Study ID Visual characteristics that make people “like” images on Instagram

Marketing researchers have identified the combination of characteristics that makes people “like” images on the Instagram social media platform. For example, the visual complexity of images has a significant effect on whether viewers choose to engage with a social media post.

“We are increasingly able to determine whether images included in social media posts are likely to pique consumer interest,” says William Rand, co-author of a work paper and associate professor of marketing at North Carolina State University. “But many of the variables that we know affect audience interest have very little to do with the images themselves.

“For example, the strength of a brand and the number of followers it has on Instagram is the strongest predictor of consumer engagement with an image,” says Rand. “The text that accompanies an image is also important.

“We wanted to examine the actual role picture plays, focusing specifically on how the complexity of an image drives consumer engagement. This is important information for the marketing community because it can inform decisions about what kind of images to use to continue building a brand.

Previous work has revealed that there are two aspects of an image that people respond to: feature complexity and design complexity. Essentially, feature complexity refers to fundamental characteristics such as color and brightness. Design complexity refers to the actual elements found in an image and how they are laid out.

To begin their analysis of how viewers respond to picture complexity, the researchers identified six measures that can be used to assess various aspects of picture complexity:

  • Distribution of colors in the image;
  • Distribution of luminance in the image;
  • Number of edges in the image;
  • Number of objects in the image;
  • The regularity of objects, which is determined by whether objects share an orientation and the extent to which they overlap; and
  • What is the symmetry of the arrangement of objects.

The researchers wrote a computer program to scan images and automatically generate scores for each of the six measurements. The researchers also conducted a validation experiment to ensure that the image rating program was consistent with how humans perceive the complexity of images.

The researchers then created a model to determine which combination of metrics was most closely associated with generating likes on Instagram. The model took into account confounding variables, such as the number of followers of a given Instagram feed.

For the study, the researchers fed 147,963 Instagram images and associated data into the model.

“We found that all six metrics are important, but there were particular patterns in which the images generated the most positive feedback,” says Rand.

When it comes to feature complexity, the researchers found there was a happy medium. Consumers preferred images with some diversity of light and color, but neither too much nor too little. The reverse is true for design complexity. People preferred very simple or very complex images.

“In practical terms, we found that you could improve the number of likes for a given image by around 3% if you applied the right filter to address issues with feature complexity,” says Rand. “It’s no small feat, especially since applying a filter only takes a few seconds. Additionally, our model suggests that optimizing for feature and design complexity could improve consumer engagement by around 19% – after accounting for variables such as the total number of subscribers of a account.

“We put this out there with the idea that it can be used to inform decisions made by design professionals in the marketing industry. But we have made available the raw code of the model. It’s not in a user-friendly format at the moment, but I’m sure the right tech-savvy people could use it to create a valuable tool for the industry.

The article, “Simplicity Is Not Key: Understanding Business-Generated Social Media Images and Consumer Appreciation,” is published in the International Journal of Marketing Research. The paper was co-authored by Gijs Overgoor of Rochester Institute of Technology; Willemijn van Dolen from the University of Amsterdam; and Masoud Mazloom from Ferdowsi University in Mashhad.

-ship-

Note to Editors: The summary of the study follows.

“Simplicity is not the key: understanding the images generated by companies on social networks and consumer preferences”

Authors: Gijs Overgoor, Rochester Institute of Technology; William Rand, North Carolina State University; Willemijn van Dolen, University of Amsterdam; and Masoud Mazloom, Ferdowsi University of Mashhad

Posted: December 29, 2021, International Journal of Marketing Research

DO I: 10.1016/j.ijresmar.2021.12.005

Summary: Social media platforms are becoming increasingly important marketing channels, and recently these channels have become increasingly dominated by content that is not textual, but visual. In this article, we explore the relationship between the visual complexity of business-generated imagery (FGI) and consumer appreciation on social media. We use previously validated image exploration methods to automatically extract interpretable visual complexity measures from images. We construct a set of six interpretable metrics that are categorized as (1) feature complexity metrics (i.e., unstructured variation at the pixel level; color, luminance, and edges) or (2) feature complexity metrics. design (i.e. structured variation in design; number of objects, irregularity of object arrangement and asymmetry of object arrangement). These measurements and their interpretability are validated using an experiment on a human subject. Subsequently, we relate these measures of visual complexity to the number of likes. The results show an inverted U-shape between feature complexity and consumer taste and a regular U-shape relationship between design complexity and consumer taste. Further, we demonstrate that using the six individual measures that constitute feature and design complexity provides a more nuanced view of the relationship between unique aspects of visual complexity and consumer appreciation for FGI across networks. than that observed in previous studies that used a more aggregate measurement approach. Overall, the automated framework presented in this article opens up a wide range of possibilities for studying the role of visual complexity in online content.

Comments are closed.