Sentiment evaluation

Sentiment evaluation using the Smarter Appstore

Sentiment analysis is a methodology for analysing text data and classifying the sentiment contained within it. It is a useful technique for every customer facing industry (retail, finance, telco, utilities, etc) which needs to understand how consumers are thinking about them and their products, features and services. 

Sentiment analysis is a key feature in understanding and predicting churn, developing more accurate customer segmentations and creating recommender systems which have a good take-up of product and service offerings. 

Today, organisations have access to vast amounts of digital data from multiple platforms, including social media, review platforms, chatbots and influencer marketing campaigns, as well as internal CRM and Enterprise Marketing Systems. This heterogeneous data environment means that multiple types of sentiment model may be needed to truly understand customers, with different models used for understanding emotions, opinions, future intent or what aspects of a product or service are liked or disliked.   


Advances in sentiment models mean we can generate huge insight with predictive accuracy of over 96% on test data pre-processed with word embeddings and trained on rudimentary data samples of sentiment, but to date, building and using these models required specialist resources, big budgets and technical know-how. 

At Smarter, our Appstore has an area dedicated to sentiment analysis, from simple pre-trained models that work on the simplest datasets, to the most advanced neural based models that use emotion to predict a customer’s future intent. But the best thing is that they all run in the Smarter Appstore so anyone can experiment with the latest techniques, without the need for teams of data scientists, marketing agencies or guru’s.  

Smarter lets users build a portfolio of sentiment models, each focused on solving unique problems using all the customer data at hand.



27 August 2021


Please log in to comment

Other posts you might like