- Enable the v5 beta.
- Edit your data spreadsheet's column headers to represent the data/metadata (see below).
- Save your spreadsheet in the comma-separated value (CSV) format.
- Create a new project using this spreadsheet. To learn what you can do with v5 metadata, see Learn More: Luminoso Analytics v5 beta.
Analytics v5 accepts the following kinds of data and metadata:
Text data is the only required data column in any Luminoso project. (Individual rows may have blank text entries.) This is the language data for analysis. Analytics accepts only one text column per spreadsheet.
Label your categorical metadata with the column header “string_[FIELD]”. The FIELD designates the metadata group (e.g. “string_Country of Origin”). You may have multiple string columns, with as many values as needed, but will only be able to filter on fields with up to 100 values.
Label your numeric metadata with the column header “number_[FIELD]”. The FIELD designates the numeric metadata by group (e.g. “number_NPS” or “number_Customer Age”). Numeric metadata is filtered by specifying a range in the filter tool.
If you have relatively few discrete values (e.g. star ratings, NPS scores) and would prefer your numeric data to be represented as a list of checkboxes, you can label them as string metadata (see above).
Analyze trends by adding one or more columns of date metadata to your project. We accept most standard date formats (excepting DD/MM/YYYY).
You can add a title or identifier to each piece of text data. The title will be viewable but not analyzed with the text data.