Get business insights from customer reviews automatically

Your hotel deals with thousands of reviews: in TripAdvisor, Yelp and your own satisfaction surveys. Nobody can process all this information and get accurate insights of what is going on. So, companies start relying on machines to do this job automatically by using sentiment analysis.

The hospitality industry deals with vast amount of customer feedback data. Hotels and restaurants always want to improve brand performance and customer loyalty, so they collect all the reviews customers spread in online platforms, social media, and even, own company surveys, to understand their customers better.

Reviews are great source of insights to enhance products and services, the problem is how to separate the wheat from the chaff to get the business relevant insights from customer reviews -and not die trying-.

Sentiment Analysis to automatically get feedback data insights

You may have heard about sentiment analysis and already know what the current technology allows to do. Nowadays there are several tools to be able to go from a vast collection of texts to a few insights that are relevant for business decisions. Thanks to the most recent advances in NLP and computational power, learning any given brand's global reputation is almost totally automated.

What kind of business insights sentiment analysis gives?

Analyzing all the feedback your customers give you, company can know accurately business insights like:

  • What particular hotel is having bad reputation between your customers
  • Detect what specific services (food providers, room services, laundry, …) are disappointing your guests
  • What areas are working better, e.g. satisfaction with lunch menu

 This kind of insights will allow your company to take measures to improve areas of dissatisfaction, and, also, it will let you know how new initiatives are going to impact your customers.

How does sentiment analysis work?

There are some sentiment analysis tools in the market, but no all of them are equally accurate. While some may be based just on keywords or syntactic tagging, others, like Bitext’s, are based on text analytics and takes advantage of all NLP resources that are enriched with linguistic knowledge. This second approach allows extract precisely what customers feel about particular topics -and even how strong those feelings are-. This is how sentiment analysis process should look like:

  1. The first part is the review undergoing segmentation and tokenization: it is as simple as splitting into sentences and then into words, following the same hierarchy we used when reading.
  2. Then, each element is tagged: using lexicons, words or expressions are tagged with their corresponding attributes (POS, morphological attributes, and, possibly, functional and/or semantic attributes).
  3. Once tagging is done, your sentiment analysis tool should conduct a syntactic analysis to correctly identify the topic customer is talking about. In reviews like “The restaurant on the beach was awful”, your tool should identify that all the feedback refers to restaurant, and not to beach, understanding the hierarchy relationships between words.
  4. The last part is semantic analysis: the platform employs a fully curated set of semantic dictionaries, tailored for the needs of different domains. Additionally, these dictionaries can be modified and adapted by the user without Bitext’s assistance, thus giving the user full power over their results.

Bitext sentiment analysis sample

Thanks to our NLP approach for sentiment analysis, Bitext can make correct analyses where other tools fail. Find below some example of this:

  1. Correct selection of topics:

Took my twins for their birthday, and the food was awful.

Correct topic: "food"; Incorrect topic identification "twins", "birthday".


  1. Merge of topics and sentiments associated to them.

All the starts and appetizers were incredible and the lasagna was mouth-watering.

“Incredible” refers to starts and appetizer and “mouth-watering” refers to lasagna.


  1. Correct sentiment assignment based on context

 High quality (as positive) vs High price (negative)


  1. Correct identification of sentiment expressions (not just words)

 The service I received from ACME restaurant was beyond the call of duty. (positive)

Waiters services were by no means the worst ones I have ever seen. (negative)

The hotel spa services were second to none. (positive)


If you want to have a look at our sentiment analysis tool, you just have to register on our API platform, and go to Sentiment Analysis menu option. There you could try how it works by  introducing a review sample to be analyzed. Easy as pie.




New call-to-action

Subscribe to Email Updates