Subscribe to DSC Newsletter

Impactful text analytics for smarter businesses

RATINGS ARE OVERRATED

Service is great, but the desserts are bad”. Overall rating 4.5/5.

Many times we have gone into a restaurant alone or in a group, came out happy and still rated it a 3 or a 4 on social media. Does any one check why 2 precious points were deducted? No one will read your review unless the overall rating dips below 3.5. Is it an healthy practice? Of course not.

Frankly, no one is to blame except the rating scales and NPS scores. These two have been used a lot by brand managers to showcase health of their brand. 80%? Brilliant. 70%? Increase it to 80%, and the cycle continues. The illusion of well being is driven by how close you are to your minimum rating threshold, not necessarily focused on the shortfall to 100%. In all this calculations, we miss the important clue to decode brand health staring at our face – the customer reviews.

This brings me to my most important hypothesis visualized below;

Visualizing customer loyalty and insights potential on ratings

Visualizing customer loyalty and insights potential on ratings

With decreasing number of stars, the probability of the guest coming back decreases a lot. However, most importantly, the restaurant owner has the most scope for extracting valuable snippets of insights from customer reviews with ratings between 3-4/5.

SENSITIZING THE PRACTITIONERS

I recently had a chance to deliver a talk in a conference titled ‘Understanding Consumers in the Digital World’, held at IIM Lucknow, Noida Campus on 16-17th November 2015. The audience mainly comprised of marketers, market research professionals and academics whose work is primarily focused on obtaining deep insights by understanding the online consumers.

My talk was titled ‘Decoding Ratings for superior service in restaurants – Using text to understand customers’. The focus was quite simple – convince and demonstrate how to read and understand customers from their reviews, not ratings. Our product, Lunchbox, a complete restaurant management solution was showcased as well. It provides restaurant owner cues for exceptional customer service. Millions of reviews for almost one lakh restaurants have been processed and can now be used for market scenarios, competition analysis, transactional information and customer profiling.

Multiple techniques of text analytics – pre-processing, machine learning, topic extraction, ontology management and sentiment analysis were discussed to present how they can be used in this age of unstructured text data for customer insights. A detailed Q&A session followed where these techniques were explored in detail in the context of Lunchbox and restaurants’ management. Such sessions go a long way in sensitizing the practitioners of the current work going on and go a long way in prolonging innovation through a symbiotic feedback system.

Slideshare link with the presentation : http://www.slideshare.net/manasrnkar/mining-customer-reviews-to-dec...

Views: 1422

Tags: data science, machine learning, natural language processing, text analytics

Comment

You need to be a member of Data Science Central to add comments!

Join Data Science Central

Videos

  • Add Videos
  • View All

© 2019   Data Science Central ®   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service