- 16th April 2018
- Posted by: criticalfuture83
To properly understand what customers want, when, why and how they want it, retailers need to pivot toward sentiment analysis, a burgeoning technology that taps into consumer demand based on natural language processing. Ironically, it does so by emulating one of the primary cornerstones of social media: figuring out whether people like you or not. That’s the promise of sentiment analysis – it tells companies what people think – and ultimately how they act on – their brands. In raw form, sentiment analysis has been around for a few years. But with advancements in data harvesting technology, “social media” analysis is coming on like gangbusters. Using top-tier data collection technologies like natural language processing, text mining, and data mining, sentiment analysis gathers, categorizes and analyzes comments consumers make about a given brand – all in a matter of sectors. It doesn’t differentiate between bad news and goods (a fact United Airlines surely learned recently when Twitter, Facebook, LinkedIn, and other social media sites exploded after a passenger was dragged off a plane, bloodied and defiant on April 10 – with those comments fueling a UAL share price dive of 2.5 percent within 24 hours of the incident.)
The Era of “Opinion Mining”
Culling useful data from the whims and moods of often cranky consumers isn’t easy, but it does pay off when done correctly.
“Sentiment analysis is also defined as opinion mining: the science of harnessing and analyzing consumer’s conversation to understand whether consumers feel “positive”, “negative” or “neutral” about a certain brand, product or topic,” says Maxime-Samuel Nie-Rouquette, a client success manager at Semeon Analytics, a Montreal, Canada-based data analytics company that specializes in sentiment analysis.
If the target is hit dead on, sentiment analysis “can do wonders for retailers in providing better customer insights and experience,” Nie-Rouquette says. “By listening to conversations being held online (such as social media, blogs, forums, etc.), a company can understand consumer emotions and give them a connection that goes well beyond whether a product simply sells well or not.”
Nie-Rouquette notes the applications for sentiment analysis in the world of retailers are numerous.
“Retailers can monitor their customers’ reactions and feedback to push content for “virality” or exercise a damage control strategy during crisis management (lie the recent asparagus water issue that plagued Whole Food),” she says. “Retailers such as Walmart, Target and Costco use sentiment analysis to understand what their customers care about and leverage that information to reposition their products, create new content or even provide new products and/or services.”
In a technology sense, sentiment analysis is a unique blend of machine learning and artificial intelligence, allowing companies to use digitally-based data tools to cull useful, actionable moves that steer social media consumers toward their products and services.
But for companies really digging deep into consumer social media data, sentiment analysis really provides them with viable options.
“Short of biometrics or putting Neurosky headsets on everyone, there are three general areas of measurement that retailers can use detect emotion, or sentiment, in their customers: voice, text, and facial analysis,” says Sean MacPhedran, an ecommerce specialist at Smith.co who’s worked with heavyweights like AT&T and Microsoft to better drive consumer transactions using high-tech tools like artificial intelligence and cognitive data sets.
The most straightforward use for sentiment analysis tools for marketers is the measurement of trends in general sentiment on social media, MacPhedran states. For example, tracking “Macy’s” mentions and looking at the words around it for emotion and modifiers. Emotional words are fairly intuitive for us to grasp. “Crappy” or “hate” are bad. “Awesome” and “great” are good.”
But there’s obviously more nuance than that, he said: The more complex insights come from the modifiers.
“For example, is there a specific location associated with clusters of negative sentiment? Is there a specific issue that is associated? “Returns” for example, might indicate people are generally unhappy with a returns policy,” MacPhedran said.
Within the larger data sets, there will be many trends (think of them as moving vectors) operating independently, and only by using a strong multivariate analysis (like artificial intelligence or machine learning) will the trends actually become clear and actionable, MacPhedran notes. “It’s not enough to know the “average sentiment” regarding a brand – that would be like knowing the “average weather” for the entire planet tomorrow,” he notes.
A New Age in Sentiment Analysis
MacPhedran says the “next-generation” of sentiment analysis, coming in the next five years, is very exciting.
“Microservice API’s are able to measure emotion in written content, but also voice and facial expressions,” he states. “For the sake of the example, assume that we have a CRM system that knows the users social handles, and has an image of the customer usable, with customer permission, for personalization based on facial recognition.”
But it’s not all sunny skies for sentiment analysis – especially if companies don’t arm themselves appropriately, technology-wise.
“There is a catch,” notes Nie-Rouquette. “Because the backbone of sentiment analysis utilizes Big Data, using datasets that are comprised of thousands upon thousands of data points, retailers need to have enough data available (including customer conversations and reviews) to gain actionable insights.”
“So in some cases where data is scarce, sentiment analysis might not provide good insights because of the lack of statistical validity. Retailers must also ensure that they engage their communities to foster some conversations.”
That’s a fixable issue, though, and one companies should address if they want to receive the maximum benefits of sentiment analysis.
“It’s a good idea,” adds Nie-Rouquette. “With the availability of data on various online sources, companies (and especially retailers) can leverage sentiment analysis to gather insights that would not be possible using traditional marketing methodologies.”