Text Classification Activity
The Text Classification activity applies machine learning models to categorize text input into predefined groups or labels. This activity is used to automate tasks such as sentiment analysis, language detection, or support ticket routing by evaluating the content of the text against a trained model.
| Field | Description | Requirement |
|---|---|---|
| Model file name | The full file path or identifier of the pre-trained text classification model. | Required |
| Text | The actual string content or variable containing the text to be classified. | Required |
| Threshold | The minimum confidence score (between 0 and 1) required to return a valid classification label. | Optional |
| Response variable name | The variable where the resulting category label and its confidence score will be stored. | Required |
Action Types & Examples
Content Categorization
Identifying the intent or topic of a customer email.
- Format:
Text: "I would like to request a refund for my order." - Example Result:
{"label": "Refund_Request", "confidence": 0.89}
Implementation Examples
Field Setup
- Model file name:
C:\Robusta\Models\TicketClassifier.model - Text:
{{IncomingEmailBody}} - Threshold:
0.75 - Response variable name:
ticketCategory
Execution Parameters
- Process: The activity evaluates the input text using the specified model. If the confidence level is above
0.75, the most likely label is assigned toticketCategory.
Technical Notes
You need to train a model first to use this activity. You can ask for assistance from the support department for training your own model. Ensure the input text is pre-processed or cleaned of unnecessary noise (like HTML tags) to improve classification accuracy.