New feature: Office 365 Advanced eDiscovery Optical Character Recognition

New feature: Office 365 Advanced eDiscovery Optical Character Recognition

Published On: May 8, 2017

Expires On: June 8, 2017

Advanced eDiscovery Optical Character Recognition (OCR) is a new Office 365 feature. You can begin using this feature today.

Advanced eDiscovery Optical Character Recognition (OCR) enables the extraction of text from images. OCR is supported for loose files, email attachments, and embedded images. This feature allows the powerful text analytic capabilities of Advanced eDiscovery; including near-duplicates, email threading, themes, and predictive coding to be applied to image files.

NOTE: Advanced eDiscovery requires an Office 365 E5 subscription for your organization. If you don’t have that plan and want to try Advanced eDiscovery, you can sign up for a trial of Office 365 Enterprise E5.

What do I need to do to prepare for this change?

With Advanced eDiscovery, you can better understand your Office 365 data and reduce your eDiscovery costs. Advanced eDiscovery helps you analyze unstructured data within Office 365, perform more efficient document review, and make decisions to reduce data for eDiscovery. You can work with data stored in Exchange Online, SharePoint Online, OneDrive for Business, Skype for Business, Office 365 Groups, and Microsoft Teams. You can perform an eDiscovery search in the Office 365 Security & Compliance Center to search for content in groups, individual mailboxes and sites, and then analyze the search results with Advanced eDiscovery. Note that when you prepare search results for analysis in Advanced eDiscovery, Optical Character Recognition enables the extraction of text from images. This feature allows the powerful text analytic capabilities of Advanced eDiscovery to be applied to image files.

Advanced eDiscovery streamlines and speeds up the document review process by identifying redundant information with features like Near-duplicates detection and Email Thread analysis. The Relevance feature applies predictive coding technology to identify relevant documents. Advanced eDiscovery learns from your tagging decisions on sample documents and applies statistical and self-learning techniques to calculate the relevance of each document in the data set. This enables you to focus on key documents, make quick yet informed decisions on case strategy, cull data, and prioritize review.

Why advanced eDiscovery? 

Office 365 Advanced eDiscovery builds on the existing set of eDiscovery capabilities in Office 365. For example, you can use the Search feature in the Office 365 Security & Compliance Center to perform an initial search of all the content sources in your organization to identify and collect the data that may be relevant to a specific legal case. Then you can perform analysis on that data by applying the text analytics, machine learning, and the Relevance/predictive coding capabilities of Advanced eDiscovery. This can help your organization quickly process thousands of email messages, documents, and other kinds of data to find those items that are most likely relevant to a specific case. The reduced data set can then be exported out of Office 365 for further review.

The following topics describe the setup and use of Advanced eDiscovery modules and features:

• Quick setup for Advanced eDiscovery: Helps you to get started with Advanced eDiscovery.
• Running the Advanced eDiscovery Process module: Enables the preparation of files from specified data sources.
• Analyzing case data with Advanced eDiscovery: Allows identification and grouping of Near-duplicate files and hierarchically structured groups of Email Threads.
• Managing Advanced eDiscovery Relevance setup: Allows the definition of parameters for Relevance processing.
• Using the Advanced eDiscovery Relevance module: Identifies and ranks files by Relevance scores, which assists with early case assessment, document culling, and review.