Abstract: Recommender systems learn about user preferences over time, automatically finding things of similar interest. This reduces the burden of creating explicit queries. Recommender systems do, however, suffer from cold-start problems where no initial information is available early on upon which to base recommendations. Semantic knowledge structures, such as ontologies, can provide valuable domain knowledge and user information. However, acquiring such knowledge and keeping it up to date is not a trivial task and user interests are particularly difficult to acquire and maintain. This paper investigates the synergy between a web-based research paper recommender system and an ontology containing information automatically extracted from departmental databases available on the web. The ontology is used to address the recommender systems cold-start problem. The recommender system addresses the ontology's interest-acquisition problem. An empirical evaluation of this approach is conducted and the performance of the integrated systems measured.

Exploiting Synergy Between Ontologies and Recommender Systems [PDF]

"There are so many dot-com companies that spent millions upon millions of dollars that tried to get a fraction of the traffic I'm getting and a fraction of the revenue that I'm getting. They have billboards in Times Square, they have 50 employees, they have a whole team of marketing and sales people. All this and they don't do anything. And that's pathetic and sad. "

Tech News - CNET.com

Audio Visual Forum. Fist time I have seen this, but it blessedly covers TVs, DVRs, and other hi-fi audio and video gear. I don't know about you, but I really enjoy being up to date on a lot of this technology.

AVS Forum - powered by vBulletin

Check it out! A new search engine startup by Todd Miller, a second-year PhD student at Georgia Tech's College of Computing.

"HyperBee is an attempt to crawl the web faster than ever thought possible. Current search engines can't keep up with the growth of the web and only index about 40% of the pages! HyperBee is a screensaver that runs while you're away from your computer, helping us crawl the web faster than any other search engine can, because we crawl it with your help along with the help of many others!"

[Very cool, but interesting possible security implications. --Randy]

HyperBee

Nice to see things are moving forward...

BBC News | SCI/TECH | Fusion power 'within reach'