Documentation / Product / Features / Content Affinity Engine

Content Classification

The Content Classification dashboard provides visibility into how your content is being scraped, indexed, and classified by the Lytics Content Affinity Engine. The end goal is to deliver personalized content recommendations and product recommendations, but to get there, you must start by making sure your account has proper content hygiene. This will allow you to build relevant Content Collection that serve as the foundation for your marketing use cases.

Domain and Path Settings

The Domain and Path Settings displays important account information to verify that Lytics is classifying the right content that will be used in your marketing initiatives. To adjust what content gets classified, your account admin can specify the list of approved domains and ignored paths via your Lytics Content Settings.

lytics-domain-path-settings

  • Classification Quota - the progress bar indicates how your account is tracking towards the monthly classification quota, which is set to 20,000 documents per month by default.
  • Approved Domains - any URLs that contain one of the approved domains will be classified. This list should include the primary domains for your company. Examples for Lytics include lytics.com, `learn.lytics.com, etc.
  • Ignored Paths - any URLs that match at least one of the ignored paths will not be classified. Examples of ignored paths include /blog, /search, /userprofile, etc.

Classification Activity

The Classification Activity module shows the number of documents that have been classified for your account in the last week. You can also adjust the chart to see the distribution of classified documents in your account throughout history to help you understand if and when you are hitting the monthly quota for your account.

classification-activity-module

The Lytics Content Engine is controlled by multiple workflows that run in the background. The workflow that classifies content runs hourly, so you can expect to see updates to your classification activity every hour, so long as you have not met the quota this month.

Document Health

The Health module surfaces a list of content that Lytics is unable to classify due to its “unhealthy” state. It's important to review your unhealthy documents to make sure the content needed for your marketing campaigns is in a state where it can be leveraged for personalized recommendations.

Lytics defines document health based on HTTP status codes. A status of 200-399 is considered “healthy” and 400+ is considered “unhealthy”. You can use the Preview option to examine the page and make adjustments as needed before requesting Lytics to manually reclassify the page.

classification-doc-health-status-code

If you want to search through all of the documents Lytics has indexed on your account, use the Find a Document section.

Manual Classification

The Manual Classification module allows you to preview how a single document will be classified by Lytics. You can use this to resolve any issues with how your page is set up before it’s added to the Lytics content corpus.

Simply enter the URL of the document you would like to preview and click Get Details. This will allow you to see things like topics extracted from the document as well as any metadata Lytics scrapes from the document.

lytics-manual-classification

Once you’re happy with the results of the classification, you can click Complete Classification to add it to the content corpus, the documents and its topics then become available for use in personalization such as recommendations or content affinity.