Sentiment analysis is useful, and important, for monitoring and improving customer experience. Customers’ feelings towards a brand can be influenced by a number of factors. Companies can resort to sentiment analysis to go through product or service reviews, for example, and attribute a score to each of them, allowing customer service agents to reach out to the customers with the most negative opinions first and try to defuse the bad situation as soon as possible. As for the reviews with more positive scores, these allow for companies to understand what actions trigger positive emotions on customers as a benchmark going forward.

What it does

Jira Issue Analyzer is an Atlassian forge app that helps businesses analyze sentiment of Jira Issues and categorizes the issue into Positive, Negative or Neutral.

This can help customer service agents to turn their attention to the most frustrated or dissatisfied customers without having to go through each of the issues in the queue manually to assess their priority.

The app can be used by support managers to measure customer's or reporter's overall satisfaction with their support team.


How we built it

We built it using Atlassian Forge, Forge UI, Confluence APIs and Natural Language Processing.

Accomplishments that we're proud of

We were able to build apps very fast using Forge was very easy. It was a great learning for the both of us. We would definitely love to build more apps for Atlassian Products using Forge.

What we learned

We learnt how Atlassian Forge could be used to build apps for Atlassian Cloud products. Building the app using Forge was a great experience as it does most of the work for you. All we need is to code!

What's next for Jira Issue Analyzer

  • Extend the capability to Confluence.
  • When Forge adds more capabilities, we would like to extend the capability of this app to Analyze the sentiment of the response written by a Support Agent. Agent can use it to check if any negative words have been use and then enhance the response to be more positive.
Share this project: