Here's what your friend circle can say about your health
| Jun 19, 2019, 11:17 IST
Do you have a strong friend circle? If so, then you're lucky. A study has now found that the strength of one's friend circle can be more effective in determining how healthy they are than a Fitbit can predict. The study claims that you should look at how close you are to your friends if you want to determine how healthy you are. The researchers were trying to figure out how social networks affected the state of health, happiness and stress.
“What we found was the social network structure provides a significant improvement in predictability of wellness states of an individual over just using the data derived from wearables, like the number of steps or heart rate,” said the study lead author Nitesh V. Chawla. The researchers asked participants to wear a Fitbit so that they could measure their health behaviour data which included steps, sleep, exercise, heart rate etc. The participants were also asked to complete surveys about their state of happiness, stress and positivity.
The researchers then analysed the data from the Fitbit using machine learning while also assessing the survey data provided by the participants. The study was able to find a strong connection between heart rate, number of steps and level of activity. They were also able to determine that this combined study helped the machine get better results. So, when social network assessments were teamed with machine learning, the results were a lot clearer.
When the survey from participants was teamed with data from the Fitbit, the machine was able to achieve a 65 percent improvement in predicting happiness, 54 percent improvement in predicting one’s self-assessed health prediction, 55 percent improvement in predicting positive attitude, and 38 percent improvement in predicting success.
“This study asserts that without social network information, we only have an incomplete view of an individual’s wellness state, and to be fully predictive or to be able to derive interventions, it is critical to be aware of the social network structural features as well,” Chawla said.
“What we found was the social network structure provides a significant improvement in predictability of wellness states of an individual over just using the data derived from wearables, like the number of steps or heart rate,” said the study lead author Nitesh V. Chawla. The researchers asked participants to wear a Fitbit so that they could measure their health behaviour data which included steps, sleep, exercise, heart rate etc. The participants were also asked to complete surveys about their state of happiness, stress and positivity.
The researchers then analysed the data from the Fitbit using machine learning while also assessing the survey data provided by the participants. The study was able to find a strong connection between heart rate, number of steps and level of activity. They were also able to determine that this combined study helped the machine get better results. So, when social network assessments were teamed with machine learning, the results were a lot clearer.
When the survey from participants was teamed with data from the Fitbit, the machine was able to achieve a 65 percent improvement in predicting happiness, 54 percent improvement in predicting one’s self-assessed health prediction, 55 percent improvement in predicting positive attitude, and 38 percent improvement in predicting success.
“This study asserts that without social network information, we only have an incomplete view of an individual’s wellness state, and to be fully predictive or to be able to derive interventions, it is critical to be aware of the social network structural features as well,” Chawla said.