Culturomics and Computational Lexicology data mining techniques.

Computational lexicology methods try to understand human behavior, cultural norms through analysis of texts. These methods try to enlist the usage of words through the years and conclude what has changed in human behavior over the years. There have been various studies done, one in particular in which Harvard scientists showed that nearly 50% of the words found in books are not mentioned in any dictionary.

One good way to research and try it yourself is to experiment with the Google Ngram search at the link below. See the link below with a search for happy and sad and see how the incidence of “happy” has decreased over time. This easy data mining effort will illustrate how easy it is to come to conclusions with so little proof!

2013-05-06-Ngram


Posted

in

by

Tags: