How to Analyze Sentiment in an Online Review

Harnessing the full potential of online reviews to enrich the customer experience

The amount of reviews posted online, whether about a restaurant, a product or a brand, has exploded over the last decade. Consulting these reviews has become automatic for consumers and greatly influences their purchasing decisions (according to a BrightLocal study, 87% of consumers consult online reviews to buy a product or service). It is therefore crucial for B2C companies to take control of these reviews and exploit their full potential. This requires tedious analysis work for marketing teams, which is all the more complex as the number of online review sources multiplies.

What are the main obstacles to auditing online customer verbatims?

• too many reviews for an exhaustive analysis of the information
• multiple channels/platforms for collecting online reviews

Our solution: Automate the analysis of online reviews to guide marketing strategy

To meet this challenge, Lettria has developed a text mining technology that allows us to analyze the sentiment of a text, and in particular to determine whether it is positive or negative.

The API uses the resources of psychology and the 8 primary emotions modeled in the Plutchik emotion wheel (joy, sadness, fear, anger, disgust, attraction, surprise and anticipation) to determine the polarity and emotional tone behind the words. By identifying the negative, positive or neutral connotation of a text, we greatly facilitate the understanding of online reviews and their classification. In fact, by automating this first level of sentiment analysis, Lettria enables marketing teams to enrich their market research and satisfaction surveys by taking into account the completeness of online reviews. If the collection of reviews is a prerequisite for measuring the customer experience, Artificial Intelligence tools like Lettria are now essential to fully exploit all the information contained.

The benefits of an integrated approach

• Access to much more information that was previously difficult to use and exploit
• Time savings (operational excellence) for marketing teams

Our partners' use-cases

• Respond quickly to reviews to improve customer service: Keeping a close link with your customers after the sale of a product or the provision of a service is essential to guarantee their loyalty. This is now done through customer reviews as well as through the response of the company and its customer success teams to these comments, especially when they are negative. An appropriate response is above all a rapid response, and Lettria will automatically send you negative comments that require rapid action on your part.
• Compare your points of sale / establishments to identify and disseminate best practices: Capitalizing on the analysis of online reviews to compare the establishments in your hotel or restaurant network is all the more relevant since the quantity of comments posted is significant for this type of service. Remember that Accor has no less than 221,000 online reviews of its hotel network. This spectrum of analysis makes it possible to identify the strong points to be replicated from one establishment to another and thus to fully exploit the advantages offered by a network.
• Improve competitive intelligence: Customer reviews are a valuable source of information, whether they concern your company or your competitors. By definition, this information is generally available as open data, yet the sheer quantity makes it complex, if not impossible, for a human to use. By automating their analysis, Lettria allows you to enrich your market research with a detailed and exhaustive vision of your competitors' customer satisfaction sources.