Text Classification

The Text Classification component enables the user to classify text into various classes also providing accuracy for the same.


  1. Make sure Intellibot Machine Learning Plugin is installed. Refer Installing Plugins documentation for details.

  2. In Toolbox, expand Machine Learning. Drag and drop Text Classification connector to Global Objects.

  3. Save the project on your machine. The ML model will be generated in the same directory.


  1. To configure Text Classifier, expand Global Objects, right click on TextClassifier and select Configure.

  2. The Text Classifier Model screen opens. User can add Text Classes as per the project requirements by clicking on the plus sign next to the Text Class. For example, let’s add business, entertainment, politics, sport and tech as class names. All the text classes will be available to view under dropdown menu of Text Class.

  3. After the Text Class is created, the user can import text samples in .txt form individually or add in a consolidated excel format with different text class. The user has 2 options to clear data, the Clear button on the extreme top left will clear all text samples for all classes, while the other Clear button will clear text samples individually for each class.


  4. Once the text for all the classes are imported, next step is to train the model by clicking on Train section of the Text Classification Model Designer.

Training the Model

  1. The Train tab will expose the Classifier Settings which the user can change as per the requirements. Alternatively, the user can train the model with the default settings.

  2. Click on Train. After the model is trained it will show the model accuracy. The user will be able to see the image classification of test data with respective confidence levels.


  3. Depending on the model accuracy the user can decide to tweak the Classifier Settings and retrain the model.

Testing the Model

  1. Click on Test tab which will help the user to test the created model with test data.

  2. Click on Import button to add test text (s).

  3. Click on Test button. The classification result will be displayed with the accuracy percentage.


  4. Close the Text Classification Model Designer.

Using the Model

  1. Double click on the TextClassifier under Global Objects to expose the various components under Methods in Object Explorer.

  2. Drag and drop ClassifyText component to the design surface which takes a text as an input and returns the class and confidence predicted by the model.

  3. Drag and drop General> Message Box > Show component to the design surface.

  4. Double click on the Text Classifier tab to expose all the classes and connect the relevant class to the message box as shown in the screenshot.

  5. Connect this component to your automation flow.