GenAI Sentiment Classifier

The GenAI Sentiment Classifier enables customers to automatically analyze social media content and determine the sentiment conveyed within posts. It categorizes content into 3 predefined sentiment labels: Positive, Neutral, or Negative. This classification helps organisations gauge public perception, track customer sentiment, and identify emerging trends in real time.

Powered by Gemini 2.5 Flash Lite, the GenAI Sentiment Classifier delivers multilingual sentiment analysis with confidence scores, providing structured outputs for better decision-making and audience engagement.

Adding to your Dynamic Pipeline

This component can be seamlessly integrated into your Dynamic pipelines through the "GenAI Sentiment Classifier" component. It requires the following fields for configuration:

Destination Path (Required)

The "enrichment.sentiment" field is designated to store the sentiment classification output. This output includes a sentiment label — one of three possible categories:

• Positive — Expresses favorable opinion, satisfaction, or approval
• Neutral — Presents factual information without emotional tone
• Negative — Expresses unfavorable opinion, dissatisfaction, or criticism

Each label includes a confidence score ranging from 0 to 1, reflecting the model's certainty for the sentiment detected.

Target Text (Required)

This is the metadata field containing the input text for sentiment analysis. By default, it's set to content.body, but any field containing relevant text can be used. If the Gemini Model encounters safety issues with certain content, the API will fail to generate output.

Dynamic Pipeline Configuration Example

The following example shows a dynamic pipeline configuration for the GenAI Sentiment Classifier component. If Unify is the preceding step in your pipeline, you can set it up as follows:

• content.body from the input document is specified as the Target Text for the GenAI Sentiment Classifier
• enrichment.sentiment is designated as the Destination Path for storing the GenAI

Sentiment Classifier output

{
    "enrichment": {
        "sentiment": {
            "label": "positive",
            "confidence": 0.92
        }
    }
}

Compatible Languages

The GenAI Sentiment 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 sentiment classification accordingly. Sentiment labels are provided in English.

Powered by Google Gemini 2.5 Flash Lite, the language coverage includes all languages supported by the model. The language coverage is: