Is a picture really worth a thousand words? ImagePulse measures how consumers feel about brands based on photos in which the brand is included. It uses a mixture of text, sentiment and image analysis to measure if the image is positive or negative and the emotions involved. What does it mean to the brand when people take pictures of themselves at a Nike store or having coffee in Starbucks?
The more photos people take, the less they bother to tag them. ImagePulse can identify brand logos and packaging in photos from popular photo sharing and social media sites without tags. The software then looks for faces, smiles and signs of emotional distress or happiness in the photos. Finally, it uses text-based sentiment analysis to identify emotional language used when sharing the image such as “This is awesome” in a tweet when sharing on Twitter. ImagePulse also maps photos to locations so brands can identify centers of activity.
Based on the photo analysis, ImagePulse calculates a Purchase Intent score, which indicates how likely it is that the person has bought or will buy the product. The score is based on factors like whether the person was in a retail environment when the photo was taken, whether the system thinks the picture expresses a desire to get information from friends or social connections, and the context in which the person shares a photo. Is it accompanied with words that indicate a “buy opportunity”? The Conjunctive Interspend score links brands together. For example, the photo analysis may reveal that a high percentage of Adidas fans own iPods and shop at Target.
CEO Jamie Thompson says that the data can be used in multiple ways.”If it turns out that large numbers of people are taking pictures of an outdoor advertising campaign, that might tell the brand that it was money well spent,” he says.
“If people in one part of the country (or world) regularly take pictures of a certain product, but they don’t take pictures of the same product in another region, that might tell you that either your product lacks strong advocates in an area or maybe it’s not as readily available. Once you have a sense of where, when and how frequently your brand is being photographed, you can build better brand engagement campaigns based on existing behavior,” Thompson concludes.
The company recently scanned 80,000 photos shared on Twitter over a five-week period. In keeping with Twitter’s techie image, the most popular brands were Google (22,483 photos), Apple (14,452 photos) and Android (11,127 photos) with Starbucks (10,713 photos) coming in 4th.
ImagePulse is a product from mobile picture sharing game company Pongr Media. Pongr Media was founded in 2008, is based in Boston and Des Moines, has 10 employees and is privately funded.
VB's research team is studying web-personalization... Chime in here, and we’ll share the results.