Do as I tweet, not as I do: comparing physical activity data between fitness tweets and Healthy People 2020

The goal of this research was to compare the self-reported estimates of daily physical-activity data provided to the Healthy People 2020 research team via a telephone survey to the mobile fitness app real-time reporting of physical activity using Twitter.

The fitness tweet classification data set was collected from mobile fitness app users who shared their physical activity over Twitter. Over 184 days, 2,856,534 tweets were collected in 23 different languages. However, for the purposes of this study, only the English-language tweets were analysed, resulting in a total of 1,982,653 tweets by 165,768 unique users. The information and data gleaned from this data set, which reflected 184 days of continuous data collection, were compared to the results from the Healthy People survey, which were compiled using telephone interviews of self-reported physical activity from the previous week.

The data collected from fitness tweets using the five mobile fitness apps suggest lower percentages of people achieving both the 150 to 300 and 300+ min levels than is reflected in the Healthy People survey results. While employing Twitter and other social media as data-collection tools could help researchers obtain information that users might not remember or be willing to disclose face-to-face or over the telephone, further research is needed to determine the cause of the lower percentages found in this study.

Though some challenges remain in using social media like Twitter to glean physical-activity data from the public, this approach holds promise for yielding valuable information and improving outcomes.