ABC automatic blog categorizer using K-means algorithm

Date of Publication

2009

Document Type

Bachelor's Thesis

Degree Name

Bachelor of Science in Computer Science

Subject Categories

Computer Sciences

College

College of Computer Studies

Department/Unit

Computer Science

Thesis Adviser

Paul Salvador Inventado

Defense Panel Member

Charibeth K. Inventado

Merlin C. Suarez

Abstract/Summary

Many web logs are being published daily throughout the World Wide Web. One of the reasons why blogs are popular is because it is free. During the survey of 2005, there are around 60 million blogs all over the internet (Riley, 2005). With the increasing number of blogs each day, it is hard to search for a specific blog. Organizing these blogs can help in searching because these blogs will have an identity based on its subject making it easier to distinguish from one concept from the other. An example will be searching for a blog containing the word freestyle, which refers to a stroke in swimming. Other subjects like freestyle as related to dance can be filtered out by specifying the intended category. This research aims to solve the problem by developing a software that will categorize blogs to their respective categories. Most document categorization software categorizes documents into pre-defined categories. This research however, aims to automatically categorize blogs based on content without using pre-defined categories. Throughout the course of the research, the proponents learned that the result of the automated categorization of blogs heavily depends on the input provided for the system. For this dataset, using words alone and without a lexical analyzer or some form of understanding the words, it is difficult to come up with clusters with general topics because these words or terms may have different meanings.

Abstract Format

html

Language

English

Format

Print

Accession Number

TU19848

Shelf Location

Archives, The Learning Commons, 12F, Henry Sy Sr. Hall

Physical Description

1 v. (various foliations) : illustrations (some colored) ; 28 cm.

Keywords

Blogs; Blogs--Social aspects; Online journalism

This document is currently not available here.

Share

COinS