-
Book Overview & Buying
-
Table Of Contents
Machine Learning for Emotion Analysis in Python
By :
In Chapter 7, Support Vector Machines, we saw that support vector machines (SVMs) can be used to classify tweets for emotions based on the words that they contain. Is there anything else that we can use that simply looks at the words that are present? In this chapter, we will consider the use of neural networks for this purpose. Neural networks are a way of carrying out computations by assigning weights to a network of nodes and propagating an initial set of values through the network until the output nodes are reached. The values of the output nodes will then be a representation of the result of the computation. When neural networks were introduced in the 1940s, they were intended as a model of the way that the human brain carries out computations (Hebb, 1949) (McCulloch & Pitts, 1943). This kind of network is no longer taken seriously as a model of the human brain, but the results that can sometimes be achieved this way can be very impressive...