Skip to Content

How a Smart Watch Can Predict Your Happiness Levels

Happiness is an elusive state of mind that many people aim to maximize. Now researchers have found a way to predict happiness levels using smart watch data.

One of the more important challenges of 21st-century living is figuring out how to be happy. There is no shortage of advice. Aristotle wrote that “happiness is a state of activity.” And one team of researchers found that it is possible to increase happiness levels by surrounding yourself with people who are happy. Indeed, each happy individual in your life reportedly increases your happiness by about 9 percent.

But the science of happiness is hindered by a significant measurement problem. How can we measure happiness levels accurately and then use that data to predict when and how a person will be happy in the future?

Today we get an answer of sorts, thanks to the work of Pascal Budner and pals at the Massachusetts Institute of Technology in Cambridge. These guys have found a way to use a smart watch to measure and predict happiness.

The technology involved is a Pebble smart watch connected to an Android smartphone, each running an app that collects and then displays data. The watch collects data such as heart rate and activity levels. The smartphone app enables users to report how happy and active they feel, via a “Happimeter” that suggests a user’s mood and allows the individual to change it if it is wrong.

The Happimeter’s suggestions are based on psychologists’ traditional view of happiness as a parameter with two dimensions: arousal and valence. Arousal reflects readiness to act or activity level and is associated with being more alert than usual and having a higher blood pressure or heart rate. The team measures arousal on a scale of not active, active, or very active. Valence is a measure of the user’s level of happiness: feeling very pleasant, pleasant, or unpleasant.

That produces a two-dimensional space in which users can be in any one of nine different states. For example, being very active and feeling unpleasant is the state of being angry, whereas feeling very pleasant and not active is the state of relaxation.

Users are prompted to choose a state four times every day, but they can also choose to input a state at any time. In addition, the apps record external factors such as the user’s location, day of the week, time, and weather conditions.

Budner and his collaborators recruited 60 people to wear the smart watch over a two-month period in 2017 and to enter their happiness data during this time. The participants included graduate students, researchers, faculty members, consultants, and business industry leaders, ranging in age from 22 to 59.  

By the end of the experiment, the team had gathered almost 17,000 pieces of data, getting an overall picture of people’s moods. Over the course of the two months, almost 80 percent of mood inputs indicated that participants felt very pleasant, with only 3 percent of participants feeling unpleasant. Only 16 percent felt very active, with 26 percent saying they felt not active.

There is more to be gleaned from this data. Budner and his team use a form of machine learning to find patterns in heart rate, location, weather conditions, and so on, that can predict how happy a user will be.

The researchers claim the prediction rate is good. “We achieve prediction accuracy of up to 94 percent,” they say.

Some pieces of data are significantly more predictive of happiness than others. “We found that weather and movement between locations are highly predictive, whereas body measures such as heart rate have lower predictive power,” say the researchers.

That suggests that smart watch data could be hugely useful in mapping happiness in the general population. It might also help people increase their happiness levels.

Of course, there are some caveats to keep in mind. The study included only 60 people—a relatively small number. What’s more, those people might reflect a selection bias because they were all interested in happiness research.

Budner and his colleagues are well aware of those limitations and hope to address them in the future with a bigger study carried out with randomly selected individuals. “Nevertheless,” they say, “we think that we have introduced a novel system for tracking and increasing individual happiness.”

Aristotle would surely be thrilled.

Ref: arxiv.org/abs/1711.06134 : “Making you happy makes me happy” Measuring Individual Mood with Smartwatches

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

Google’s Gemini is now in everything. Here’s how you can try it out.

Gmail, Docs, and more will now come with Gemini baked in. But Europeans will have to wait before they can download the app.

This baby with a head camera helped teach an AI how kids learn language

A neural network trained on the experiences of a single young child managed to learn one of the core components of language: how to match words to the objects they represent.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.