Presented By O'Reilly and Cloudera
Make Data Work
March 13–14, 2017: Training
March 14–16, 2017: Tutorials & Conference
San Jose, CA

Emotion text analytics for deeper understanding and better prediction of irrational human behavior

Lana Novikova (Heartbeat AI Technologies)
4:30pm5:00pm Tuesday, March 14, 2017
Location: LL20 A
Average rating: *****
(5.00, 2 ratings)

We don’t need to try hard to convince anyone today that human beings are emotional first, rational second. Decisions that we make every minute, from what flavor of Starbucks to buy to who to vote for, are made deep inside our emotional minds and are influenced by both conscious reasons and subconscious “primes.” Emotion text analytics is a new, possibly groundbreaking area of research and analytics. What if we could rely on text data to be the “secret sauce” for accurate prediction of future events that are based on human decisions, such as elections, consumer behavior, public opinion, and social movements.

Lana Novikova shares the results of Heartbeat Ai’s experiment to see if it could build a predictive algorithm for national elections using unstructured text data from surveys. Traditional election polling asks questions like “If elections were held today, who would you vote for?” or “Who do you think will become the next prime minister of Australia?” Heartbeat Ai picked three traditional questions and added two open-ended questions asking how people felt about each candidate winning the elections. The survey ran on Google Survey Platform for six weeks prior to the June 2 Australian elections and November 8 US elections. Heartbeat Ai then used an advanced analytics model to predict the results. In both cases, emotional measurements helped improve the level of predictability, and the company was able to make correct predictions for both the Australia and US elections. But what was even more interesting is that the models showed what particular emotions drove voters’ behavior, which explained the deeper “why” behind people’s decisions.

Photo of Lana Novikova

Lana Novikova

Heartbeat AI Technologies

Lana Novikova is the founder and CEO of text analytics startup Heartbeat Ai Technologies, which is bringing a unique perspective to collecting and analyzing affect data. Lana is a market research innovator and tech entrepreneur with a solid research management career and an award-winning portfolio of research inventions. A marketer by training and a market researcher by trade, she was never satisfied with mere numbers and shallow observations, always pushing to understand the “deep why”​ behind peoples’ decisions by connecting the dots between cognitive sciences, consumer research, and marketing. This drive is evident in Heartbeat Ai’s products, which offer insight tools to business leaders who, like Lana, are not satisfied with the "status quo.”