A new research tool has analysed the tweets from users of Twitter, who have indicated they are dieting or thinking of beginning a diet, to determine how successful the diet might be. The analysis has found that the success or failure of a diet can be predicted with 77 percent accuracy based on the types of tweets a person sends alone. The findings may have implications for the way organizations that seek to promote dieting use social media to convey messages of support or encouragement to dieters.
The study was carried out at Georgia Institute of Technology, focusing on people who connected their MyFitnessPal (a calorie-counting app) and their Twitter accounts together. The researchers analysed some two million tweets and over 100,000 daily app uses. How successful a diet was garnered from MyFitnessPal entries.
The researchers looked for particular words and phrases and an interest in health and fitness, as signs of dieting success. They also noted that the more successful dieters are the more socially interactive. Social interaction included sharing of diet tips and healthy recipes.
In a research briefing, lead scientist Professor Munmun De Choudhury said: “We see that those who are more successful at sticking to their daily dieting goals express more positive sentiments and have a greater sense of achievement in their social interactions.”
He explains this by saying that people with these attitudes are “focused on the future, generally more social and have larger social networks.”
In terms of the key statement’s and phrases most likely to lead to success, Professor De Choudhury calls out:
“Train smart like a trainer…win like 6 time champion [sic].”
“If your not failing your not trying hard enough…[sic].”
“If we never stumble we never fall. If we never fall we never fail, and if we never fail we never grow!”
These types of tweets are considered as ‘upbeat’ and ‘self-reflective’. In contrast those who were less successful with their diets tended to tweet with negative phrases. This suggested anxiety and less emotional control. Examples of negative tweets included:
“I’m pretty sure I’m going to lose my mind.”
“Feel rough as old boots this morning.”
“Ankle hurts, shin hurts, chest hurts, head hurts.”
Going forwards, Professor De Choudhury suggests a new analytical method could be developed to provide greater health and wellbeing benefits.
The research paper is headed “Computational Approaches Toward Integrating Quantified Self Sensing and Social Media” and it will be presented at the 20th ACM Conference on Computer-Supported Cooperative Work and Social Computing.