You can use project to classify or tag future data, so that it automatically does it for you.

How do you create a a project?

You can create a project by uploading a file in the Projects section or connecting your data from our Zendesk integration (more integrations coming soon).

Note that you will need to upload a CSV file with a valid date column in order to take full advantage of the Dashboard section of your project. We support the following dates formats: ISO-8601 (e.g.: 2019-11-20) and MM/DD/YYYY (e.g.: 11/20/2019).

What's the recommended file size or number of tickets to upload?

We recommend to connect at least 1,000 tickets or 200 calls to see value in a test and from historical 10,000 tickets or 2000 calls to build a reliable workflow.

Is there a maximum document size to upload?

Our Enterprise product doesn't have a size limitation, although it will be limited by the hardware that is running on, in case it is self-managed.

Can I upload short texts? What’s the minimum size of each unit of text?

The technology works well with short texts (tweets, chat conversations, etc…). However the dataset needs to provide enough context, so on average we recommend comments to have at least 5 words. Other short interactions will be identified as noise

Can I upload long texts or documents? What’s the maximum size of each unit of text?

The technology works well in long texts, however there needs to be a representative amount of texts to extract contexts.

How long does it take to generate a classifier to review?

It depends on the size of the file and the vocabulary. Usually it takes between 5-20 minutes for 5-20k comments. For a 200k texts file it takes about an hour.

Formats

What are the valid formats of the files to upload?

The current format is a plain text file encoded in UTF-8 with each text you need to analyze in a separate line or a CSV file. You can also directly connect data from our Zendesk integration (more integrations coming soon)

Can I upload voice data?

Voice data cannot be uploaded into the platform. You first need to do a speech2text process, Microsoft, Google, IBM and Amazon all have speech2text functionalities that can be easily accessed. We also work with partners in case you want a more tailored approach.

Did this answer your question?