GenAI Emotion Detection Classifier

AI emotion detection classifier that identifies emotions (Happiness, Sadness, Anger, Fear, etc) in multilingual content with confidence scores.

The GenAI Emotion Detection Classifier analyzes and detects emotional tones within content, enabling businesses to understand audience engagement patterns and public perception at scale. This model categorizes emotions such as Happiness, Sadness, Anger, Fear, Surprise, Disgust, and Neutral, providing real-time and batch-processing capabilities for improved decision-making.

Powered by Google Gemini 2.5 Flash Lite, this component leverages advanced NLP techniques to analyze text and contextual cues across multiple languages.

Adding to your Dynamic Pipeline

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

Destination Path (Required)

The "enrichment.emotion" field is designated to store the emotion classification output. This output includes an emotion label—one of seven possible categories (Happiness, Sadness, Anger, Fear, Surprise, Disgust, or Neutral), alongside a confidence score ranging from 0 to 1, reflecting the model's certainty for each emotion detected.

Target Text (Required)

This is the metadata field containing the input text for emotion analysis. If you are using Unify, you can set to content.body, but any field containing relevant text can be used.

Safety Notice

If the Gemini Model encounters safety issues with certain content, the API may fail to generate output.

Filter Condition

This component processes all documents that contain the configured text field. Documents without the specified text field will be skipped.

Compatible Data Sources

As a Post-Processing operation, it can be run on any data source containing text content, including:

  • Social media content
  • News articles
  • Reviews
  • Blogs
  • Forums

Sample Output

The classifier adds a new metadata section within the "Enrichment" section, along with the predicted confidence level. Here is the sample JSON output:

"enrichment": {
    "emotions": {
        "label": "Happiness",
        "confidence": 0.87
    }
}

Compatible Languages

The GenAI Emotion Detection 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 emotion classification accordingly. Emotion labels are provided in English. Language coverage is continuously improved as this component uses Google Gemini 2.5 Flash Lite in the back end. Supported languages:

LanguageLanguage ID (ISO-639)
Arabicar
Bengalibn
Bulgarianbg
Chinesezh
Croatianhr
Czechcs
Danishda
Dutchnl
Englishen
Estonianet
Finnishfi
Frenchfr
Germande
Greekel
Hebrewiw
Hindihi
Hungarianhu
Indonesianid
Italianit
Japaneseja
Koreanko
Latvianlv
Lithuanianlt
Norwegianno
Polishpl
Portuguesept
Romanianro
Russianru
Serbiansr
Slovaksk
Sloveniansl
Spanishes
Swahilisw
Swedishsv
Thaith
Turkishtr
Ukrainianuk
Vietnamesevi