Frontline Marketing

Brands Discover Feelings Make Recommendation Engines Work

Bot automating emotion

By | November 10, 2017 |

Recommendation-engine technology is reshaping the entire digital consumer experience from entertainment to online shopping. To make a lasting impression, experts recommend focusing recommendation engines not only on user activity but the emotions driving those decisions.

For cable and entertainment providers, recommendation engines infuse algorithms with emotional connection data to create recommendations based on similar benefits, drivers and emotions that consumers are looking for in a show.

“If the consumer is given recommendations that are not relevant, do not resonate with them and do not seem to match their tastes, that will lead to a lack of trust,” Jill Rosengard Hill, executive vice president of Magid, told AListDaily.

Magid, a research-based consultancy for television and entertainment industries, curates “emotional DNA,” a database of consumer-rated emotions and attributes associated with TV prime time and network programming.

“We believe that those emotional drivers and connections that consumers have to content will make recommendations more relevant and more appealing than the current matching algorithms being used to make suggestions,” said Hill. “So much of [recommendation engines is] based on a matching algorithm. ‘Do you like this drama? Here are three other dramas you’ll like.’ That is somewhat obvious and it doesn’t necessarily surprise and delight consumers.”

Hill described how matching emotional attributes of a movie or TV show such as “adrenalin” and “fun” hones in on the reason a user chose that content as opposed to simply recommending the same format or genre.

This sentiment echoes a statement made by Todd Yellin, vice president of product innovation at Netflix. In a recent interview, he said that around 80 percent of subscribers trust and follow the recommendations of the Netflix algorithm.

“Personalization is about creating the right connection between a viewer and their content,” Yellin told MobileSyrup. “To do that, we have to understand everything there is to know about the content. It’s important we present the right content to the right member at the right time.”

Recommendation engines are commonly used for online retail and entertainment but are also used in other industries where emotions lead the buying process. When it comes to travel, recommendations become a source of inspiration.

“We know from our research and data that travel is a considered and time-consuming purchase, and the booking path is complex,” Lisa Lindberg, vice president of product management at Expedia Media Solutions, told AListDaily. “Expedia doesn’t use a traditional recommendation engine, as you may find on other e-commerce platforms because we’re a different form of retail. Travelers are visiting our sites to dream and be inspired, as well as purchase, so we have a different level of insights, including data on what consumers are actually viewing versus booking.”

Expedia websites recommend content to aid in research and planning. Once a purchase has been made, additional recommendations are provided to help build itinerary such as special deals on flights, hotels and attractions.

“Informative content is a strong influence on consumers—they’re open to inspiration and can be influenced when planning a trip,” said Lindberg. “Ultimately, recommendations should be relevant and provide valuable information to consumers, whether they are coming from a traditional recommendation engine or as a result of sophisticated audience targeting and relevant product offerings.”

Gartner predicts that by 2020, smart personalization engines used to recognize customer intent will enable digital businesses to increase their profits by up to 15 percent.

Someday, an entire consumer experience may be powered directly by emotions. For guests at Walt Disney Resorts, that day may soon be here. Disney filed the patent “Sensing and Managing Vehicle Behavior Based on Occupant Awareness” that reads guest emotions or pre-determined interests to customize ride experiences.

That means someone looking bored may cause the ride to speed up, or a child might see a charming fairyland while another sees a spooky graveyard. The patent also states it may be able to sense passenger comfort levels such as temperature and alter the air-conditioning of the ride to make it more pleasant.

“You look as if the ride made you really happy.”

“Would you like to buy a souvenir?”