Uncovering Consumer Purchasing Cues from Online Conversation Clues

By Dax Hamman

SPF/Shutterstock.com

What could Disney, the United States Marine Corps, Hershey’s and Under Armour possibly have in common? On the marketing front, at least, they share a desire to put a finer, more cost-effective point on their online targeting efforts, and a willingness to move past traditional approaches to get the results they seek.

An openness to using a progressive targeting strategy ultimately led each of the aforementioned organizations to an emerging AI-driven tool called conversational analysis, which parses online conversations to provide predictive insight into consumer behavior. And in each case, conversational analysis delivered. In a campaign to identify an audience of potential recruits, with a focus on unemployed men from the millennial generation, the Marines used conversational data to build a new audience of some 2.6 million prime recruiting candidates, surpassing the campaign’s benchmark on-target rate by 139 percent. Conversational analysis defined that audience by identifying key words and phrases young men were using in their online conversations, zeroing in on those discussing college graduation, job search, unemployment, etc.

Likewise, when Disney wanted to promote a superhero film on social media via a series of short videos featuring stars of the movie, instead of shotgunning those videos across the Twitter universe, it used conversational analysis to define and connect with a highly targeted audience of close to 10 million genuine movie fans across dozens of unique segments. The campaign yielded true personalization at scale, producing more than two million video views in its first 24 hours — three times the benchmark for total views — along with about 440,000 opt-ins.

Outcomes such as these are opening the marketing world’s eyes to the possibilities conversational analysis brings as a targeting tool. The shift in everyday human conversations from face-to-face to online provides an increasingly massive supply of potentially valuable marketing insight. But it takes a powerful technology to read between the lines of all that digital dialogue in real time. Conversational analysis does just that, using natural language processing (NLP) technology to process and analyze streams of social media chatter to gain insight into consumers’ wants, needs and emotions. When peoples’ words come unsolicited and unprompted as they usually do in informal online conversations (minus the inherent bias of an online survey, for example), they tend to carry greater weight, meaning and marketing value. Using algorithms in tandem with NLP, conversational analysis does what demographics, psychographics, purchase history, behavioral markers, etc., cannot, contextually connecting what people say in their online conversations to how they’re likely to act as consumers.

Context is the operative word here. Conversational analysis processes the constant torrent of online conversation through the filter of an expansive taxonomy of keywords, phrases and classifiers (my company, audience.ai, currently has a library of close to 35,000 of them, for example). That taxonomy is continually updated as new words — slang, jargon, brand and product names — enter the lexicon and others drop off. Conversational analysis plugs into that taxonomy to gain insight into how peoples’ use of specific words and phrases make them more or less inclined to buy a product.

Conversational analysis also captures nuance, with an ability to predict consumer behavior based not only on what they say but how strongly they say it. By tracing keywords back to specific conversations and user information, it creates profiles and defines unique audiences of motivated consumers who show the greatest likelihood of engaging and purchasing at the most opportune time.

What’s more, conversational analysis is adept at extracting both implicit and explicit meaning from online conversations, as a case in which it was used to generate audiences of people considering moving or renovating their residences illustrates. By intelligently gleaning implied meaning from comments like, "We are really outgrowing this place,” and "I hope mortgage rates stay this low,” it created segments of people who are seriously contemplating moving. Meanwhile, it was also building segments around explicit language about mortgage brokers, school districts, etc., that suggests a move is imminent. Ultimately, the analysis yielded exactly the type of motivated, segmented and target-rich audiences that contractors, realtors, lenders, home improvement stores, etc., crave.

Conversational analysis also brings immediacy to a targeting campaign. It moves at the speed of the digital world, using fresh online conversations to deliver defined audience segments as members of these segments move along various points of the purchase cycle.

As compelling as these attributes may be, conversational analysis remains a largely untapped resource. Based on our experience applying it in a variety of targeting scenarios, here are a few best practices to help maximize its impact:

1. Test the waters. As new as conversational analysis may be to some organizations, and as scalable as the data is, it’s well suited to testing with a pilot program before scaling up based on results, budget and comfort level.
2. Pick a subject about which there’s abundant conversation. The greater the volume of fresh online conversations to analyze, the stronger, more targeted and more segmentable the conversational data will tend to be.
3. Approach with an agile mindset and methodology. Conversational data sets are readily iterated and segmented in a multitude of ways, allowing the user to learn from their targeting experience on the fly and adjust accordingly.
4. Let conversational analysis stand on its own. As tempting as it may be to overlay conversational data with demographic data from other sources, doing so lessens the clarity of the insight conversational data yields.
5. Use it for an online or offline campaign, or both. Conversational analysis can provide highly defined audiences for direct mail, call center, email, social media and other forms of marketing and promotion.

As a certain female athletic apparel brand discovered, even a dip of the toe in the conversational analysis waters can yield unexpectedly valuable insights. Not only was the company able to pinpoint a reliable predictive connection between females who mentioned the pop star Rihanna in their online posts and a strong inclination to purchase a certain type of yoga pants, it also saw a 20 percent increase in performance-repeatable targeting data and a 45 percent reduction in cost per acquisition. Numbers like these are sure to get more advertising and marketing professionals talking.

Dax Hamman is chief marketing officer for audience.ai.

The views and opinions expressed in Marketing Maestros are solely those of the contributor and do not necessarily reflect the official position of the ANA or imply endorsement from the ANA.