Brands often tout how many social media followers they have, offering numbers that, in and of themselves, don’t necessarily translate to true customer engagement and customer loyalty.

Being able to go beyond social media popularity and target actionable reference points can elevate a brand’s status in the world of customer engagement and, ultimately, customer loyalty.

Lithium Technologies’ data science team released a research paper titled, “Mining Half a Billion Topical Experts Across Multiple Social Networks,” which analyzes and ranks topic experts across Twitter, Facebook, LinkedIn, and Google+.

What’s more, the study analyzes more than 12 billion messages and ranks 500 million experts on more than 9,000 topics. This expert ranking system flows directly into Lithium’s products, allowing brands to better understand their Total Community of customers. It also offers brands a way to identify what social networks specific topic experts are engaging on.

“Brands need to evolve past simply trying to reach the people with the most followers, or taking a scattershot approach of engaging with anyone and everyone on digital channels,” said Rob Tarkoff, President and CEO of Lithium Technologies. “We’re making it easier for brands to identify the right experts for their product or service, but that’s just the first step – they then need to work on cultivating authentic relationships with them.”

Since it acquired Klout in 2014, Lithium has focused on integrating its wealth of data across its entire portfolio of products to help businesses connect, engage, and understand their Total Community.

“In this study, we derive and examine a variety of features that predict online topical expertise for the full spectrum of users on multiple social networks,” the research paper notes. “We evaluate these features on a large ground truth dataset containing almost 90,000 labels. We train models and derive an expertise scores for over 650 million users, and make the lists of top experts available via APIs for more than 9,000 topics. We find that features that are derived from Twitter Lists, Facebook Fan Pages, Wikipedia and webpage text and metadata are able to predict expertise very well. Other features with higher coverage such as those derived from Facebook Message Text and the Twitter Follower graph enables us to find experts in the long tail. We also found that combining social network information with Wikipedia and webpage, Mining Half a Billion Topical Experts Across Multiple Social Networks data can prove to be very valuable for expert mining. Thus a combination of multiple features that complement each other in terms of predictability and coverage yields the best results. Further studies in this direction could unify cross-platform online expertise information, in addition to other data sources such as Freebase and IMDB. Another area that could be explored in the future is the overlap and differences in the dual problems of topical expertise and topical interest mining. To conclude, we provide an in-depth comparison of topical data sources and features in this study, which we hope will prove valuable to the community when building comprehensive expert systems.”

Recent Content