Our main goal with MonkeyLearn is to make text analysis simple.

We want to enable developers, marketers, salespeople, customer support representatives and entrepreneurs without any knowledge or experience in natural language processing or machine learning to take advantage of these technologies by having access to a powerful, customizable and affordable platform for text analysis.

With these things in mind, users have two basic ways to use MonkeyLearn:

• Public Modules: pre-trained and ready to use modules for particular tasks, created by the MonkeyLearn team.
• Custom Modules: created by users for their specific needs.

By using public modules, users can have an easy and fast way to incorporate text analysis capabilities to their apps or workflows. Public modules are modules that have been already trained with training data and resolve particular text analysis tasks. They are ready to be integrated via a web API, Zapier or our Google Sheets integration.

These modules are implementations to common particular applications including:

General use:

• Language detection: detect language in text. New languages were added for a total of 48 different languages arranged in language families.

• Topic classification: classify text according to a broad and generic topic tree.

• Retail classification: classify retail products using their descriptions.

• News categorizer: classify news by topic.

• Business classifier: classify professional profiles or companies.

• Affinity profiler: classify users into affinity groups.

• Profanity & abuse detection: identify profanity or abuse in comments.

  • E-commerce Customer Support Ticket Classifier: classify customer service tickets into categories like fraud, missing item, shipping problem, etc.
  • NPS SaaS Product Classifier: classify NPS responses into categories like usability, features, pricing and customer Service.
  • Outbound Sales Response Classifier: classify outbound sales email responses based on subject and body.

Sentiment Analysis:

• Tweets Sentiment (English): classify tweets in English according to their sentiment: positive, neutral or negative.

• Tweets Sentiment (Spanish): classify tweets in Spanish between positive, neutral and negative sentiment.

• Product sentiment: classify product reviews and opinions in English as positive or negative according to the sentiment.

• English tweets products sentiment analysis: sentiment analysis for tweets about products and brand reviews.

• English tweets Apple products sentiment analysis: sentiment analysis for tweets about Apple products comments.

• Hotels sentiment: this sentiment analysis classifier was trained with data from different hotel review sites.

• Movies sentiment: this sentiment analysis classifier was trained with data from movie review sites.

• Restaurant sentiment: this sentiment analysis classifier was trained with data from different restaurant review sites.

• Telcos - Sentiment analysis (Twitter): sentiment analysis for tweets about phone carriers comments.

• Airlines Sentiment: sentiment analysis for tweets about airline reviews.

Extraction:

• Keywords extractor (English): extract relevant keywords from texts in English.

• Keywords extractor (Spanish): extract relevant keywords from texts in Spanish.

• Entity extractors (English): extract entities (like people, companies and locations) from texts in English.

• Entity extractors (Spanish): extract entities from texts in Spanish.

• US Address extractor: use this module to extract US addresses from text.

• Useful data extractor: extract useful data (like dates, prices, phones, links and more) from text.

• Boilerplate Extractor: extract relevant text from HTML, it also removes boilerplate.

Check out and explore the public modules here. New public modules will be continuously added and improved by the MonkeyLearn team.