Book Image

Building Slack Bots

Book Image

Building Slack Bots

Overview of this book

Slack promises that its users will "be less busy." Slack bots interact with users in Slack chatrooms, providing useful immediate information, and automating work. This book gives you everything you need to build powerful and useful Slack bots. You’ll see how to hook into the Slack API to create software that can read and post to chatrooms, respond to commands and hints given in natural conversational language, and build fun and useful bots for your own place of work, both as a front end to your own service and to distribute and share as apps. You can even sell your bots and build a business as a Slack bot developer. Throughout the book, you’ll build useful and fun example applications that you can modify for your own situations. These range from simple, fun applications to liven up discussions to useful, data-driven apps to help you make decisions quickly and manage work.
Table of Contents (14 chapters)

Classifiers


Classification is the process of training your bot to recognize a phrase or pattern of words and to associate them with an identifier. To do this, we use a classification system built into natural. Let's start with a small example:

const classifier = new natural.BayesClassifier();

classifier.addDocument('is it hot', ['temperature', 'question','hot']);
classifier.addDocument('is it cold', ['temperature', 'question' 'cold']);
classifier.addDocument('will it rain today', ['conditions', 'question', 'rain']);
classifier.addDocument('is it drizzling', ['conditions', 'question', 'rain']);

classifier.train();


console.log(classifier.classify('will it drizzle today'));
console.log(classifier.classify('will it be cold out'));

The first log prints:

conditions,question,rain

The second log prints:

temperature,question,cold

The classifier stems the string to be classified first, and then calculates which of the trained phrases it is the most similar to by assigning a weighting to each possibility...