SenseLearn - Advertising Research - Use Case
The world’s largest consumer goods company decided to use emotion data analytics to improve its branding, advertising and packaging. The company’s R&D group wanted an integrated facial expression emotion analysis platform to develop and build brands that consumers would love.
- Use focus groups to gather emotional data about consumer preferences leading to insights enhancing predictability.
- Add an emotion-based dimension to survey / A/B testing in order to improve decisions concerning branding, packaging and aesthetics.
- SenseLearn emotion AI technology captures macro and micro facial reactions in focus groups exposed to advertising. This enables the level of the group’s engagement to be scored and provides deep insight into the participants unfiltered and unbiased reactions. Marketers can know what the group’s participants really think and how likely they are to follow up with an actual purchase after watching an ad. Moment-by-moment emotion data also detects confusion and lack of engagement that may result from a specific segment in the ad.
- The emotion data link directly to outcome norms such as brand recall, sales lift, purchase intent and virality, which can be compared across different ads. This is crucial in deciding which advertising copy to use. These norms can be compared to those of competitors, by product category, geography, media length and repeat view.
- Our metrics and analytics provide important insights concerning consumer interest and behaviour. This enables accurate profiling. The algorithm also recognizes emotional preferences that may be affected by differences in ethnicity and culture.
- A/B testing on the company’s website uses emotion data to determine which variant is most effective at driving conversions and attracts the most traffic to the website. The information is used in making more effective designs for packaging.
- Analysis of emotions helped our client improve content messaging and story flow by detecting and refining those parts of the company’s ads that caused viewer confusion and low engagement.
- We identified the moments in the ad that were the most emotionally engaging. That let the client to reduce the length of the ad while focusing on those parts that had the greatest impact.
- The analysis helped the client increase the impact of its media spend.
- The client had the option of extending the analytics to build future digital marketing strategies
- Purchase intent increased significantly after ads were refined using our emotion data. This was enhanced by the fact that our algorithm eliminates the group conformity bias that often inhibits individuals from expressing their true feelings.
- Our approach to emotion recognition was shown to increase granularity and the degree of data validity by 30% when compared to conventional survey techniques. Emotion feedback circumvents the natural instinct in focus groups to give polite, non-committal answers. Real-time emotion AI saved 2 months of survey efforts by significantly reducing the feedback loop.