Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2019 May:2019:571-582.
doi: 10.1145/3308558.3313432.

Goal-setting And Achievement In Activity Tracking Apps: A Case Study Of MyFitnessPal

Mitchell L Gordon  1 , Tim Althoff  2 , Jure Leskovec  1
Affiliations

Goal-setting And Achievement In Activity Tracking Apps: A Case Study Of MyFitnessPal

Mitchell L Gordon et al. Proc Int World Wide Web Conf. 2019 May.

Abstract

Activity tracking apps often make use of goals as one of their core motivational tools. There are two critical components to this tool: setting a goal, and subsequently achieving that goal. Despite its crucial role in how a number of prominent self-tracking apps function, there has been relatively little investigation of the goal-setting and achievement aspects of self-tracking apps. Here we explore this issue, investigating a particular goal setting and achievement process that is extensive, recorded, and crucial for both the app and its users' success: weight loss goals in MyFitnessPal. We present a large-scale study of 1.4 million users and weight loss goals, allowing for an unprecedented detailed view of how people set and achieve their goals. We find that, even for difficult long-term goals, behavior within the first 7 days predicts those who ultimately achieve their goals, that is, those who lose at least as much weight as they set out to, and those who do not. For instance, high amounts of early weight loss, which some researchers have classified as unsustainable, leads to higher goal achievement rates. We also show that early food intake, self-monitoring motivation, and attitude towards the goal are important factors. We then show that we can use our findings to predict goal achievement with an accuracy of 79% ROC AUC just 7 days after a goal is set. Finally, we discuss how our findings could inform steps to improve goal achievement in self-tracking apps.

PubMed Disclaimer

Figures

Figure 1:
Figure 1:
Histogram of weight loss goals as a percent of initial weight. We see a somewhat skewed distribution (skewdness of −0.46), with a peak around 10% weight loss.
Figure 2:
Figure 2:
Weight loss goal as percent of current weight, by age. (A): Without stratification by BMI. We find a U-shaped curve in agreement with existing literature. The U is significantly deeper for women than for men. (B): With this stratification (results shown only for women), we now see that younger adults set the most ambitious goals, but get less ambitious up until the age of 30, from which point goals stay relatively consistent. Then, around 60, older adults set increasingly less ambitious goals. Error bars in all plots correspond to bootstrapped 95% confidence intervals (here, they are mostly too small to be visible).
Figure 3:
Figure 3:
Women set more ambitious goals than men; when controlling for BMI, women aim to lose approximately 5% more weight.
Figure 4:
Figure 4:
CDF of goal achievement, stratified by goal difficulty. X-axis indicates percent of goal achieved while y-axis indicates the portion of users who have achieved at least that amount of their goal. We find that across the board, goals are unlikely to be achieved. Only 30% of the easiest goals are ever reached, while less than 5% of the most difficult goals are ever reached.
Figure 5:
Figure 5:
CCDF of days taken to achieve a goal, stratified by goal difficulty. More difficult goals take more time to achieve.
Figure 6:
Figure 6:
Propensity to meet weight loss goal by weight loss over the first week. (A): Without stratification by goal difficulty, we find a U-shaped curve in agreement with existing literature suggesting that “too much” early weight loss is unsustainable and leads to worse longer-term outcomes. (B): With stratification by goal difficulty, we now see that people who lose more weight in the first week are far more likely to reach their goals. Contrary to what medical literature might suggest, there is no such thing as “too much” unsustainable early weight loss which ultimately leads to worse results.
Figure 7:
Figure 7:
Propensity to achieve goal by number of days logged a weight over the first seven days, stratified by goal difficulty. We see that across all difficulty of goals, people who log weights more frequently over the first week are more likely to achieve their goal.
Figure 8:
Figure 8:
Committed food loggers during the first 7 days of a goal are much more likely to meet their weight loss goals than less committed loggers. Further, committed loggers who log more calories are less likely to meet their goal, while uncommitted loggers who log more calories are more likely to meet their goal.
Figure 9:
Figure 9:
Propensity to achieve goal by motivation. Motivations derived from learning a topic model over free-text goal reasons provided by users and then assigning each goal a primary topic.
Figure 10:
Figure 10:
ROC AUC for predicting whether a user will achieve their weight loss goal from observing their behavior over the first seven days after setting it. We report accuracy for each feature set individually and all features together. We reach 79% ROC AUC in a combined model with all features.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Marc A Adams, Sallis James F, Norman Gregory J, Hovell Melbourne F, Hekler Eric B, and Perata Elyse. 2013. An adaptive physical activity intervention for overweight adults: a randomized controlled trial. PloS one 8, 12 (2013), e82901. - PMC - PubMed
    1. Althoff Tim, Jindal Pranav, and Leskovec Jure. 2017. Online actions with offline impact: How online social networks influence online and offline user behavior. In Proceedings of the Tenth ACM International Conference on Web Search and Data Mining ACM, 537–546. - PMC - PubMed
    1. Astrup Arne and Rössner Stephan. 2000. Lessons from obesity management programmes: greater initial weight loss improves long-term maintenance. obesity reviews 1, 1 (2000), 17–19. - PubMed
    1. Bandura Albert. 1977. Self-efficacy: toward a unifying theory of behavioral change. Psychological review 84, 2 (1977), 191. - PubMed
    1. Bodenheimer Thomas and Handley Margaret A. 2009. Goal-setting for behavior change in primary care: an exploration and status report. Patient education and counseling 76, 2 (2009), 174–180. - PubMed

LinkOut - more resources