New Study Shows Pinterest Users Pin Healthy Recipes But Are More Likely to Make the Unhealthy Ones

mthomp7 — Mon, 17 May 2021 11:38:44 +0000

New Study Shows Pinterest Users Pin Healthy Recipes But Are More Likely to Make the Unhealthy Ones mthomp7 Mon, 05/17/2021 - 07:38

In This Story

Hong Xue, PhD

Lawrence J. Cheskin, MD

Y. Alicia Hong, PhD

Janusz Wojtusiak, PhD

Study found that users liked and pinned posts that were healthy but more heavily engaged off-line with recipes that were high in fat, sugar, and total calories. Findings indicate that users were more like to actually cook the less healthy recipes.

New Study By Hong Xue Shows Pinterest Users Pin Healthy Recipes But Are More Likely to Make the Unhealthy Ones

When it comes sharing recipes on social media, what users post, and what they cook may be two entirely different things. That’s the conclusion of a recent study from George Mason University’s College of Health and Human Services, published in April in the Journal of Medical Internet Research (JMIR), a leading journal for digital medicine and health research. The study led by Hong Xue, PhD analyzed hundreds of Pinterest Users and Pinterest Influencers, and found users liked and pinned posts that were healthy, featuring more poultry, fish and vegetables, but users more heavily engaged off-line with recipes that were high in fat, sugar, and total calories – indicating that users were more like to actually cook the less healthy recipes.

“It’s an interesting discrepancy between what pinners posted/liked and how users actually consumed the information,” Xue said. “Pinners are more likely to post recipes that are socially rewarded with likes and repins. They are more likely to adhere to an elite social norm set by celebrities and influencers promoting healthier, low-calorie, clean eating. But when it comes to the recipes users are more interested in making food high in fat, sugar, and high calories. We see a very different picture. They’re commenting on and posting finished dish photos of the less healthy recipes.”

The disconnect between popularity and engagement is an important one, Xue noted, because users aren’t taking the additional step from interest to action. And that could have significant implications for anyone attempting to increase healthy eating behaviors through social media campaigns. Specifically, the study found:

Engagement (commenting, sharing photos of finished dishes) increased as the amount of fat, sugar, total calories increased in a recipe
Popularity (reposting, liking) of a recipe increased as the number of poultry and seafood went up in a recipe
Comment mining on recipe posts revealed that users were more likely to comment on the way a recipe tasted
Users were far less likely to comment on a recipe’s difficulty level (less than 8 percent) or its health attributes (less than 3 percent).

With 18 percent of the adult U.S. population using Pinterest, and recipe sharing being one of its most popular interest areas, the platform represents an unprecedented opportunity to reinforce healthy eating habits, Xue said, if Pinterest influencers posting recipes used some different strategies.

“If users are engaging with more unhealthy recipes, then perhaps influencers should offer options for lowering the fat in them, as part of those recipes. There’s definitely a role for healthcare organizations and fitness experts to provide healthier recipes that are big on flavor, as this appears to be an area where users find the recipes lacking. To change perceptions, public health experts need to make healthy food the treat, and not the other way around. There’s tremendous opportunities in social media to influence healthy behavior,” he said. “We’re only beginning to understand it’s potential and pitfalls.”

Fellow CHHS faculty Alicia Hong (HAP), Janusz Wojtusiak (HAP), and Lawrence Cheskin (NUTR) also collaborated on this study.

Topics

Exploring Social Media’s Potential to Improve Public Health

mthomp7 — Wed, 04 Dec 2019 16:27:32 +0000

Exploring Social Media’s Potential to Improve Public Health mthomp7 Wed, 12/04/2019 - 11:27

The Role of Social Media in Cancer Campaigns

Crooks and Jacobsen and collaborators also studied how public health officials harnessed social media for cancer campaigns including World Cancer Day, National Breast Cancer Awareness Month, and the Movember campaign for prostate cancer awareness month. Their research suggests that such campaigns tend to focus on awareness and support (wearing pink or growing a mustache) rather than concrete actions and behaviors. The success of such campaigns varies depending on the platform, the type of cancer, and the nature of the campaign itself, indicating the need for more research to truly harness these channels for outreach during health awareness initiatives.[4] [5]

The researchers found that “top down” approaches in which public health officials use social media to promote public health interventions typically garner only modest engagement from the general public. Participants in grassroots communities on social media platforms are not necessarily more effective communicators. Users exchange information and experiences within their groups, but they may not actively engage with new visitors looking for general health information.

In a world where tweets literally travel faster than seismic waves, it is imperative to know when a wolf really is a wolf — and when it’s not. Together, an epidemiologist and a computational social scientist unleash the power of Web 2.0 data.

Drs. Andrew Crooks and Kathryn H. Jacobsen see social media through a different lens than your average Twitter or Instagram user. Crooks, a computational social scientist in Mason’s College of Science, and Jacobsen, an epidemiologist in Mason’s College of Health and Human Services, study how social media influences public health perceptions and behaviors as well as how public health information is disseminated.

The vast data sources created by Web 2.0 – through sites that promote features such as crowdsourcing and location-sharing—provide researchers like Crooks and Jacobsen insights into how social systems work and the patterns in how information spreads. More than 350 million tweets are sent per minute, and 75% of all users include some sort of geolocation information in their tweets. Crooks explains that computational social science (CSS) allows us to harness that data to explore the world around us, study the connections between people, derive knowledge about human behavior, and ultimately use that knowledge to improve public health. [The data also reveal quite a bit about Bot behavior—more on that later.]

Computational social science is crucial in a complex adaptive system where the behavior of an individual actor does not convey an understanding of the whole system’s behavior. “Yes, data can show patterns, but we need to understand the context and the process behind that data,” says Crooks, who calls upon a familiar fable to illustrate his point. “If one boy cries wolf, there probably isn’t a wolf. If 100 people cry wolf, there’s probably a wolf. If 100 people cry wolf and post pictures of the wolf at that geolocation, there’s definitely a wolf.” To make sense of social media narratives, as illustrated by the wolf example, we need three critical pieces of information: actors, concepts, and locations.

Even with machine learning capabilities, truly understanding the “concepts” behind the data requires significant manual labor. Take the example of the extensive work to code or classify the sentiment behind social media posts on vaccinations—a controversial and politicized topic on social media. “How would you code a tweet that says ‘I don’t feel anyone should be forced’ to vaccinate. Is that pro-vaccination, anti-vaccination or neutral?” Crooks asked in a recent Health Administration Policy Seminar. [The correct answer is anti, in case you’re wondering.][1] Providing that context is critical in understanding the nature of the discussion and tracking patterns in how the information flows across systems.

After arduous manual data classification, the research team was able to deploy machine learning analysis of more than 660,000 tweets about vaccinations and found, to their surprise, that 75% of the traffic on social media was pro-vaccination. Their analysis showed that those who were tweeting anti-vaccination sentiment were largely talking among themselves and there was little engagement between anti- and pro-vaccination social media users.

Although these emerging types of data are valuable sources for researchers, it can be expensive to acquire, store, and analyze social media data. For example, Instagram data used to be free via open application programming interfaces (APIs), but Facebook, which now owns the platform, now assesses hefty fees that can be in the $100k range. “If you are tracking the data yourself,” Crooks reports, “you may be able to avoid licensing fees, but you still have the challenge of storing huge amounts of data.”

In 2015, before the widespread outbreak of Zika virus in the Americas, Jacobsen gave Crooks a heads up that he may want to start collecting social media data about Zika. Based on her tip, they were able to watch the narrative unfold across social channels—seeing who was spreading information, where the clusters of discussion were forming, and the frequency of words being associated with one another. They were also able to see that the U.S. Centers for Disease Control and Prevention and World Health Organization were leading the flow of scientific information about Zika. [2] That was different what they observed in their research on vaccines, for which the flow of information was primarily driven by media outlets.[3]

In a world where tweets literally travel faster than seismic waves, it is imperative to know when a wolf really is a wolf and when it’s not—and to understand how information and misinformation spreads. Interdisciplinary collaboration between Crooks, Jacobsen, and their colleagues will continue to play a critical role in harnessing social media - and the growing mass of data - to improve public health.

A Note on The Role of Bots in Social Media Narrative

Chatbots or Bots, computer programs designed to simulate human conversation, present an additional challenge in understanding the flow of information between virtual and physical neighborhoods. To show the magnitude of the challenge, studies report that 15,000 Twitter accounts identified as Bots used the #IVoted hashtag on election day during the 2018 elections. While automated Bot detection services do exist, there is little consensus across services when it comes to classifying which specific Tweets are generated by a Bot and which are generated by a human – making manual review important.

[1] Yuan, X., & Crooks, A. (2018). Examining Online Vaccination Discussion and Communities in Twitter, Proceedings of the 9th International Conference on Social Media and Society, Copenhagen, Denmark, pp.197-206.

[2] Stefanidis, A., Vraga, E., Lamprianidis, G., Radzikowski, J., Delamater, P.L., Jacobsen, K.H., Pfoser, D., Croitoru, A., & Crooks, A. (2017). Zika in Twitter: Temporal Variations of Locations, Actors, and Concepts JMIR Public Health Surveill, 3(2):e22, DOI: 10.2196/publichealth.6925

[3] Radzikowski, J., Stefanidis, A., Jacobsen, K.H., Croitoru, A., Crooks, A., & Delamater, P.L. (2016). The Measles Vaccination Narrative in Twitter: A Quantitative Analysis, JMIR Public Health Surveill 2(1):e1, DOI: 10.2196/publichealth.5059

[4] Vraga, E., Stefanidis, A., Lamprianidis, G., Croitoru, A., Crooks, A., Delamater, P., Pfoser, D., Radzikowski, J., & Jacobsen, K. (2018) Cancer and Social Media: A Comparison of Traffic about Breast Cancer, Prostate Cancer, and Other Reproductive Cancers on Twitter and Instagram, Journal of Health Communication, 23:2, 181-189, DOI: 10.1080/10810730.2017.1421730

[5] Vraga, E., Radzikowski, J., Stefanidis, A., Croitoru, A., Crooks, A., Delamater, P.L., Pfoser, D., Jacobsen, K.H. (2016). Social Media Engagement with Cancer Awareness Campaigns Declined During the 2016 Presidential Election, World Medical Health Policy, DOI 10.1002/wmh3.247