New metrics for blog mining

Brian Ulicny; Ken Baclawski; Amy Magnus

doi:10.1117/12.720454

9 April 2007 New metrics for blog mining

Brian Ulicny, Ken Baclawski, Amy Magnus

Proceedings Volume 6570, Data Mining, Intrusion Detection, Information Assurance, and Data Networks Security 2007; 65700I (2007) https://doi.org/10.1117/12.720454
Event: Defense and Security Symposium, 2007, Orlando, Florida, United States

Abstract

Blogs represent an important new arena for knowledge discovery in open source intelligence gathering. Bloggers are a vast network of human (and sometimes non-human) information sources monitoring important local and global events, and other blogs, for items of interest upon which they comment. Increasingly, issues erupt from the blog world and into the real world. In order to monitor blogging about important events, we must develop models and metrics that represent blogs correctly. The structure of blogs requires new techniques for evaluating such metrics as the relevance, specificity, credibility and timeliness of blog entries. Techniques that have been developed for standard information retrieval purposes (e.g. Google's PageRank) are suboptimal when applied to blogs because of their high degree of exophoricity, quotation, brevity, and rapidity of update. In this paper, we offer new metrics related for blog entry relevance, specificity, timeliness and credibility that we are implementing in a blog search and analysis tool for international blogs. This tools utilizes new blog-specific metrics and techniques for extracting the necessary information from blog entries automatically, using some shallow natural language processing techniques supported by background knowledge captured in domain-specific ontologies.

Citation Download Citation

Brian Ulicny, Ken Baclawski, and Amy Magnus "New metrics for blog mining", Proc. SPIE 6570, Data Mining, Intrusion Detection, Information Assurance, and Data Networks Security 2007, 65700I (9 April 2007); https://doi.org/10.1117/12.720454

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available