In your Models view, click the Actions button and select Create Classification Model
You will be taken to a page that will help guide you through how to define various parameters needed to build a classification model.
Step 1. Adding Classes & Training Data Using Text Documents
Click Add Class in the Step 1: Add Classes panel
A new modal will pop up for adding your class. Provide the label you want for this class (e.g. “review” for systematic literature reviews)
Next, you’ll want to narrow your view to display only documents you want to be reviewed. This will build out a ground truth training dataset for the classification model to train on. Employ the filters as seen in Document Sets to assist you in this process. Check out the Boolean tips page to learn more about conducting searches for narrowing the document set.
Example
In the photo above, we used an annotation provided through PubMed that identifies a document as a review, systematic review, editorial, etc. We used the values “review” and “systematic review” to make a class with ~61K document samples (see bottom left for the total number of documents in your class’ set).
When your class set is ready, you can click Save to save those documents into the training dataset for the class (in this example, the class is “review”)
Continue to add however many classes as you need for your classification model. When ready, we’ll proceed to the next step: customizing parameters
Step 1a. Adding Classes & Training Data Using Spreadsheets
Click "Select Spreadsheet".
Choose a spreadsheet you already have uploaded or drag and drop a spreadsheet to upload it.
Choose the column that contains the class names.
Choose the column that has the training values.
(OPTIONAL) Enabled Multi-Label if you have setup the class column with multiple classes.
💡 Pro Tip - It’s best to keep the number of examples for each class as close to equal as possible (this is known as balancing your classes). This ensures that your training run is not biased towards classes with a larger number of examples.
Step 2. Providing Customized Parameters
Once you have solidified your classes, you have the option to adjust any model parameters used during the model training. We also have defaults if you want to skip this step and use the base parameters instead.
See Classification Model Parameters for descriptions of each advanced parameter option.
Step 3. Commence Build!
You're all set to submit the classification model job. Push that button!
Click the Train Model button in the third panel
Upon clicking Train Model, you’ll be asked to name your new model
Click Save. Your model will begin automatically building, using the training datasets and parameters you have defined. You can leave or close out of this page and return at any time by clicking on your classification model’s name from the Models tab
Note: If you plan to do multiple iterations of the model, we suggest having some versioning in your name (e.g. “Publication Classification V1”, “Publication Classification V2”, etc.).
When the model is done building, this page will automatically update to show you the model’s performance results, which were run on the test set you determined in your parameters portion of the training (see: Test Set Size in Classification Model Parameters). You will see metrics for F1 score, precision, and recall, as well as a confusion matrix and average loss function visualization.
To learn more about these performance metrics, please see Classification Model Performance Metrics.