Diversity sampling for technology-assisted document review

A computer-implemented method to implement diversity sampling for technology-assisted review (“TAR”) of documents, comprising:

• identifying, using one or more computing devices, documents by a classification model;
• providing, using the one or more computing devices, the identified documents for review;
• receiving, using the one or more computing devices, an input of a label for each of the identified documents provided for review;
• logging, using the one or more computing devices, a found rate of presented documents labeled as relevant;
• determining, using the one or more computing devices and based on the found rate, to provide diversity in the documents that are identified by the classification model and provided for review;
• and
• providing, using the one or more computing devices, diverse documents for review with the identified documents that are provided for review.

A system to implement diversity sampling for technology-assisted review (“TAR”) of documents, comprising:

• a storage resource;
• and
• a processor communicatively coupled to the storage resource, wherein the processor executes application code instructions that are stored in the storage resource to cause the processor to:
• identify documents by a classification model;
• provide the identified documents for review;
• receive an input of a label for each of the identified documents provided for review;
• log a found rate of presented documents labeled as relevant;
• determine, based on the found rate, to provide diversity in the documents that are identified by the classification model and provided for review;
• and
• provide diverse documents for review with the identified documents that are provided for review.