MonkeyLearn

Raul Garreta

All about classifier models and how to build your own custom classifier

What it means to classify text data based on content

How tags are created and how classifier training works

Showing you each step to build and train a machine learning model to classify text with the tags you define

How to upload historical data, or data that has already been classified, to build and train a new classifier

See this walkthrough to see how custom classifiers work. We will give you a data set and the list of tags to define.

How to add more training samples to improve your classifier accuracy.

Understanding the statistics for Accuracy, F1 Score, Precision and Recall of your custom classifier

When working on a classifier, you should focus on working on improving the tags with the lowest precision and recall.

Tagging mistakes have a profound impact on the accuracy of your classifier. Here we show you how to find these mistakes and fix them.

Tagging consistency is critical for training an accurate classifier.

What to do when you want to improve these classifier metrics

How to test and fine-tune your custom classifier using keywords and tags

Best practices and recommendations for defining tags and taxonomies when making a custom classifier

Find out how much text data is required to build a classifier, how clean it should be, and why tagging text is necessary for training.

Multi-tag classifiers can return 1 tag, 2 tags, or 3 tags, or even no tags at all when it thinks that the text doesn't belong to any tag.