Skip to content
Crimson Hexagon
Request a Demo
Back
  • Technology
    • Platform
    • Artificial Intelligence
    • Data Library
    • Image Analytics
    • Role-Based User Experience
    • Products
    • ForSight
    • HelioSight
    • Dashboards
    • API
    • Services
    • Services at Crimson
  • Solutions
    • AI-Powered Consumer Insights
    • Use Cases
    • Audience Analysis
    • Brand Analysis
    • Campaign Analysis
    • Competitive Intelligence
    • Industry & Trend Analysis
    • Roles
    • Analysts
    • Marketers
    • Consumer Insights
    • Developers
    • Executives
    • Industries
    • Financial Services
    • Automotive
    • Entertainment
    • Retail
    • Agencies
    • CPG
    • Travel & Leisure
    • Brands
  • Social Insights Center
    • Resources
    • Case Studies
    • Guides
    • Industry Reports
    • Videos
    • Webinars
    • See All...
    • Featured
    • What Can You Do With One Trillion Posts?
    • Social Insights on Consumer Packaged Goods
  • About Crimson
    • Careers
    • Contact Us
    • Customers
    • Customer Events
    • Newsroom
    • Media Coverage
    • Analyst Reports
    • Events
    • Partnerships
    • FAQs
  • Blogs
    • Quick social insights about today's top news stories
    • In-depth stories on social media analytics and consumer trends
  • Login
  • Help Center
  • Contact Us
  • Login
  • Help Center
  • Contact Us
Crimson Hexagon
  • Technology
  • Solutions
  • Social Insights Center
  • About Crimson
  • Blogs

Request a Demo

  • Platform
  • Artificial Intelligence
  • Data Library
  • Image Analytics
  • Role-Based User Experience
  • Products
  • ForSight
  • HelioSight
  • Dashboards
  • API
  • Services
  • Services at Crimson
  • AI-Powered Consumer Insights
  • Use Cases
  • Audience Analysis
  • Brand Analysis
  • Campaign Analysis
  • Competitive Intelligence
  • Industry & Trend Analysis
  • Roles
  • Analysts
  • Marketers
  • Consumer Insights
  • Developers
  • Executives
  • Industries
  • Financial Services
  • Automotive
  • Entertainment
  • Retail
  • Agencies
  • CPG
  • Travel & Leisure
  • Brands
  • Resources
  • Case Studies
  • Guides
  • Industry Reports
  • Videos
  • Webinars
  • See All...
  • Featured
  • What Can You Do With One Trillion Posts?
  • Social Insights on Consumer Packaged Goods
  • 5-minute Guide to Audience Analysis

  • Careers
  • Contact Us
  • Customers
  • Customer Events
  • Newsroom
  • Media Coverage
  • Analyst Reports
  • Events
  • Partnerships
  • FAQs
  • Quick social insights about today’s top news stories

    In-depth stories on social media analytics and consumer trends

Back to Blog

What is Image Analysis?

How brands can use image analytics for consumer insights

Share this post:
Share on FacebookTweet about this on TwitterShare on LinkedIn
Photo of Garrett Huddy

February 1, 2017

by Garrett Huddy
@GarrettHuddy

Images are taking over social media. Whether it’s a meme, artsy photo, selfie, or link to an article, our social feeds are increasingly filled with more images and less text. Why? Images are more impactful than text. More memorable. More engaging. More likely to be shared and reshared. It makes sense that they’re everywhere.

badge-elementsofsocialmedia

But what does the growth of image sharing mean for social media analytics? How can brands track and leverage the growing number of images posted to social media? As part of our ongoing Elements of Social Media Analytics series, this post covers emerging image analysis technology and what it means for brands.

Why Images Matter

As social media and the web as a whole become more visual, brands can’t rely on text alone when analyzing social media data to better understand their audiences.

Here’s Gartner on the importance of image analytics:

“We do expect multimedia posts to become the predominant type of post on social media. Even the text that accompanies those posts is getting shorter and shorter…It becomes increasingly important for companies to be able to understand what’s going on in those images.”

-Jenny Sussin,VP of Research at Gartner

Over three billion photos are shared daily on social media according to Mary Meeker. Many of those photos contain brands’ products and logos, but 85% of them don’t include a text reference to the brand (LogoGrab). Without image analytics, brands are missing out on a huge chunk of the social conversations about their brand, products, customers, and competitors.

For example, take a look at this Instagram post from Drake:

Dubai you will be missed. Thank you for the inspiration and the reset. Back to work now. 🇦🇪💙🌺

A post shared by champagnepapi (@champagnepapi) on Dec 3, 2016 at 6:37pm PST

Drake’s Instagram post prominently features the Bentley logo, but contains no tag or text mention of the brand. If this is an organic mention of the brand, Bentley would surely want to know about it as soon as possible. If Bentley is paying or sponsoring Drake to post about the brand, image analysis technology can help them track exactly when and how Drake is representing the brand.

“Without image analysis, brands are missing out on a huge chunk of the social conversations about their brand, products, customers, and competitors.”

This is just one example of the power of this new technology and why it matters for brands. The ability to identify brand logos within images may seem like futuristic technology, but it’s actually one of the most basic functions of image analysis.

What is Image Analysis?

Image analysis (also known as “computer vision”) is the ability of computers to recognize attributes within an image. Do you use Google Photos or Apple’s Photos app on your smartphone? They both use some basic image analysis features to recognize faces and categorize them in your photos so you can look at all of your photos of a particular person. Type “dog” into the search function within either app to quickly locate your collection of puppy photos or type “beach” to find your tropical vacation pics.

Social media analytics started with, and continues to be based on, text analysis. But image analysis is becoming increasingly important. When applied to social media analytics, image analysis is an extension of text analysis features applied to visual content. The same methods of categorization apply to image analysis. Instead of looking at all of the posts that contain the word “computer,” object recognition can show you all of the posts that contain photos of a computer.

Let's get this week started…cafes are open & now at my desk to work on big plans! #entrepreneur #motivated #business #coffeelababuk #10x pic.twitter.com/MRtKDfvN4H

— Alex Donnan (@alex_coffeelab) January 23, 2017

Image analytics can also identify faces within photos to determine sentiment, gender, age, and more. It can recognize multiple elements within a photo at the same time, including logos, faces, activities, objects, and scenes. The technology can automatically caption images “man and woman standing outside wearing Patagonia shirts with bike and mountains in the background.” And that’s just the basic details.

 

image-analysis-example

 

But that’s just the beginning. As social media image analysis technology evolves, it will be able to provide even more context around photos. For a deeper look at the future of image analytics, download the Altimeter report: Image Intelligence: Making Visual Content Predictive.

Getting the Whole Story with Image + Text Analysis

The fact that social media is becoming more image-focused doesn’t mean text analysis should take a back seat. The only way to get the complete picture of what’s consumers are saying on social media is to look at text and images together.

There are some big advantages to looking at both text and images when analyzing social media data:

  • Images don’t require translation making image analysis extremely useful in a global strategy.
  • Looking at a more complete data set enables businesses to more effectively incorporate social insights into decision-making.
  • Images can tell a completely different story than text mentions (Example: Text-based analysis of conversation around Disney’s Frozen, shows adults in their 30s. Image analysis of the same conversation shows the movie’s true audience, children.)

The technology behind image analysis is advancing quickly—making it much easier to scale.  Images show contextual, environmental, and emotional factors that you can’t get with just text.

How Brands can Use Image Analytics

While image analytics is a new addition to the social media analysis technology, it already has a wide number of valuable use cases for brands.

Track Brand Mentions More Accurately

The simplest application of computer vision technology is to more accurately measure brand mentions. Companies use social media analysis tools to track and analyze how people are talking about their brand. In the past, the only way to find mentions of your brand or product within social posts was to look for text-based mentions or direct tags of your brand.

When a big brand like Nike wants to see how many people are talking about their products, one of their first steps may be to analyze their share of voice on social. But, as we’ve discussed, looking at these direct mentions is only one piece of the puzzle. What about the conversation that doesn’t involve text? This is where “share of eye” is important.

Finally got some new kicks today ❄️ pic.twitter.com/84WHYUJzkO

— maciemoo((basslanta)) (@macierenee11) January 23, 2017

Nike would miss posts like this if they are only measuring text-based social conversation about their brand. Image analysis solves this problem by extending social media analysis to visual content, allowing them to identify anything from their logo to any image of containing a particular type of product (for example, running shoes).

 

Improve Sentiment Analysis

Many companies use social media analytics to track how people feel about their brand or products. If you’re only looking at text you aren’t seeing the full picture.

Here, Gatorade’s Summit Storm flavor is “gross”:

Gross flavor. Highly disappointed. pic.twitter.com/AYjUpRrR7Y

— Cookie Takanawa (@JDaddy_3000) June 3, 2016

Both of these posts are great examples of the need to look at text and images together. Just looking at one or the other won’t give the full context. In these posts, text analysis identifies the sentiment while image analysis identifies the brand and product.

 

Measure Sponsorship ROI

How can you determine if paying to place your brand’s logo in a sports stadium is worth the investment? Was it worth it to sponsor that big event? These types of questions have been raised in marketing discussions for years, but logo recognition technology can finally start to give some answers to the “ROI of offline advertising” question.

Logo recognition technology allows you to quantify the number of impressions and exposure that your brand is getting from something like a red carpet sponsorship. Otherwise, you have no way to track those visual-only mentions.

#Flashback ….I really did love this dress…. 😉 #Vionnet

A post shared by Anna Kendrick (@annakendrick47) on Jan 8, 2017 at 2:36pm PST

 

Find Visual Influencers

Similar to the Drake/Bentley example, this Instagram post from Skrillex showcases the Adidas logo. Whether or not this is an organic or paid plug for Adidas, they would want to keep tabs on how influencers like Skrillex are promoting their brand.

A post shared by SKRILLEX (@skrillex) on Jul 25, 2016 at 3:54pm PDT

 

Identify Moments of Consumption

One of the most interesting and useful applications of image recognition technology is identifying moments of consumption.  Every company wants know as much as possible about how, when, and where people are using their products, but the limits of text analysis can’t provide a complete picture of actual product use. Unlike text, images provide visual validation of the who, where, and how people are using your product. Without image analysis, your fans and customers have to specifically mention your product, which is less likely to happen.

Anguilla – beach & beer! (@ Blanchards Beach Shack in Meads Bay, Anguilla) https://t.co/Cl7sRVrUWz pic.twitter.com/7egdpzEmr0

— cigarkirk (@cigarkirk) December 15, 2016

Visual evidence of product usage in the wild provides a much more powerful metric for brands than just measuring mentions. To take it a step further, you can start to correlate sales data with the number of times your product is appears up in social photos. Crimson Hexagon’s research has shown a strong correlation between sales numbers and the volume of social photos that show use of your products.

For more on how images fit into social media analytics, download our free guide: The Fundamentals of Image Analytics

imageanalytics-socialmedia_li

Photo of Garrett Huddy
Garrett Huddy
As a Content Marketing Manager at Crimson Hexagon, Garrett writes everything from newsletter emails to guides about social media analytics. When he isn't writing, you can find him running along the Charles river, attending a concert, or relaxing in coastal Maine.
Follow @GarrettHuddy

Request a Demo

Ready to transform your business?

Get a walkthrough of Crimson Hexagon and learn how social insights can help you make better business decisions.

Sign Up for a Demo Ask Us a Question
Crimson Hexagon

What is “The Crimson Hexagon”?

Our company’s name derives from the “Crimson Hexagon” described in Jorge Luis Borges’ short story, The Library of Babel, which was published in Spanish in 1941 in his collection, The Garden of Forking Paths.

The narrator in Borges’s story describes a library of astronomical size comprised of almost infinite adjacent hexagonal-shaped rooms that collectively contain every possible combination of just 25 characters, a period, and a comma.

Though most of the books are gibberish, the library also contains every valuable book every written and that might ever be written.

Similarly, our Crimson Hexagon software platform finds meaning in a seemingly endless volume of unstructured text and images.

Given our name, it flows naturally that the color crimson is central to our identity.

Interestingly, our founder, Gary King, is a world-renowned social scientist and professor at Harvard University, which is another world-leading institution that also is known not only for the color crimson, but also for helping inquiring minds find meaning.

  • Technology
    • Platform
    • Artificial Intelligence
    • Data Library
    • Image Analytics
    • Role-Based User Experience
    • Products
    • ForSight
    • HelioSight
    • Dashboards
    • API
    • Services
    • Services at Crimson
  • Solutions
    • AI-Powered Consumer Insights
    • Use Cases
    • Audience Analysis
    • Brand Analysis
    • Campaign Analysis
    • Competitive Intelligence
    • Industry & Trend Analysis
    • Roles
    • Analysts
    • Marketers
    • Developers
    • Executives
    • Industries
    • Financial Services
    • Automotive
    • Entertainment
    • Retail
    • Agencies
    • CPG
    • Travel & Leisure
    • Brands
  • Social Insights Center
    • Resources
    • See All
    • Case Studies
    • Guides
    • Industry Reports
    • Videos
    • Webinars
  • About Crimson
    • Customers
    • Careers
    • Contact us
    • Newsroom
    • Media Coverage
    • Analyst Reports
    • Events
    • Customer Events
    • Partnerships
    • FAQs
  • Blogs
    • The Crimson Post
    • Blog

Connect With Us

© 2018 Crimson Hexagon.
  • All rights reserved.
  • Privacy Policy