Newsblaster: An Automatic Weblogger

Newsblaster is a great new tool for news junkies. It also points the way toward some seriously good automated web harvesting technologies that will be a boon to searchers.

Online news has gone through several revolutions since the first media web sites appeared in the mid 1990s. During the "portalisation" craze news was one of the first features to be bolted on to the major search engines and directories. Later, headline aggregators became popular, providing tailored newsfeeds to anyone with a web site.

Are we talking about a Blog here?

Yes, and of course, the whole weblog phenomenon started as a source of "alternate" news on the web, with the first bloggers "editing" the web with links to news with a distinct point of view and often annotated with opinionated commentary.

What actually is Newsblaster?

Newsblaster, a project developed by the Columbia NLP (natural language processing) Group, and it represents the next level of evolution for news on the web. This system is a single service that monitors seventeen major web news services. It then groups related stories together for easy access.

What's so special about that? Isn't that what other news aggregators do?

Well, yes and no. What makes Newsblaster different is that it actually "reads" the news, using natural language and artificial intelligence techniques, and then actually writes short summaries of each major news event based on what it has "understood." Further, it's remarkably good at what it does.

After the summary, Newsblaster then includes links to the news stories it has read to generate the summary.

Is it as good at summarising news as a journalist?

While Newsblaster is an excellent tool for gleaning a quick summary of the most important news stories of the day, it won't replace journalists or editors any time soon. As good as the Natural Language Processing (NLP) techniques are at extracting and synthesizing information from news, the program lacks the perspective and critical mindset of a professional journalist, at least for now

Importantly, although Newsblaster uses credible news sources, it can't yet account for bias or inaccurate reporting.

What are some of the advantages of the Newsblaster?

Perhaps one of the greatest benefits is that of the timesaving facility Newsblaster offers. As the underlying technology improves and is extended, it's easy to see how this sort of approach could be used to develop customised web crawlers that you can personally tailor to recognise your own interests and then send out on autonomous search missions.

If such a system were combined with a Web address (URL) monitoring service, and seeded with a classification of subjects personally interesting to you, it could effectively create your own web "advisory" service, automatically building directories of promising sites annotated with high-level summaries that would spare you the time of manual searching.

Just as Newsblaster won't replace journalists, this type of hybrid crawler-agent wouldn't replace information professionals. But it would make a powerful addition to our arsenal of web search tools.

Arthur Hissey
Computer Research & Technology
www.crt.net.au