The text ($Text) of notes is scanned to extract information that might be useful for agents. These results include:
- $NLNames: a set of personal names found in the text.
- $NLOrganizations: a set of the names of organisations found in the text.
- $NLPlaces: a set of place names found in the text.
- $NLTags: a set to hold annotations automatically generated using Natural Language Processing. The first such annotation adds the tag 'plan' to notes that Tinderbox believes might represent a planning note, such as "remember to deposit the cheque" or "remind the freshers to begin planning their module essays".
- $DominantLanguage: Tinderbox's guess at the primary language used in the text of each note; stored as two-letter ISO-639-1 codes such as “en” for English, “de” for German, and “zh” for Chinese.
Note that these result values are extracted automatically and are thus subject to a variety of extraction errors.
Results are extracted from the $Text of:
- New notes.
- Re-edited notes, including pre-existing notes in old TBXs that have be re-edited.
Values are not extracted from pre-existing notes, such as in files created, unless they are subsequently re-edited.
This process may store some working files in the application support 'analytics' folder. These should not be edited by users.