Datasets are sets of interactions from your contact center that have been transcribed (if voice) and parsed
Process of analyzing data and breaking it into parts.. They span a specific time period and match any filter criteria you specify. Interactions can come from voice calls, emails, chats, supported digital channels, or any combination of these.
For example, you could create a dataset from now to a week from today that includes contacts containing the phrase 'Rosings Park' but excludes contacts containing the keyword 'Collins'. The fields available when you specify your filter criteria provide AND, OR, and NOT options.
Maria Bertram is a data analyst in the Classics, Inc., contact center for the Mansfield Park brand of clothing. The contact center administrator has noticed that Classics seems to be losing younger customers lately to a new competitor, Fables Ltd. She wants to make sure none of the contact center agents are recommending Fables to these customers, since Fables recently introduced a new line that's receiving a lot of buzz in social media.
Maria creates a dataset for her administrator to analyze. She configures it for a period of the past 90 days. It includes interactions where the keyword "Fables" was mentioned, but excludes interactions where customer said that keyword.
Key Facts About Datasets
- Voice data becomes available as soon as the call is transcribed into text. This is typically one to two hours after the call ends.
- Email, chat, and digital interactions are available immediately after the interaction ends.
- If your company has Interaction Analytics for multiple languages, you can create datasets for the different languages. You cannot create a single dataset that includes interactions in more than one language.
- You can filter the data contained in a dataset based on keywords, phrases Combination of words that have special significance when used together in a specified order, such as "want to cancel"., or entities Defined keyword or phrase, with or without variants, in an interaction or message the interaction contain or do not contain. You can also choose which channels to include, and the period of time to cover.
- When you create a dataset, you can apply a category template Category groupings that help you use the data for a specific purpose. Out-of-the-box category templates include Intent to Buy and Risk Aversion. and a workspace template Multiple workspaces grouped as a reusable template. right from the dataset page.