MonkeyLearn is a Machine Learning platform for Text Analysis. It allows our users to easily get actionable data from raw text. For example, you can detect topic or sentiment expressed in texts like tweets, chats, reviews, articles and more.
- A Graphical User Interface that allows users to easily create and test customized machine learning models to solve particular problems.
- Publicly available and pre-trained models for common problems (sentiment analysis, topic detection, etc).
- A scalable cloud computing platform where machine learning algorithms can be trained and ran instantly without installing or deploying any software.
- An API and SDKs (Python, Ruby, Node, Java and PHP) that allows users to integrate the MonkeyLearn cloud computing engine with any software project, using any programming language.
- A documentation and blog to provide additional content around guides and use cases.
One of the stand-out features in MonkeyLearn is that you can train an highly dependable Machine Learning model on the fly with your particular data. More accuracy is gained by using texts from your own domain, and building a model with your specific criteria in mind.
Models in MonkeyLearn are organized into two families:
- Classification: models that take text and return labels or categories.
- Extraction: models that extract particular data within a text.
Much of the documentation and terminology in our platform will refer to classification models as classifiers, and to extraction models extractors.