Semantic Search Engine as a model for Intel Analysis tool

[JeffC]

TrueKnowledge recently unveiled its semantic search engine (in private Beta) via a video that you can see at my IntelFusion blog (http://idolator.typepad.com/intelfusion/2007/11/trueknowledge-s.html).

I think it holds great promise as a model for an analyst's tool. If you have a few minutes to watch the video, I'm interested in hearing from those of you with analyst experience as to its potential, in your opinion.

[Jedburgh]

It looks interesting as a research tool. I wouldn't categorize it as an analyst's tool.

For me, restricting any on-line search to a specific question is constrictive - it narrows the thought processes. By the time I reach the phase in the project where I'm down to such specific questions, I damn well better know where to look (of course, this statement does not refer to true intelligence gaps, as regards shortfalls in collection).

In the research phase of a project, I very much prefer broad response to queries, as I'm looking at an entire spectrum of information. This helps develop the approach as I go along. Starting an analytic project with specific questions is like using leading questions in an interrogation - you're only going to get back what you've set yourself up for, and you end up missing out on the really valuable information.

If you haven't seen this, give it a whirl: A Periodic Table of Visualization Methods (http://www.visual-literacy.org/periodic_table/periodic_table.html)



FYI, whenever I see "Intelligence" and Debkafile mentioned in the same space I want to spew. Debka, the Northeast Intelligence Network (a particularly foul misuse of the term) and WorldNetDaily are all utterly unreliable steaming piles of internet dung.

[Rex Brynen]

FYI, whenever I see "Intelligence" and Debkafile mentioned in the same space I want to spew. Debka, the Northeast Intelligence Network (a particularly foul misuse of the term) and WorldNetDaily are all utterly unreliable steaming piles of internet dung.

I wonder if IntelFusion understands "Is Debkafile an unreliable steaming pile of internet dung?" ;)

(I agree, btw)

[JeffC]

It looks interesting as a research tool. I wouldn't categorize it as an analyst's tool.

For me, restricting any on-line search to a specific question is constrictive - it narrows the thought processes. By the time I reach the phase in the project where I'm down to such specific questions, I damn well better know where to look (of course, this statement does not refer to true intelligence gaps, as regards shortfalls in collection).

I do see your point. What I like about TrueKnowledge is the ability to load a Knowledge Base with new source material. You could easily create a highly focused KB about a specific region or group, and then query it using Natural Language Processing algorithms. Further, other analysts could see the provenance of that data that gets pulled into the search results.



If you haven't seen this, give it a whirl: A Periodic Table of Visualization Methods (http://www.visual-literacy.org/periodic_table/periodic_table.html)

Thanks. I have seen that table, but I'm glad you reminded me. I'll add it to the Resources section of my blog.



FYI, whenever I see "Intelligence" and Debkafile mentioned in the same space I want to spew. Debka, the Northeast Intelligence Network (a particularly foul misuse of the term) and WorldNetDaily are all utterly unreliable steaming piles of internet dung.

You know, I've been suspicious of DebkaFILE's reliability for awhile, and I hunted around trying to find something online that debunked them but nothing really surfaced either way. I think I've quoted them twice in the last 8 months, including their November 11th prediction. We'll see what happens with that.

What do you think of John McCreary's Nightwatch newsletter?

[selil]

For semantic search technology without having to sign up and by nature much more flexible try http://www.hakia.com/ . It works pretty good, but will still work for key words. It gets smarter as you use it though its pretty static at this time.

[Jedburgh]

ReadWriteWeb, 29 May 08: Semantic Search: The Myth and Reality (http://www.readwriteweb.com/archives/semantic_search_the_myth_and_reality.php)

....Semantic search is an upcoming technology that has set the expectations way too high. We have all been misled into thinking that these technologies are here to dethrone Google by delivering better search results. Neither of those things are true. What is true, however is that semantic search is going to be big and it is going to help us answer questions that we simply cannot answer today - complex, inferencing queries asked over the entire web as if it was a database.

In order for these semantic search technologies to make a dent in the market, they need to clean up their messaging and most importantly, their user interface. Presenting a search box is both misleading and detrimental, as people associate it with the simplistic questions that Google solves without any problems. To really showcase semantic search, these companies need to come up with innovative UIs that will help users to understand the power that is being put at their fingers.
Watson (http://watson.kmi.open.ac.uk/WatsonWUI/)

Yahoo Microsearch (http://www.yr-bcn.es/demos/microsearch/)

Semantic Web Search (http://www.semanticwebsearch.com/query/)