More feedback on Healthline coming in

First, let me say, that there’s no coverage like splog coverage; it’s simply amazing how popular press releases are with splogs. Having now sorted through most of them, here are some more reactions I’ve found…

1. Valentin, a PhD student working on AI and Semantics, says:

I had a look at it and I’m happy to report that it is the first really cool semantic search engine in the wild. Granted, building such a system is not rocket science – but still, I’m not aware of any public website that has a comparable semantic search engine.

Hey now, your “not rocket science” is our “we’re just getting warmed up”! 😉 Considering Valentin wasn’t briefed, he’s got a good perspective on what we’re doing, though I’ll drop one hint… we’re doing more than just full text index/retrieval.

2. Chad Williams encourages us to grow our index (of, no, not MedlinePlus information, but “non-traditional sources”!) so that he can get better results when searching for “fishbone caught in throat”; earlier he notes that Google disappointed him on this front too. Chad, a small army of crawler boxes are already on order; it’ll take time, but it will get done.

3. Mark Allen would prefer we not use the oh-so-trendy “beta” moniker, but commends us for a strong set of results for scoliosis. Mark, we’re too hip to worry about being hip! 😉 In all seriousness, we’re Beta because we know we can do better with everyone’s help (it’s hard to build a top-notch search engine until you’re live and have searches coming in… more on that another day).

4. Finally, Alf Eaton of HubLog dings us for a search listing that wasn’t to a health web site, but seems to really dig our taxonomy-driven query refinement (hey, what about the HealthMaps? [grin]):

I got a result that pointed to a page that wasn’t really health-related but happened to have the right words on it (Scirus suffers from this too) – but the taxonomised directory is excellent and I found some useful information straight away. Broadening and narrowing of searches based on a hierarchical taxonomy is something biomedical searches have needed for a long time)

Like everyone else, we’re fighting the splog/content-thievery issue (sploggers appearantly love the CPCs of health ads) and duplicate medical content is everywhere (i.e., if you think your blog/RSS content is popular with sploggers, you don’t know the half of it).

Looking forward to more feedback (but I promise I won’t post everything… I know that’s not why you’re reading my ramblings).

Posted in Uncategorized