Attensity, extractive exhaustion, and the FRN
Two of the clearest and most charismatic speakers in the text mining business are Attensity cofounders Todd Wakefield and David Bean. Last year, Todd’s Text Mining Summit speech gave an excellent overview of the various application areas in which text mining was being adopted; vestiges of that material may be found in a blog post I made at the time, and on Attensity’s web site. This time, David’s Text Analytics Summit speech was basically a pitch for Attensity’s latest product release – and it was a pitch well worth hearing.
Read more
| Categories: Attensity, BI integration, Comprehensive or exhaustive extraction, Text Analytics Summit, Text mining | 10 Comments |
Procter & Gamble on text mining projects
Terry McFadden of Procter & Gamble made a number of interesting points in his Text Analytics Summit talk, in the area of how to build and “amass” (his word) lexicons. Above all, I’m thrilled that he recognized the necessity of amassing lexicography that can be reused from one app to the next. Beyond that, specific comments and tips included: Read more
| Categories: About this blog, ClearForest/Reuters, Companies and products, Ontologies, Text Analytics Summit, Text mining | 2 Comments |
The current state of text mining/analytics marketing?
One thing that didn’t go so well at the Text Analytics Summit was the marketing panel. Indeed, when we wracked our brains afterward, Mary Crissey (who was on the panel) and I could only think of a single observation that was actually made about marketing. Namely, she referred to a core truth of marketing: Just selling features doesn’t work (nobody cares). Just selling benefits doesn’t work (you’re not differentiated). What you have to do is sell the connection between your features and desirable benefits.
So I’m going to try to gather some useful observations on marketing here, filling the gap that the panel left. Key questions I’d love input on include:
1. Which feature-benefit connections do you see customers easily accepting?
2. Which feature-benefit connections is it harder to get them to believe?
3. How are customers defining text analytics market segments?
4. What do they see as the key issues in each segement?
5. Which application areas are showing growth even beyond that of the market overall?
I’m particularly interested in comments from the larger vendors that are selling into multiple parts of the text mining and text analytics market. But everybody else’s input would be warmly appreciated too.
The comment thread to this post is open for business!
| Categories: About this blog, SAS, SPSS, Text Analytics Summit, Text mining | 6 Comments |
Notes from the Second Annual Text Analytics (formerly Text Mining) Summit
Thursday morning at the Text Analytics Summit featured, among other things, one excellent panel, a couple of lively and interesting presentations, and the usual tedious discussion of “What do we call this technology area anyway?” Lots of airtime went to industry stars such as Olivier Jouve (SPSS), Todd Wakefield (Attensity), Ramana Rao (Inxight), and Mary Crissey (SAS). There also was a gratifying repetition from the front of the room of the statement “Curt is right”, so as of when I’m writing these notes (midday) I’m happy, even if Ramana somehow neglected to join that chorus …
Repeated themes and messages included:
- This technology is practical for a lot of apps. Really, it’s practical. In particular, the vendors feel they’ve done a good job now of separating the technology from the ontology implementation. It was even claimed, sort of, that the technology was a commodity (but see below).
- Growth hasn’t continued on the rocketship trajectory it was on a year ago. It couldn’t. But it’s been very healthy by any other standards. (Actually, SAS later told me they were still growing at the old pace.)
- A typical text mining vendor has 25-30% of its revenue in services. I.e., this really is a license business, unlike a few years ago when it was focused on custom government (defensive/security) applications.
- Like analytics vendors in general, text mining/analytics vendors are selling a lot on an application basis. More than I think they should be, actually. A number of people think that text analytics companies will be bought by various other kinds of software company, to be rolled into their general product lines.
- Nobody is doing anything about the platform advances I think are necessary. However, when prodded, they admit that something like that is needed, and the technology really isn’t finished or a commodity after all. But some other company should do it, because they aren’t going to. Arggh.
I’ve only slept one night in the past three, so I’ll stop here and blog more about the conference later.
| Categories: About this blog, Text Analytics Summit, Text mining | Leave a Comment |
Data capture for the sake of text mining
One of the major factors driving successful use of advanced analytic tools is direct initiatives to procure more data. The single best example I can think of is the gaming industry’s use of otherwise-contrived loyalty cards; improved marketing based on that data at chains like Harrah’s seems to produce upwards of 100% of total profits.
So can we apply the same approach to text mining? One place would be surveys. Rather than those annoying, contrived forms demanding we fill in a lot of choices as if we were taking the SATs all over again, maybe users would be more revealing if they could just write whatever they wanted? The obvious firm to ask is SPSS, which is big both in surveys and text mining, not to mention the intersection of the two markets. So I emailed Olivier Jouve, and he shot back an answer from an airport. Read more
| Categories: About this blog, SPSS, Text mining | 3 Comments |
Product search fun at Tesco
Single-site websearch can be quite problematic. Here are screenshots of two examples:
Canned fish returned on a drain cleaner search
Rum returned on a condom brand search
| Categories: Search engines, Specialized search | Leave a Comment |
Text analytics white papers
The Text Analytics Summit folks have created a page where you can download a bunch of whitepapers. Most of those are tripe, of course, but I’m finding some of them interesting. The first few Megaputer ones I looked at seemed to have non-obvious application stories. The two SPSS ones actually called “Case Study” are worth a quick glance. And the ones from Lexalytics and Intellisophic definitely seem worthy of more thought and/or research.
Edit: Also possibly worth a look on that page is a Henry Morris opus for ClearForest called “Putting the Why in BI.”
| Categories: Ontologies, Search engines, Text Analytics Summit, Text mining | Leave a Comment |
DISCOUNT on Text Analytics Summit, June 22-23, 2006
Last year I blogged glowingly about the first annual Text Mining Summit. Now it’s time for the second annual conference, with the name changed to Text Analytics Summit. It is in Boston (next to the Prudential Center/Hynes Auditorium complex) on June 22-23, 2006. From the descriptions*, it sounds a lot like last year’s, with the same high-level industry attendance. Indeed, in many cases there will be exactly the same high-level industry speakers …
*Unlike last year, I wasn’t involved in the planning, and am not going to be a speaker.
Anyhow, I plan to be there. Even better, I am empowered to offer a discount to anybody else who cares to attend. I am told that if you register online, there will be a discount box, and if you enter “CAM” you will receive a $100 reduction in your registration fee.
| Categories: Text Analytics Summit, Text mining | 3 Comments |
Four (at least) issues in text and taxonomy federation
For any issue in text analytics, there are a lot of smart people who understand it very well (and, in particular, better than I do). But I suspect that even many of the discipline’s better thinkers have failed to grasp just what will be involved in taking text analytic technologies to the next level of usefulness and adoption. One example is what I see as the requirements for an ontology management system; I’m not aware of anybody else right now who has as expansive a view of this as I do. In this post, I’m going to address another issue whose complexity is in my opinion under-appreciated – federation. More specifically, I’ll argue that the various aspects of the federation task are a big part of what makes ontology management so complex.
The thing is – there are at least four different senses of “federation” in the text sphere, all of them important, most of them still technically unsolved. Namely:
| Categories: Ontologies, Search engines | 1 Comment |
That great linguist, Groucho Marx, and other stories
If you’re reading this blog, you’re probably familiar with a saying that illustrates some of the basic challenges of disambiguation:
Time flies like an arrow. Fruit flies like a banana.
But did you know who said it first? I didn’t until recently. Read more