Re: Red, Purple and Pink: The Colors of Diffusion on Pinterest

john c.

LOL, you’re too much Dan. Good one. They stopped teaching critical thinking in schools decades ago.
john castronovo

Sent: Tuesday, May 26, 2020 9:08 AM
Subject: Re: [colortheory] Red, Purple and Pink: The Colors of Diffusion on Pinterest

On May 25, 2020, at 8:45 PM, Kevin Stecyk <stecyk@...> wrote:
For those that are interested, here's an abstract of an academic article titled "Red, Purple and Pink: The Colors of Diffusion on Pinterest." You can click on the link in the prior sentence to read the article.

Many lab studies have shown that colors can evoke powerful emotions and impact human behavior. Might these phenomena drive how we act online? A key research challenge for image-sharing communities is uncovering the mechanisms by which content spreads through the community. In this paper, we investigate whether there is link between color and diffusion. Drawing on a corpus of one million images crawled from Pinterest, we find that color significantly impacts the diffusion of images and adoption of content on image sharing communities such as Pinterest, even after partially controlling for network structure and activity. Specifically, Red, Purple and pink seem to promote diffusion, while Green, Blue, Black and Yellow suppress it. To our knowledge, our study is the first to investigate how colors relate to online user behavior. In addition to contributing to the research conversation surrounding diffusion, these findings suggest future work using sophisticated computer vision techniques. We conclude with a discussion on the theoretical, practical and design implications suggested by this work—e.g. design of engaging image filters.
From the article, I interpret diffusion to mean sharing.
The article has a useful review, with references, to previous research on the impact of specific colors. Its own research methods are well documented but fall victim to the well-known scientific epidemic of Failure to See the Forest for the Trees Syndrome. And speaking of epidemics just yesterday we had news that investigation of one FSFTS theory has had to cease on ethical grounds because it appeared to be killing more people than it helped. And the thinking is much like that of the researchers above. To wit:
PROVEN FINDING: That persons with the autoimmune disorder lupus tend not to get Covid-19 and if they do get it they tend to do better than others.
FSFTS CONCLUSION: It must be some medication that the lupus patients are taking, and since many of them take hydroxychloroquine, that’s probably it.
12-YEAR-OLD’s CONCLUSION: When invaded by a previously unknown virus, a hyperactive immune system is likely helpful.
Note the similarity with this article’s theories.
PROVEN FINDING: That based on pixel analysis, the presence of reds and pinks is associated with a higher rate of sharing in social media.
FSFTS CONCLUSION: It must be some subconscious appeal of these particular colors.
12-YEAR-OLD’s CONCLUSION: Pictures of people are much more commonly shared than any other image category.
Dan Margulis

Join to automatically receive all group messages.