Computational Analysis of Blogs
David S. Ferry* and Laura E. Hurlburt
Dr. Mary Shapiro, Faculty Mentor
One of the growing trends of the expanding internet is the advent of the weblog (or blog). Blogs are typically seen as an informal place for people to keep a public diary of the events and frustrations in their private and professional lives. A natural question to ask about blogs is whether they follow the same conventions as formal writing. In this study, we look at word lengths and word occurrence to see if they differentiate the gender of the blog author as we would expect them to do. In order to investigate these questions we turned to computational analysis. Computers are able to accomplish simple tasks with astounding efficiency, which made them the natural tool for our study. Unfortunately, our analyses suggest gender differences but are statistically not significant enough to draw conclusions. However, we were surprised by the almost total lack of characteristics of highly informal writing like slang and expletive use.
Keywords: computer science, linguistics, computational linguistics, blog, weblog
Topic(s):Interdisciplinary
Presentation Type: Oral Paper
Session: 38-3
Location: OP 2115
Time: 1:45