HANDS ON SharePoint
HANDS ON Teams
HANDS ON Lists
HANDS ON tek
M365 Admin
Communication Compliance: Prioritize analysis of policy-driven alerts with Azure Cognitive Services (public preview)
Coming soon to public preview, Communication Compliance will support Azure Cognitive Services text analysis, helping customers’ compliance managers prioritize and investigate alerts related to violations of their organizations’ defined regulatory requirements. Using Azure Cognitive Services, this update helps investigation of potential regulatory incidents by providing customers more context. Only messages that have already triggered an alert in an existing Communication Compliance policy will be analyzed.
This message is associated with Microsoft 365 Roadmap ID 88918.
When this will happen:
Public preview: Will begin in early December and is expected to be complete by mid-January.
How this will affect your organization:
Azure Cognitive Services provides machine learning capabilities to analyze text for sentiment using a pre-trained model. Leveraging Azure Cognitive Services, messages already matching policy conditions will be categorized in “positive,” “negative,” or “neutral” sentiment, giving policy investigators more context to prioritize potentially riskier messages to address first.
This sentiment context will appear as a sentiment column in the “Pending” view of Communication Compliance without any setup required, however admins will have the ability to remove the sentiment column from view by going to the “Customize columns” action and choosing to enable/disable the column.
What you need to do to prepare:
Access the Communication Compliance solution in the Microsoft Purview compliance portal.
Learn more:
Microsoft Purview Communication Compliance provides the tools to help organizations detect business conduct and regulatory compliance violations (e.g. SEC or FINRA), such as sensitive or confidential information, harassing or threatening language, and sharing of adult content. Built with privacy by design, usernames are pseudonymized by default, role-based access controls are built in, investigators are opted in by an admin, and audit logs are in place to help ensure user-level privacy.
Message ID: MC481197
No comments yet