IBM Watson Marathon Match: Live Now!

Data Science Challenge: Use IBM Watson to Predict Customer Reviews is live. Click here to compete.

Online reviews and ratings have become standard reference points for products and services, that we avail in our everyday lives.

However, these reviews are widely subjective, depending on individual customer experience(s). Most online reviews have two components: a specific and objective star/rating system and the more elaborate comment section which lets past customers detail the the pros and cons of the product and/or services they availed.

In this Data Science challenge, you have to Use IBM Watson to Predict Customer Reviews attempts to correlate the comments left by customers with the review scores for a given seller and/or service provider. You will be required to develop a sentiment analysis/evaluation for a service that allows individuals to rent part of their property for short-term, temporary residence by visitors.

The means to do the analysis will be left to you. Feel  free to take reference from the following scenarios; or you can create your own data set to come up with a more accurate feedback system for probable future customers for the service concerned.

  • Keywords or sentiment analysis of the title and description associated with each listing
  • Sizing, pricing, or other details associated with each listing
  • Geographical considerations
  • Comparisons between similar described/located properties
  • Number or and/or recency of reviews that have been left
  • Keywords or sentiment analysis of the reviews themselves

If you are not a part of the Topcoder Community yet, join now to participate in this challenge.