Sentiment score

Analyse, score, and classify messages. ThinkAutomation comes with an inbuilt sentiment analyser, so you can automatically grade messages based on constructs such as positive/negative. Then, you can automate subsequent actions based on the results.

Sentiment score – overview

• This baked-in ThinkAutomation action retrieves messages from any connected source and performs sentiment analysis on the extracted text
• The score will be returned as a number between 1 (maximum negative) and 100 (maximum positive)
• You can use the analyser to classify a message for any construct – for example, sorting sales enquiries from support enquiries
• ThinkAutomation includes built-in training data for common English positive and negative words, but you can also use custom training data to tune the analyser to your needs
• ThinkAutomation will return the sentiment score to a variable, to (optionally) fire conditional actions against the results as part of your workflows

Sentiment score – use cases

• Prioritise and escalate emails based on sentiment
• Send an SMS alert if an incoming email contains a high negative sentiment score
• Score emails for sales-readiness and email prospects to sales
• Segment customers based on satisfaction
• Automatically push positive feedback to a Teams channel
• Shortlist CVs based on keywords
• Plus countless more, depending on your desired use case