deepsight cloud · Intent analysis Sort comments by what people want.
Organize comments by intent – such as a complaint, praise, a question or an explicitly stated intention to cancel. Check every classification against the passage in the text.
One comment, two intents
“For three weeks the internet has kept dropping out in the evening, and I have reported the fault twice. If it isn’t fixed by the end of the month, I’m switching providers.”
Select an intent to see the passage.
Illustrative example.
What comments are sorted by
- Complaint
- Praise
- Question
- Feature request
- Bug report
- Intention to cancel
These are the standard categories; you can extend them or replace them with your own. One comment can express several intents. Typical tasks: forward questions to support, group complaints by topic, and look specifically at explicitly stated intentions to cancel.
Questions about intent analysis
Topics describe what someone writes about, such as delivery or price. The intent describes what someone wants: to complain, to ask something or to cancel. Combined with topic analysis, you see which intents are expressed for a topic.
No. It detects what is in the text, such as an explicitly stated intention to cancel. That is not a prediction, and there is no real-time monitoring with alerts. When an analysis is finished, deepsight can notify you by email.
That depends on your texts and categories, so we do not quote a fixed hit rate. Intents that are stated indirectly or ironically are harder to classify than explicit ones. Check classifications against the passage in the text before you pass comments on.
Yes. Analyze responses in other languages, too: an integrated translation (AI-powered, or with DeepL or Google if you prefer) supports the analysis.
You can sort customer feedback from surveys, reviews and support tickets by intent, for example.
More features · Analyze responses
See the feature with your own data
We will walk you through the analysis using an example from your field.