This page is going to document how Impact is calculated, what we use to determine if a comment is positive or negative, and more, for Open Ended collections of data.

Question: I don't know what the numbers next to my topics mean

Answer: They are there to show you how much positive, negative, and neutral feedback that Topic has

For Open Ended collections of data, we don't have any key metric to use to display Impact. Instead, we display how much each topic is receiving positive, negative, and neutral feedback. Red bar for negative, green for positive, gray for neutral. The percentages next to those numbers display the sentiment for the TOTAL amount of feedback. Meaning, using the image below for reference, those negative comments from the General topic are basically 20% of ALL feedback in this collection.

Example Topics

Question: How is it determined if a comment is put into the Negative or Positive section of a Topic?

Answer: The sentiment found from the comment

Each time a comment is submitted to Lumoa, we will break those comments up into sentences. Those sentences are what we then use to analyze sentiment for a comment. We use a specially designed AI to look at comments like "I love your customer service" and we can then say that comment is both positive and about the "Customer Service" topic.

Note that some sentiment is stronger than others. A customer saying "I like your customer service" is weaker than a customer saying they love it. Assuming the amount of comments are equal, a topic can still have a higher Impact because the sentiment from those comments is stronger.

Question: How are the Impact numbers next to my Topics calculated?

Answer: The Impact is based off of the amount of associated feedback and the sentiment of those feedback

A higher Impact means that there are more people talking about a certain topic, and it can also be when people talk about that topic they are talking about it with a more powerful sentiment. If a topic has a high amount of Impact, it means that it is a key driver based on the data in the collection. That lots of comments in the collection both mention this topic, and talk about it very powerfully.
Was this article helpful?
Thank you!