Resources for Researchers

Research Spotlight

Zita Oravecz

Cultivating Kindness through Computation

Posted 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.


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.”


Related Posts