In the 30 min recorded webinar below, we walk you through many of the key features and best practices to use and build text analysis models in MonkeyLearn, as well as how to connect them via add-ons and integrations.

MonkeyLearn offers two types of models to work with text: Classifiers and Extractors. 

Classifiers are used to group or tag data into a defined category (by sentiment, emotion, topic, etc.). 

Extractors are used to retrieve pieces of information (like keywords, entities, phrases, numbers, etc.). 

A number of pre-trained classifiers and extractors are already public and available for users.

Users can build their own custom models to fit the exact requirements of their business or process. Anyone can build a custom model with MonkeyLearn, no technical expertise or coding is required for the development or training. 

To make a custom model, MonkeyLearn will walk a user through a wizard where they can define categories and tag text data that will train their custom model. When enough text data is tagged, MonkeyLearn will offer statistics on the accuracy of the model.

Text can be processed manually by uploading a .csv or excel file to your models. MonkeyLearn will process the file and present it for download with the results included.

Automatic processing of text can be done through the MonkeyLearn API or by using the following:

We suggest these to help get your bearings. We understand that text analysis with machine learning can be daunting at first. 😉