Monday, April 10, 2017

Voyant and Ngram


The picture above shows the total words used in our data mining extravaganza. Throughout our blog thus far, we used 4,013 words. The most frequent words were share, Moore, piece, Plimpton, and faith. Using Voyant, we discovered these pieces of data. The picture below shows how frequently those words are used in proportion to others. The larger words are used the most often.

The picture directly below shows where the most common words were used. The left is the most recent, the right is the beginning of our blogs life. It makes sense that Moore and Plimpton (green and purple respectively) were used mostly in the beginning because that was our first blog post. Share was used throughout our blog. This may be because we are talking about technology in this course and today "sharing" information over the internet is very popular.


To the right the diagram shows the connection that words have with each other. The green words are keywords and the red words are other frequently used words. The thicker the line, the more frequently those words appear near to each other. For example, "share" and "Facebook" are linked with a think line because they are both used in the same context in our blog. "Pittsburgh" and "Plimpton" have a thin line because they were used together but not as frequently as "share" and "Facebook." 


Finally, the picture was generated by using Ngram. Ngram looks through information to find when that word was the most popular. It is interesting to see that over the past 40 years that "share" has become more popular. As mentioned above, with technology increasing and social media growing, sharing online has become part of many people's everyday lives. "Piece" has decreased. This could be because piece could refer to a piece of music or a piece of art. Today, the word piece is not used as frequently. "Song" or "work" may be used to describe art or music. Moore was just a name so that is why it is consistently low throughout the years.

Data mining can lead to many different conclusions. It highlights what words are used which shapes out culture. Language is culture. The more that we can identify how we communicate, the better we can be at communicating.

Devan Orr
Sean McCarney
Jack Shirk


No comments:

Post a Comment