Using Python, Matrix and TensorFlow to analyse the content of messages

May 25, 2019, 2:30 p.m. - 4:30 p.m.

Matrix is an open standard for interoperable, decentralised, real-time communication over the Internet. It can be used to power Instant Messaging, VoIP/WebRTC signalling, Internet of Things communication - or anywhere you need a standard HTTP API for publishing and subscribing to data whilst tracking the conversation history. There are Python SDKs available for interfacing with Matrix as a client (that is, doing things a client application or bot would do, such as sending and receiving messages.) 

In this workshop you will investigate how to interact with the Matrix platform, first using curl HTTP calls, then using Python. You will use the Matrix Python SDK to read messages, and extract their contents. Then, you will make a basic use of TensorFlow to analyse the text (Sentiment Analysis is just an example of what can be done.) On getting the result, you will learn how to send a message back in response to the original message.

Ben Parsons

Get PyConWeb event announcements

No spam, 2 emails per year