Analysis

Aim: For litigation teams to be able to make informed decisions about strategy and scope through reliable methods based on verified data.

As data volumes increases and time frames continue to diminish, the need for technology assisted review picks up pace. Apogee deploy Relativity and utilise, to the full extent that our clients require, a suite of tools designed to help lawyers cut through the mass of documents.

Relativity Analytics amplifies your review efforts with powerful text analytics technology. With Analytics, you can visualise and sort your documents by concept, allowing you to increase your doc-to-doc review speed and improve accuracy. Use Analytics for email threading, foreign language identification, near-duplicate detection, and more – helping you make sense of your data quickly. Understand how documents and keywords are related, move quickly, and follow an investigative pattern of thought to dig into the real substance of a case.

Apogee FTE Analysis

Relativity Assisted Review combines text analytics technology and workflow, allowing users to train Relativity to identify responsive and non-responsive documents. While reviewers code documents as they always have, Assisted Review uses their expertise to make decisions on the rest of the documents in a collection. The quality and effectiveness of these decisions are demonstrated through an iterative QA process using statistics. Because human experts validate the decisions made by the system using statistics, reviewers retain the control, flexibility, and transparency needed for an accurate and defensible review.

The suite of Relativity analytics features includes:

Email Threading
Email threading is a text analytics feature that works behind the scenes to detect all emails in a single conversation and organise them for faster review. With email messages grouped together, conversations are organised in a way that’s easy to understand and batch out to reviewers.

Near Duplicate Detection
Text analytics can identify documents that are nearly identical, such as multiple versions or drafts of the same document, so you can focus your efforts on those documents at once. Near-duplicate identification saves you time when tagging highly similar documents with the issues in your case.

Foreign Language Identification
Text analytics can detect the languages that exist in a document and tag the document with those languages. Documents can then be organised by language, so you can quickly batch them out to translators or reviewers fluent in those languages. Relativity analytics can identify 173 languages. A single document may contain more than one language so Relativity will detect a primary language and up to two secondary languages.

Concept Searching
Allows you to enter a block of text and return conceptually correlated records.

Assisted Review
Leverages a small group of documents reviewed by a high level reviewer to execute a first pass review by the system. Relativity Assisted Review combines text analytics technology and workflow, allowing users to train Relativity to identify responsive and non-responsive documents. While reviewers code documents as they always have, Assisted Review uses their expertise to make decisions on the rest of the documents in a collection. The quality and effectiveness of these decisions are demonstrated through an iterative QA process using statistics. Because human experts validate the decisions made by the system using statistics, reviewers retain the control, flexibility, and transparency needed for an accurate and defensible review.

Find Similar Documents
Returns conceptually correlated documents based on an entire document.

Categorisation
Finds similar documents based on a set of example documents.

Clustering
Group’s conceptually similar documents, without the need for example documents.

Repeated Content Identification
This filter removes the text in a document that matches your configuration parameters. You can use this filter to remove content such as confidentiality footers or standard boilerplates from documents. This text does not contribute to the conceptual content of the document, so it should be removed to prevent the Analytics engine from discovering unwanted term correlations.