagues at Cornell University and the University of Iowa, published in Nature Astronomy, also proposes that this is not the last we'll hear of the strange noise. The scientists write that "the emission's persistence suggests that Voyager 1 may be able to continue tracking the interstellar plasma density in the absence of shock-generated plasma oscillation events."
Voyager Captures Sounds of Interstellar Space www.youtube.com
The researchers think the droning sound may hold clues to how interstellar space and the heliopause, which can be thought of as the solar's system border, may be affecting each other. When it first entered interstellar space, the PWS instrument reported disturbances in the gas caused by the sun. But in between such eruptions is where the researchers spotted the steady signature made by the near-vacuum.
Senior author James Cordes, a professor of astronomy at Cornell, compared the interstellar medium to "a quiet or gentle rain," adding that "in the case of a solar outburst, it's like detecting a lightning burst in a thunderstorm and then it's back to a gentle rain."
More data from Voyager over the next few years may hold crucial information to the origins of the hum. The findings are already remarkable considering the space probe is functioning on technology from the mid-1970s. The craft has about 70 kilobytes of computer memory. It also carries a Golden Record created by a committee chaired by the late Carl Sagan, who taught at Cornell University. The 12-inch gold-plated copper disk record is essentially a time capsule, meant to tell the story of Earthlings to extraterrestrials. It contains sounds and images that showcase the diversity of Earth's life and culture.
- Lawrence Kohlberg's experiments gave children a series of moral dilemmas to test how they differed in their responses across various ages.
- He identified three separate stages of moral development from the egoist to the principled person.
- Some people do not progress through all the stages of moral development, which means they will remain "morally undeveloped."
Has your sense of right and wrong changed over the years? Are there things that you see as acceptable today that you'd never dream of doing when you were younger? If you spend time around children, do you notice how starkly different their sense of morality is? How black and white, or egocentric, or oddly rational it can be?
These were questions that Lawrence Kohlberg asked, and his "stages of moral development" dominates a lot of moral psychology today.
The Heinz Dilemma
Kohlberg was curious to see how and why children differed in their ethical judgements, and so he gave roughly 60 children, across a variety of ages, a series of moral dilemmas. They were all given open-ended questions to explain their answers in order to minimize the risk of leading them to a certain response.
For instance, one of the better-known dilemmas involved an old man called Heinz who needed an expensive drug for his dying wife. Heinz only managed to raise half the required money, which the pharmacists wouldn't accept. Unable to afford it, he has only three options. What should he do?
(a) Not steal it because it's breaking the law.
(b) Steal it, and go to jail for breaking the law.
(c) Steal it, but be let off a prison sentence.
What option would you choose?
Stages of Moral Development
From the answers he got, Kohlberg identified three definite levels or stages of our moral development.
Pre-conventional stage. This is characterized by an ego-centric attitude that seeks pleasure and to prevent pain. The primary motivation is to avoid punishment or claim a reward. In this stage of moral development, "good" is defined as whatever is beneficial to oneself. "Bad" is the opposite. For instance, a young child might share their food with a younger sibling not from kindness or some altruistic impulse but because they know that they'll be praised by their parents (or, perhaps, have their food taken away from them).
In the pre-conventional stage, there is no inherent sense of right and wrong, per se, but rather "good" is associated with reward and "bad" is associated with punishment. At this stage, children are sort of like puppies.
If you spend time around children, do you notice how starkly different their sense of morality is? How black and white, or egocentric, or oddly rational it can be?
Conventional stage. This stage reflects a growing sense of social belonging and hence a higher regard for others. Approval and praise are seen as rewards, and behavior is calibrated to please others, obey the law, and promote the good of the family/tribe/nation. In the conventional stage, a person comes to see themselves as part of a community and that their actions have consequences.
Consequently, this stage is much more rule-focused and comes along with a desire to be seen as good. Image, reputation, and prestige matter the most in motivating good behavior — we want to fit into our community.
Post-conventional stage. In this final stage, there is much more self-reflection and moral reasoning, which gives people the capacity to challenge authority. Committing to principles is considered more important than blindly obeying fixed laws. Importantly, a person comes to understand the difference between what is "legal" and what is "right." Ideas such as justice and fairness start to mature. Laws or rules are no longer equated to morality but might be seen as imperfect manifestations of larger principles.
A lot of moral philosophy is only possible in the post-conventional stage. Theories like utilitarianism or Immanuel Kant's duty-focused ethics ask us to consider what's right or wrong in itself, not just because we get a reward or look good to others. Aristotle perhaps sums it up best when he wrote, "I have gained this from philosophy: that I do without being commanded what others do only from fear of the law."
How morally developed are you?
Kohlberg identified these stages as a developmental progression from early infancy all the way to adulthood, and they map almost perfectly onto Jean Piaget's psychology of child development. For instance, the pre-conventional stage usually lasts from birth to roughly nine years old, the conventional occurs mainly during adolescence, and the post-conventional goes into adulthood.
What's important to note, though, is that this is not a fatalistic timetable to which all humans adhere. Kohlberg thought, for instance, that some people never progress or mature. It's quite possible, maybe, for someone to have no actual moral compass at all (which is sometimes associated with psychopathy).
More commonly, though, we all know people who are resolutely bound to the conventional stage, where they care only for their image or others' judgment. Those who do not develop beyond this stage are usually stubbornly, even aggressively, strict in following the rules or the law. Prepubescent children can be positively authoritarian when it comes to obeying the rules of a board game, for instance.
So, what's your answer to the Heinz dilemma? Where do you fall on Kohlberg's moral development scale? Is he right to view it is a progressive, hierarchical maturing, where we have "better" and "worse" stages? Or could it be that as we grow older, we grow more immoral?
Dunbar's number is a popular estimate for the maximum size of social groups. But new research suggests that it's a fictitious number based on flimsy data and bad theory.
- A team of researchers recalculated Dunbar's number using his original methods and better data.
- Their estimates were as high as 520 and were stretched over a wide enough range as to be nearly useless.
- The authors suggest that the method used to calculate the number of friends a person can have is also theoretically unsound.
Since 1992, people have been talking about "Dunbar's number," the supposed upper limit of the number of people with whom a person can maintain stable social relationships. Named for British anthropologist Robin Dunbar, its value, rounded from 148 to 150, has permeated both professional and popular culture.
The Swedish taxation authority keeps offices under 150 people as a result of it, and the standard facilities of the W. L. Gore and Associates company are based around the concept. Dunbar's number was cited in Malcolm Gladwell's bestselling book Tipping Point, and it also has a fair amount of academic influence, the original paper having been cited 2,500 times.
It's also probably wrong.
Despite its fame, Dunbar's number has always been controversial. A new study out of Sweden and published in the journal Biology Letters suggests it might be both theoretically and empirically unsound.
Getting to 150
Less well known than the value of Dunbar's number is how he came up with it. The value of 150 is determined by looking at the ratio between the size of the neocortex in primates and the average size of groups they form. These ratios were then applied to data on the human brain, and the average value of roughly 150 relationships was determined.
The point of this study isn't to replace Dunbar's number but to dismiss the notion that such a number can be determined in the first place.
However, this number has always been the subject of debate. An alternative value based on empirical studies of American social groups is a much higher 291, nearly double that of Dunbar, and suggests that the median social network has 231 people in it. That value wasn't calculated by crunching other numbers; it kept coming up again and again when the authors of that study looked at the professional and social networks cultivated by different groups of people.
Yet, even in the face of critics and new studies, Dunbar's number always managed to hang on in popular and academic discourse. That is where this latest study comes in.
A new study with old methods but better data
In the new study, the researchers did similar calculations as Dunbar but with updated information on the size of monkey brains and social networks. While their average human group size was below Dunbar's estimate, the upper boundary of the 95 percent confidence interval ranged between 2 and 520 people depending on what methods were used. Nearly every method gave a range of possibilities with a maximum value higher than 150.
When the authors applied Dunbar's exact same methods from 1992 to their new data, they got an average group size of 69 people — but a 95% confidence interval between roughly 5 and 292. This is far too wide a range to be of any use.
Additionally, the authors discuss the flimsy nature of the theory behind Dunbar's number. Human brains often work differently than those of our nearest evolutionary cousins, as evidenced by our ability to create things like, "Stockholm, symphonies, and science." The idea that we would process social information exactly like other apes do is a bold and largely unsubstantiated claim.
They quote a study by Jan De Ruiter and their rejection of the idea that the ratio between monkey neocortex size and group composition can be carried over to humans:
"Dunbar's assumption that the evolution of human brain physiology corresponds with a limit in our capacity to maintain relationships ignores the cultural mechanisms, practices, and social structures that humans develop to counter potential deficiencies"
So, is there a new Dunbar number?
The point of this study isn't to replace Dunbar's number but to dismiss the notion that such a number can be determined in the first place. The authors go so far as to end their paper with:
"It is our hope, though perhaps futile, that this study will put an end to the use of 'Dunbar's number' within science and in popular media. 'Dunbar's number' is a concept with limited theoretical foundation lacking empirical support."
While this study may not be the death of Dunbar's number — after all, less empirically sound ideas have endured much longer — it may be the foundation for new attempts to determine how large our meaningful and stable social groups can be.
SMARTER FASTER trademarks owned by Freethink Media, Inc. All rights reserved.