The AI Brand Recognition Classifier for social media is designed to identify and track brand mentions within social media content. This model efficiently detects brand names across various languages, providing valuable insights into brand visibility and reach. Optimised for real-time and batch processing, it’s a powerful tool for monitoring brand presence, engagement, and trends at scale.

Adding to your Dynamic Pipeline

This component can be added to your Dynamic pipelines through the "AI Brand Recognition" component. It requires the following fields for configuration:

• Destination Path (Required): The "enrichment.brands " field holds the output from the AI Brand Recognition Classifier. But you can map it to another field or create a new one. This field will contain recognised brand names in an array.
• Target Text (Required): The metadata field containing the input text for brand recognition. By default, this is set to content.body, but any field containing relevant text can be used.

If the Gemini Model encounters safety issues with certain content, you will find that Gemini API failed to generate output.

Dynamic Pipeline Example Configuration

The example below demonstrates the dynamic pipeline configuration for the AI Brand Recognition Classifier component. If Unify is the preceding step in your pipeline, you can set it up as shown in the example:

• content.body from the input document is specified as the Target Text for the AI Brand Recognition Classifier.

• enrichment.brands is designated as the Destination Path for storing the output of the AI Brand Recognition Classifier.

  

  
  

Sample Example Output

Compatible Languages

The Micro Classifier supports content in multiple languages. When the input text is in a language other than English, the component automatically detects the language and performs the brand classification accordingly. The language coverage is continuously improved as this component uses Google Gemini 1.5 Flash in the back end. Referring to https://ai.google.dev/gemini-api/docs/models/gemini#gemini-1.5-flash the language coverage is: