Cultivating Kindness through ComputationPosted on October 5, 2017
Zita Oravecz, ICS Co-hire
Most smartphone owners use apps to perform mundane tasks such as checking Facebook or staying on top of emails. As useful as these apps can be, they’re hardly life-changing.
What if an app could learn to predict your emotional state, help you avoid stress, and even make you a kinder and more mindful person?
Penn State’s Zita Oravecz, assistant professor in the Department of Human Development and Family Studies and a co-hire of the Institute for CyberScience (ICS), works to make this vision a reality. Oravecz and her colleagues are developing an app that can predict your psychological state using data from smartphones and wearable health monitors.
With this information, the app will send you texts to help improve your well-being. You might get a reminder to take a deep breath to fend off stress. Or you could receive an encouragement to pay someone a compliment — which would make both you and that person happier.
“I’m interested in making people feel better via technology,” said Oravecz. “So many people use smartphones nowadays. Why not harness those devices to improve their mental health?”
A major challenge is designing the app to learn how to predict the emotional states of different users. People vary greatly in how they regulate their emotions. You might get upset frequently but calm down quickly. Someone else might rarely get upset but, once angry, have trouble cooling off. For the app to be universally effective, it must adapt itself to these kinds of individual differences.
To create a predictive model of emotional states that learns a user’s quirks, Oravecz’s team uses data gathered from a study they conducted in the summer of 2016. Over four weeks, 52 study participants received text messages at six random times each day. These messages directed the participants to a brief survey with questions about their daily activities and experiences.
“We asked about a range of markers of well-being: how active you feel, how pleasant you feel, how much you feel loved, how much you slept last night, how many minutes you exercised yesterday,” explained Oravecz. “These questions arrived at random times while people were going on with their everyday life, which helped us capture the variations in their daily experiences.”
In addition to answering questions, participants wore digital health monitors, similar to a FitBit. These devices gathered physiological data from their wearers, including anxiety-induced perspiration levels, skin temperature, heart rate, and physical movement levels.
Oravecz combines this physiological data with the participants’ self-reports to build a mathematical model that can learn an individual’s unique predictors of well-being.
Because the model involves complex calculations using real-time streams of physiological data, it requires powerful computers. To run the model, Oravecz uses the ICS Advanced CyberInfrastructure (ICS-ACI), Penn State’s high-performance computing system containing 23,000 computer cores. The initial tests to build the framework of the model might take days or even weeks to run on a typical one- or two-core desktop computer, but by using many ICS-ACI cores in parallel, Oravecz can speed up the development process and aim to make her algorithms work in real-time.
“We need to make predictions quickly,” said Oravecz. “It doesn’t help someone if they are approaching a period of high stress and we tell them two weeks later to take a deep breath and calm down. We’re investigating ways to make the model less computationally intensive, but we’ll still need to rely on high-performance computing resources to deliver timely analysis on a wide scale.”
The next step in the project is to complement the psychological and physiological data with other information available from a smartphone, such as the user’s geolocation and activity level, and the noise level of the user’s surroundings. This additional information will help the app more accurately predict a person’s psychological state.
COMPASSION AND COMPUTATION
The ultimate goal of the app is to reduce stress and increase positive behavior. The messages to calm down when approaching a high level of negative emotion, combined with reminders to act positively, can significantly improve psychological health.
“Random acts of kindness — and other positive behaviors — are beneficial both for you and for the recipient,” said Oravecz. “The short reminders about acting kindly can increase users’ psychological well-being and help them flourish in their everyday lives.”
The desire to elevate people’s well-being through positive behavior has long motivated Oravecz. When she was a teenager, she noticed that many of her friends didn’t seem as happy as she was, even though they didn’t have any serious psychological problems. Her compassion for her friends’ unhappiness spurred her to study psychology.
She found that many in her field focused on returning people who had disorders to a “normal” mental state. But Oravecz wondered why there wasn’t more research on improving the lives of people who have no serious psychological problems, like her friends.
When she took a statistics course with someone who would turn out to be her favorite professor in college, she fell in love with math and statistics. She knew she could combine these passions with her drive to help others.
“I realized that not many people in my field get as excited about mathematical modeling and statistical programming as I do,” said Oravecz. “I think the field of psychology needs people with computational skills who also understand the human aspects of well-being. I love that I can use the power of computation to bring meaningful change to people’s lives.”
Oravecz wants to share her team’s model and methods with other researchers so they can perform their own research in reducing negative emotions and cultivating positivity.
“It would be great if other researchers learn about our approach and apply it in new ways,” said Oravecz. “That way the impact of our work can extend beyond the app and ultimately benefit many more people.”
- Featured Researcher: Nick Tusay
- Multi-institutional team to use AI to evaluate social, behavioral science claims
- NSF invests in cyberinfrastructure institute to harness cosmic data
- Center for Immersive Experiences set to debut, serving researchers and students
- Distant Suns, Distant Worlds
- CyberScience Seminar: Researcher to discuss how AI can help people avoid adverse drug interactions
- AI could offer warnings about serious side effects of drug-drug interactions
- Taking RTKI drugs during radiotherapy may not aid survival, worsens side effects
- Cost-effective cloud research computing options now available for researchers
- Costs of natural disasters are increasing at the high end
- Model helps choose wind farm locations, predicts output
- Virus may jump species through ‘rock-and-roll’ motion with receptors
- Researchers seek to revolutionize catalyst design with machine learning
- Resilient Resumes team places third in Nittany AI Challenge
- ‘AI in Action’: Machine learning may help scientists explore deep sleep
- Clickbait Secrets Exposed! Humans and AI team up to improve clickbait detection
- Focusing computational power for more accurate, efficient weather forecasts
- How many Earth-like planets are around sun-like stars?
- Professor receives NSF grant to model cell disorder in heart
- SMH! Brains trained on e-devices may struggle to understand scientific info
- Whole genome sequencing may help officials get a handle on disease outbreaks
- New tool could reduce security analysts’ workloads by automating data triage
- Careful analysis of volcano’s plumbing system may give tips on pending eruptions
- Reducing farm greenhouse gas emissions may plant the seed for a cooler planet
- Using artificial intelligence to detect discrimination
- Four ways scholars say we can cut the chances of nasty satellite data surprises
- Game theory shows why stigmatization may not make sense in modern society
- Older adults can serve communities as engines of everyday innovation
- Pig-Pen effect: Mixing skin oil and ozone can produce a personal pollution cloud
- Researchers find genes that could help create more resilient chickens
- Despite dire predictions, levels of social support remain steady in the U.S.
- For many, friends and family, not doctors, serve as a gateway to opioid misuse
- New algorithm may help people store more pictures, share videos faster
- Head named for Ken and Mary Alice Lindquist Department of Nuclear Engineering
- Scientific evidence boosts action for activists, decreases action for scientists
- People explore options, then selectively represent good options to make difficult decisions
- Map reveals that lynching extended far beyond the deep South
- Gravitational forces in protoplanetary disks push super-Earths close to stars
- Supercomputer cluster donation helps turn high school class into climate science research lab
- Believing machines can out-do people may fuel acceptance of self-driving cars
- People more likely to trust machines than humans with their private info
- IBM donates system to Penn State to advance AI research
- ICS Seed Grants to power projects that use AI, machine learning for common good
- Penn State Berks team advances to MVP Phase of Nittany AI Challenge
- Creepy computers or people partners? Working to make AI that enhances humanity
- Sky is clearing for using AI to probe weather variability
- ‘AI will see you now’: Panel to discuss the AI revolution in health and medicine
- Privacy law scholars must address potential for nasty satellite data surprises
- Researchers take aim at hackers trying to attack high-value AI models
- Girls, economically disadvantaged less likely to get parental urging to study computers
- Seed grants awarded to projects using Twitter data
- Researchers find features that shape mechanical force during protein synthesis
- A peek at living room decor suggests how decorations vary around the world
- Interactive websites may cause antismoking messages to backfire
- Changing how government assesses risk may ease fallout from extreme financial events
- Algorithm aims to alert consumers before they use illicit online pharmacies
- Scientists tap AI betting agents to help solve research reproducibility concerns
- Search engine could help researchers scour internet for privacy documents
- Deep learning may help doctors choose better lung cancer treatments