The most powerful aspect of MonkeyLearn is really in the ability of users to create a custom model for their own processes. 🚀
See a walkthrough video on building a classifier with tips and recommendations.
Five Steps to Build a Classifier
1. Start here to build a custom model, and then click "Classifier"
2. Import your text data by uploading files directly or connecting with an outside app.
If you are uploading data with previously defined tags, click the option at the bottom "Upload already tagged samples".
3. Selecting the columns containing the texts. This is the data you will build and test the model with. If you select multiple columns the data will be concatenated or joined together.
4. Define the tags you will use for the classifier. At least two are needed initially, more can be added at a later stage.
5. Tag each text that appears by the appropriate tag or tags. This will help train the model.
️Using a Trained Classifier
The classification model is now trained with the training data and tags you provided. It can be used to classify new text or be trained further.
Processing Text under the "Run" Tab
You can test your trained model by pasting in text and seeing what the predictions will be.
Or upload a file directly to process text in a batch all at once.
🔍 Building Further Accuracy
Go to the Build Tab to see options to further train the module by tagging more texts.
In Data, you can see all your text data, filter by tags, and select texts to perform bulk operations.
Once you have tagged enough text data, you can begin to see classifier stats in the Stats section. At the overall level, you will see data for Accuracy and F1score. Clicking on each tag will show you that tag's precision and recall, as well as keywords.
More on working with Custom Classifiers:
More on how to improve your custom classifier and make it more accurate: