The use of clustering and visualization for the management of blog content - an empirical investigation

今天的互联网用户接触到了来自许多来源的大量信息，如电子邮件和网页。信息的绝对数量很容易使用户不堪重负，并对他们过滤、分析、消费和理解各种形式的所有这些信息的能力产生不利影响。网络使用的新浪潮，通常被称为Web2.0，为信息的传播和利用带来了各种机会。然而，早期互联网应用程序存在的信息过载问题仍然存在，可以说是以一种更严重的形式出现。截至撰写本文时，最大的博客搜索引擎Technorati(Technorati.com)跟踪了近1.1亿个博客网站(相比之下，2006年1月这一数字仅为2450万)和超过2.5亿条有标签的社交媒体。鉴于搜索引擎只为现有信息空间的一部分编制索引，而且每天有超过17.5万个新博客定期更新，每天有160万篇帖子更新，显然Web2.0上的信息过载将比以往任何时候都更加紧迫。

Today's Internet users are exposed to an abundance of information from many sources such as e-mail and web pages. The sheer quantity of information can easily overload users, and adversely affect their ability to filter, analyze, consume, and understand all of this information in its various forms. The new wave in web use, commonly referred to as web 2.0, brings in a variety of opportunities for information dissemination and use. Yet, the information overload problem that existed for the earlier Internet applications still presents itself, arguably in an aggravated form. As of this writing, Technorati (technorati.com), the largest blog search engine, tracks almost 110 million blog sites (as a comparison, this figure was only 24.5 million in January, 2006) and over 250 million pieces of tagged social media. Given that search engines index only a portion of the existing information space and that there are over 175,000 new blogs every day regularly updated by 1.6 million posts per day, it is clear that information overload on web 2.0 will be even more pressing than it has been so far.