As we recall, it was discussed in the last chapter how unsupervised learning, including clustering and topic modeling, is applied in news data. We will continue to see supervised learning on the other hand applied in this domain, specifically classification, in this chapter.
In fact, classification has been widely used in text analysis and news analytics. For instance, classification algorithms are used to identify news sentiment, positive, or negative as in binary cases, or positive, neutral, or negative in multiclass classification. News sentiment analysis provides a significant signal to trading in stock markets.
Another example we can easily think of is news topic classification, where classes may or may not be mutually exclusive. In the news group example that we just worked on, classes are mutually exclusive, such as computer graphics, motorcycles, baseball, hockey, space...
