Analytics categorization set tab

Using categorization, you create a set of example documents that Analytics uses as the basis for identifying and grouping other conceptually similar documents. Categorization is useful early in a review when you understand key concepts of a case and can identify documents that are representative examples of these concepts. As you review documents in the Relativity viewer, you can designate examples and add them to various categories. You can then use these examples to apply categories to the rest of the documents in your workspace.

Unlike clustering, categorization allows documents to be placed into multiple categories if a document is a conceptual match with more than one category. Many documents deal with more than one concept or subject, so forcing a document to be classified according to its predominant topic may obscure other important conceptual content within it. When running categorization, you can designate how many categories a single document can belong to (maximum of five). If a document is placed into multiple categories, it is assigned a unique rank for each.

Categorization is the backbone of the Relativity Assisted Review workflow. When documents are categorized, Analytics maps the examples submitted to the concept space, as if they were a document query, and pull in any documents that fall within the set threshold. However, when you have multiple examples, the categorized documents consist of the combined hits on all of those queries. These results return with a Rank, representing how conceptually similar the document is to the category.

Categorization is most effective for classifying documents under the following conditions:

This page contains the following content:

Identifying effective example documents

Each example document conceptually defines a category, so you need to know what your categories are before you can find the most appropriate example documents. Keep in mind that a category doesn't have to be focused around a single concept. For example, a category might deal with fraud, but different example documents for the category might reflect different aspects of fraud, such as fraudulent marketing claims, fraudulent accounting, and fraudulent corporate communications.

Example documents define the concepts that characterize a category, so properly defining example documents is one of the most important steps in categorization. In general, example documents should be:

back to top

Creating a categorization set

To create a categorization set, perform the following steps:

Note: You must have an Analytics index set up before you can create a categorization set.

  1. Create a saved search with the documents you want to categorize. See Searching for details.
  2. Under Indexing & Analytics, click the Analytics Categorization Set tab.
  3. Click New Analytics Categorization Set. The Analytics Categorization Set Layout appears.
  4. Complete the fields on the Analytics Categorization Set Layout to create the set. See Fields. Fields in orange are required.
  5. Click Save to save the categorization set.

Fields

Job information

The following information is displayed in the Job Information section of the Analytics Categorization Set Layout:

If you don't populate the Categories and Examples Source field on the set, and you haven't linked any categories or example objects to the set, no buttons on the console are enabled. Console buttons only become enabled after you add at least one category and one example object to the set. See Adding new categories and examples through the layout and Adding new categories and examples through the viewer.

back to top

Adding new categories and examples through the layout

If you choose not to make a selection for the Categories and Examples Source field on the categorization set, you can manually add new categories and assign example documents to a set using the Analytics Categorization Set layout.

Adding a new category through the layout

To add a new category from the layout, perform the following steps:

  1. Click New in the Analytics Category heading. The Add Analytics Category layout displays.
  2. Complete the fields on the layout.
  3. Click Save. The category is now included in the categorization set.

Adding a new example through the layout

You can add an entire document or a chunk of text as an example. To add a new example from the layout, perform the following steps:

  1. Click New in the Analytics Example heading. The Add Analytics Example layout displays.
  2. Complete the fields on the layout. Fields in orange are required.
  3. Click Save. The example is now included in the set.

back to top

Adding new categories and examples through the viewer

You can add categories and examples using the viewer instead of the Analytics Categorization Layout. You can add an entire document or a text excerpt from the document as an example.

Adding a new category through the viewer

To add a new category from the viewer, perform the following steps:

  1. Select a document from the document list and open it in the Relativity viewer.
  2. Right-click inside the document to display the menu options.

  3. Hover over Analytics Categorization, then select either Add Document as Example or Add Excerpt as Example to display the Add Analytics Example layout.
  4. Click Create New Category on the Add Analytics Example layout. The Add Analytics Category layout displays.
  5. Complete the fields on the layout.
  6. Click Save. The category is now available for selection in the Add Analytics Example layout.

Adding a new example document through the viewer

To add a new example document from the viewer, perform the following steps:

  1. Select a document from the document list and open it in the Relativity viewer.
  2. Right-click inside the document to display the menu options.
  3. Hover over Analytics Categorization, then select Add Document As Example to display the Add Analytics Example layout.
  4. Complete the fields on the layout.
  5. Click Add Example at the top of the layout to add this document as an example.

Best practices for adding example documents

Adding a new example excerpt through the viewer

To add a new example excerpt from the viewer, perform the following steps:

  1. Select a document from the document list and open it in the Relativity viewer.
  2. Highlight a section of text, and right-click to the display menu options.
  3. Hover over Analytics Categorization, then select Add Excerpt As Example to display the Add Analytics Example layout.
  4. Complete the fields on the layout. Fields in orange are required.
  5. Click Add Example at the top of the layout to add this excerpt as an example.

back to top

Adding new categories and examples automatically

If you haven't manually created any categories or examples, but you have populated the Categories and Examples Source field on the categorization set, the Create Categories and Examples button is enabled on the console. You can use this button to automatically add new categories and examples to your categorization set.

When you click Create Categories and Examples, Relativity clears all existing categories and examples and generate new ones. Examples are created from every document with a designation of Yes for the field selected as the Example Indicator Field on the categorization set.

During creation, the Create Categories and Examples button changes to Stop Creation, which you can click to stop the process.

Once category and example creation is complete, the Analytics Category and Analytics Example associative object lists reflect the results.

back to top

Categorizing documents

When you have assigned categories and examples to your categorization set, the Categorize All Documents button becomes enabled on the Categorization Set console.

Clicking this button kicks off a categorization job based on the settings specified when you created the set. When you run a new categorization job, all results of the previous categorization job are deleted.

To begin categorizing, click Categorize All Documents. When the confirmation message appears, asking you if you want to run categorization, click OK.

Note: kCura recommends running only two categorization sets at once for optimal performance.

Once the categorization has been kicked off, the following options are enabled in the Categorization Set console:

After the initial categorization process is complete, or after you have clicked Stop Categorization, the following button is enabled:

When you run a categorization set, the system creates the Categories - <name of categorization set> and Category Rank fields. Use Categories - <name of categorization set> to view the search results. Use Category Rank to see how closely related documents are to the category. See Viewing categorization results in the field tree and Searching on categorization resultsfor details.

Note: The Pivot On and Group By fields are set to Yes by default for all Categories - <name of categorization set> and Category Rank fields. For Categories - <name of categorization set>, you can change the Pivot On and Group By to No; however, you can't change the Category Rank fields to No. When you run a categorization set, all previously created Pivot On and Group By fields for Category Rank change to Yes.

back to top

Viewing categorization results in the field tree

After a categorization job is completed, you can view the results in the field tree. All category set names are appended with the word "Categories" in the format Categories - <name of categorization set. Click + to display a list of categories in the set.

In this example, one of the categorization sets is named Categorization Tutorial, which contains the categories Investments, Accounting, Fraud, and so on.

back to top

Searching on categorization results

The fields created by your categorization set are available as conditions when you create a saved search, which allows you to search on them and review the results.

To create a saved search to see your categorization results, perform the following steps:

  1. Display the Saved Search form. See Searching.
  2. In the Conditions section, select Categories – <name of categorization set> from the Field drop-down.
  3. Select these conditions from the Operator drop-down.
  4. Click in the Value field. Select the value(s) you want to review. See Searching.
  5. Click Save & Search.
  • Review the results of the search. The saved search displays the same number of documents that you would see by filtering in the field tree.
  • back to top

    Send us feedback down arrow