How Retailers Can Use Sentiment Analysis to Tap Into Consumer Demand
Big-name retailers have had a rough year. While the economy continues to make gains, the stock market reaching record highs and jobs reports putting smiles across economists’ faces, retailers such as Macy’s have failed to exploit the improving economic landscape.
In fact, according to WWD, Macy’s, Sears Holdings Corp., The Limited, American Apparel, BCBG Max Azria, Wet Seal, J.C. Penney, and Abercrombie & Fitch are set to shut down around 1,000 stores this year.
While there are undoubtedly multiple factors playing into these disappointing results, one of the main reasons for the slow sales is bad product assortment. Basically, these retailers failed to put the right products on the shelves, and consumers punished them by spending their money elsewhere.
Similarly, tech companies such as Fitbit have failed to meet expectations when its products don’t fully satisfy consumer demands. In the final months of 2016, Fitbit reported a loss of over 50 cents per share. As a result, it was forced to cut back and lay off 110 workers as it attempted to reorganize.
Consumer Sentiment Index Doesn’t Cut it Anymore
Understanding consumers has always been high on retailers’ to-do list. However, too often these companies fall into the trap of using antiquated marketing methods such as the consumer sentiment index to make product decisions. While the consumer sentiment index delivers important information regarding macroeconomic conditions, it doesn’t offer any help with meeting consumer demand.
Furthermore, traditional wisdom states that the best approach is to offer a wide variety of products online and in-store, increasing the chances that consumers find ones they like. Unfortunately, this method doesn’t always work as many consumers become confused with all of the choices. In fact, many end up purchasing from a competitor, where they can more easily identify the product they’re actually looking for.
NLPNobody wants to be bombarded with 25 different types of toothpaste. Normally, what they want is to find their favorite go-to toothpaste brand, and get out of the store as fast as possible.
Sentiment Analysis Can Help
Sentiment analysis relies upon natural language processing (NLP), text mining and data mining capabilities to find information on consumer demand. A field of machine learning and artificial intelligence, NLP allows machines to read and derive meaning from human language. However, because it's done through machines, it develops a way to analyze millions of posts that are uploaded every day to social media sites like Facebook and Twitter.
Sentiment analysis reads through the text to see whether it's positive, negative or neutral. It can also take into account the meaning of the words as well as the specific context of what was said. The reason that sentiment analysis is becoming popular for retail and technology businesses is because customers increasingly express their desires, thoughts, preferences and frustrations online.
With sentiment analysis using NLP, businesses have the opportunity to find out what their customers are saying and how they feel about the products they’re offering. Using social media, it's now possible for retailers and tech companies to understand the sentiment of their customers in real time, finding out how they feel about the products on store shelves, store layouts and commercials. Furthermore, sentiment analysis can tell businesses how deeply customers feel about products, as well as which features are responsible for those feelings.
In the future, technology businesses such as Fitbit could turn its fortunes around by implementing sentiment analysis with its product releases. With real-time data coming in, the merchandising team could make adjustments to make the public fall in love with its products again. More traditional retailers like Macy’s can use sentiment analysis to identify more attractive retail locations as well as stock their shelves to better fit their customer's mood.
Taran Volckhausen is a contributing editor at Vector, a natural language processing application.
