Summary
In this chapter, we started with the idea of gathering evidence which supports investigation into an article of our interest. We looked at how we can have a general evaluation for an article and how to measure, weigh down, and lift up the value of certain words in any article.
We learned how to see an article as a bag of words and how to use this concept to calculate similarity. We set up and used Custom Search Engine and Yahoo APIs to query and fetch the contents of Web pages in periodic time spans.
Finally, we learned how to get some insight by clustering the gathered articles - corpus - around specific subjects and we saw how to visualize the cluster using a third-party data visualization library (VisJs) and an Angular wrapper module (ng2-vis).
In the next chapter, we take one step back and try to organize what we have created so far into an informative report.
