Month: November 2017

LTE: Urban, suburban and rural discourse

6 Comments / natural language processing, sociolinguistics / By / December 4, 2017

After I labeled all the data by topic, I took a quick look at the topic tallies, both overall and by newspaper, keeping in mind the newspapers’ locations. The overall percentages are shown in the graph below: Some of these stats were expected, others surprising. I expected most of the letters to be about politics …

LTE: Urban, suburban and rural discourse Read More »

LTE: Labeling data for machine learning

2 Comments / machine learning, natural language processing / By / December 4, 2017

For the project of automatically assigning topics to the letters to the editor, I needed labeled data. Sometimes blog posts, or articles in a newspaper will have assigned labels (for example, this post is tagged with “machine learning” and “natural language processing”). However, none of the newspapers I got my data from did that. Thus, …

LTE: Labeling data for machine learning Read More »