Using Social Listening to identify target personas and social influencers
Customer segmentation and persona development is a key step in the development of a marketing strategy. It involves the grouping together of customers and potential prospects within a marketplace based on their similarities. Customers can be segmented in any number of ways including by geographic location, customer profitability, perceived benefit from a given product feature, preferred communication channel and so on. The key is to segment your customers in a way that best delivers on business goals.
Traditionally marketers would focus on high-level generic similarities. For example, a Craft brewer may be targeting a customer “segment” represented by males, 17-35, based in the UK. Going a level deeper, we can look to create customer personas. A persona is literally a personification of the characteristics of the customer segment. In the case of the brewery their Persona might be “Bob” who is male, aged between 17 and 35, enjoys watching and playing sports, loves good food, has a beard and is partial to the occasional beer.
Identifying Customer Personas using Text Analysis
We share a lot of what businesses would class as “useful” information on the web today. Our contact details, what brands we like, what bands we listen to, where our last holiday was, where we ate lunch…we pretty much share everything and mainly through social channels.
With the help of Text Analysis, a lot of this information can be mined to create incredibly targeted Customer Personas, by creating a database of your customers’ “taste” profiles. “Taste” profiles consist of a list of what customers like and dislike with a weighting score to indicate how much they like or dislike something. Taking the database as a whole we can look for similarities to uncover personas and use these insights to tailor our messaging to be more effective.
Sample Taste Graph:
Using Text Analytics and data mining, we can analyse online interactions like tweets, reviews on yelp, comments and likes and shares. Modern technology and solutions allow us to dive into what our personas like about a product, a news article, what their interests are, where they ate lunch and even if they enjoyed it!
Once you have nailed your target personas you can utilise the same social media platforms to identify new customers, who fit your target persona and nurture existing ones with super targeted marketing communications in the right channels that are sure to resonate.
How to leverage your personas
Individuals like celebrities or social influencers have a greater voice on social media, but not all us can afford a celebrity endorsed tweet.
Social media influencers however are a little easier to access. They are generally passionate and knowledgeable in their area of interest and are regarded as trustworthy authorities by their followers who will be open and receptive to what they have to share.
While it may seem difficult to do, identifying influencers can actually be accomplished quite easily with the right tools and technology. On social platforms, we can define keywords to monitor, classify text they share in comments, content or posts, extract entities and concepts and use Sentiment Analysis techniques to discover the polarity of aspects in the text.
This data can then be filtered to uncover the most relevant influencers for a given segment, those with the largest and most engaged audiences based on the number of shares, likes, upvotes, retweets, followers etc…
In summary, Text Analysis allows you to listen to the voice of your customers and prospects giving you a better understanding of their interests and allowing you to get more targeted in identifying target personas or finding social influencers.
A legal convert with a masters degree from Smurfit Business School, Mike runs our Sales and Marketing at AYLIEN. Mike gathered his Sales and Marketing experience with technology companies in Sydney and Dublin before getting the startup itch and joining the team at AYLIEN.
Introduction This is our second blog on harnessing Machine Learning (ML) in the form of Natural Language Processing (NLP) for the Automatic Classification of documents. By classifying text, we aim […]
We’ve just returned from RapidMiner Wisdom 2016 in New York City. This fantastic event organised by our partners RapidMiner, saw data scientists, academics and the newly coined citizen data scientists […]