Classification of blogs

For this post, I have found a unique blog classification system. Qu et al. (2006) designed an experiment based on natural language processing (NLP). NLP is a field of computer science and linguistics concerned with the interactions between computers and human (natural) languages that converts information from computer databases into readable human language (Wikipedia 2001). Their NLP program is used for categorizing one hundred and twenty blogs into four topic groups: personal diary, politics, news, and sports.

The NLP experiment was carried out by weighing specific linguistic features such as the title of individual blog entries and the anchor text from incoming links will make the classification algorithm even more accurate. They explained further that even if blogs are hardly distinguishable because of the nature of bloggers that blog about whatever they feel like to, they were aiming for the NLP techniques to explore the feasibility of automatic blog classification.

If the NLP approach done by Qu et al. (2006) seemed a bit technical, Simmons (2008) offered a more defined classification of blogs by categorizing them into Pamphleteering blogs, Digest blogs, Advocacy blogs, Popular Mechanics blogs, Exhibition blogs, Gatewatcher blogs, Diary blogs, Advertisement blogs and News blog. The NLP approach takes into consideration of titles of blog entries and the anchor text whereas Simmons' categorization looks into the blog's nature as a whole allowing her to name the categories as such.

In my opinion, the NLP approach might provide us with a more mathematically accurate result in blog classification but to truly justify a blog type one must personally define what the blog is all about by reading through it and understanding the blog's intention.

References:

1. Qu, H., La Pietra, A. & Poon, S (2006), Classifying Blogs Using NLP: Challenges and Pitfalls,University of California at Berkeley, School of Information Management & Systems

2. Wikipedia 2oo1, Natural language processing, online, retrieved 10 April 2010, from http://en.wikipedia.org/wiki/Natural_language_processing

3. A taxonomy of blogs (2008), online, retrieved 7 April 2010, from http://www.abc.net.au/rn/mediareport/stories/2008/2372882.htm#transcript.