Edelman and Cision Form Communications Cloud Partnership Read More

3 Stages of Using Sentiment in Social Media Monitoring or Listening Programs

Sentiment has become a big topic of conversation and a key ingredient to a dependable recipe for deriving Social Intelligence from social media monitoring platforms.  It’s hard to deny the appeal of flashy and colorful report graphics showcasing positive and negative sentiment trends, scary red volume spikes and overwhelmingly green “whew, they love us!” pie charts.  They are impressive looking, put pizzazz in reports and at the same time can convey very important and pertinent information to business decision makers.

In social analytics research and reporting, sentiment plays a prominent role when comes to broader, aggregate level reporting.  A sentiment score can be an extremely useful in evaluating a large data set of social brand mentions—say a brand and image focused topic.  Tracking weekly or monthly shifts in positive or negative sentiment, say comparing your sentiment percentages to those of your competitors, is a great way to continually assess your brand health.

I like to refer to this as the baseline view of social reporting, the big picture overview.  These insights are very exciting in the early stages of social listening—what I like to refer to as the What Stage of social media monitoring.  What are they talking about, what percentage of posts are favorable, what sites are they talking on, what authors are the most vocal?  There is a lot to learn at this stage and monitoring shifts in these areas over time is key to understanding your position in the social conversation.

Naturally, in the early stages of listening, this What data makes up the bulk of reporting which leads us to the next stage—the Why stage.  You’ve knocked their socks off with some impressive stats and charts!  So of course the first thing you are going to be asked by your boss when you turn in your report showing that your brand mentions are 17% more positive this month than they were last month is. . . why?  Why were they happier?

Sentiment scores definitely help you here.  Filtering content based on positive or negative commentary can help you isolate the themes or issues that are driving the sentiment.  Sentiment doesn’t always hold the answer though.  Sometimes there are not specific drivers for a sentiment change and sometimes it isn’t that bloggers were more positive this week, they just didn’t have as much negative to say.  These types of explanations never feel as impressive as we’d like but remember, it’s part of the social analytics process.

Finally, this brings us to the third stage of social media listening—the Unknown-Unknown stage.  This is the holy grail of what every marketer, brand manager and agency is looking for.  What do I need to know that will change the way I do business that I didn’t even know I should be looking for!  While there are those revelations out there to be had, not every brand will have one or find one.  When it comes to finding the insights behind the data, the sentiment often starts to take a less featured role and move into a better support position.

Let me give you an example of an Unknown-Unknown finding I helped a client find that started with sentiment.  The client was one of the largest global food and beverage corporations and I was working with the brand managers for their meat enhancers (barbeque and other meat sauces, marinades, etc).  Their focus was on comparisons to competitive brands, concerns around ingredients, pricing discussions, and the like.  Looking at the positive and negative scored content definitely helped us come to some insightful conclusions with these aspects.

However, getting a little creative, I decided to review a list of the Web sites where the positive and negative posts were taking place and suddenly something jumped out.  There were a large number of vegan and vegetarian-focused sites that were all abuzz about one of their meat flavor enhancing products for vegetables and had been for a long time.  Reviewing the individual posts themselves it would have been very hard to find that trend but looking at the sentimented data from a different angle opened up a new opportunity, a niche market to focus on.

After this discovery the client prepared to focus on targeted messaging to this audience and promoting the fact that their product ingredients were vegan/vegetarian friendly.  I would love to hear from you and how you find sentiment helps you the most in social media monitoring.

For additional reading regarding sentiment accuracy and methods for scoring content for sentiment, please refer to our white papers on Sentiment in Social Media and Measuring Social Sentiment.

Recent Posts

Cision Blogs

  • Communications Best Practices

    Get the latest updates on PR, communications and marketing best practices.

  • Cision Product News

    Keep up with everything Cision. Check here for the most current product news.

  • Executive Insights

    Thought leadership and communications strategy for the C-suite written by the C-suite.

  • Media Blog

    A blog for and about the media featuring trends, tips, tools, media moves and more.