Be Careful What You Watch! Marketing Persona Can Now Be Generated by Social Media Data

Social media data is more revealing than most netizens know, especially now that computers are capable of grouping consumers into marketing segments in real time by simply observing peoples' response to online videos and other social media data.

Researchers from Penn State have presented their findings at the Second International Workshop on Online Social Networks Technologies held in Agadir, Morocco. They work featured how computers utilize information from social media accounts to automatically build marketing personas. Lead researcher James Jansen, a professor of information sciences and technology from Penn State, is aware of how marketing research professionals usually generate personas to allow editors and marketers understand the behaviors of their target consumer groups.

"A lot of times we have to use numbers in decision making, whether that's using numbers in understanding a market segment or an audience base or demographics, for instance," shared Jansen. "But it's hard to make a decision looking at a bunch of complex numbers that most people don't understand. One way that has been proposed and implemented in a wide number of domains to understand consumers is through personas. Researchers take a bunch of market data and condense it into a fictitious person."

The typical process is for marketers to manually generate personas from data gathered from focus groups, ethnography methods and surveys. "The problem with that, though, is that, in addition to being time consuming and expensive, they can rapidly become obsolete," said Jansen.

In contrast, computer-drawn personas are generated in real time and at a much lower cost. The data generated could also be updated quickly as economic conditions and demographics continuously change.

Algorithms were developed to analyze the following data from 188,000 subscribers of a news website: demographic information, topics of interest and customer interactions. This data included the subscribers' demographic information such as gender, age and country location, and their interactions with videos on the site. The algorithms were able to identify new ways people interacted with the information.

"The method is transferrable to other domains," said Jansen. "It could work at any consumer touchpoint, any place where we can see what the consumers are buying or what they are viewing before they buy and then tie it back to some demographics."