INFO 202 Fall 08 Blog

I read about Twine in Technology Review (and then saw Shawna just posted on it). Well the TR review is interesting in itself. It seems to even includes a 202 kitchen sink:  Autotagging, Autosummary, Bookmarking, Sharing, AI, Concept extraction, NLP, Semantic Web, etc.. but they report bugs, too.

Probably a lot of you have heard of Twine, but it just came out of private beta and is now open to the public.  A social network built on the semantic web… hmm…

I experimented with an automatic-tagging experiment/engine tonight.  The designer cleverly used Wikipedia’s URIs as a source for a controlled concept/tagging vocabulary!  Pretty cool.  He full-text indexed Wikipedia (yes, he downloaded it all) with Lucene, (an open source search engine), and used its, “I feel lucky,” feature to make tag/concept associations.

As input I experimented with text from Bob’s first slide from the last lecture:

Overview of the Semantic Web RDF OWL A Critical Evaluation of the Semantic Web Semantically-aware systems

Try copying it and pasting it here

There’s too much output to post here, but you get a tiered-list of potential tags.  I found the third-tier results pretty interesting. I could imagine this being useful (though imperfect) for automatically adding keyword/tag metadata to a document.

..So someone could develop a blog plugin that automatically generates tags based on this..

Ha.

Even if we could automagically classify, categorize and connect all the textual content on the web, what would we do with the 2 billion + photos on Flickr? Well, ALIPR (that’s Automatic Linguistic Indexing of Pictures in Real-time) is going to take care of all that tricky classification for us by using image recognition (and some other stuff) to automatically tag all of our photos.

It is not hard to guess how this works right now. But even if the software improves, good 202ers know that the problem is far from solved.

I read a paper today that discussed a step covered in class today on document engineering.  We learned how the Berkeley Calendar Network team manually harvested and consolidated tables of terms in a huge excel spreadsheet.  The IEEE paper I read argues for semi-automating this process of deriving homonyms in IS-A relationships, for instance, and integrating the terms with the http://wordnet.princeton.edu ontology.

The buzzword-laden paper continues to argue for creation of a working Semantic Web by harnessing the large quantity of structured, “Deep Web” data. The, “Deep Web” (unindexed by conventional search engines) contains ~over 4 orders of magnitude of data than the, “Surface Web” and some data is structured in databases.  The Semantic web, they claim, has been hampered by difficulty in manually creating large OWL and RDF ontologies, and harvesting the richer potential of the Deep Web points to a possible solution:
Semantic Web + Deep Web-Ontology-aware browser.

Ironically, the paper, itself, is buried in the deep web:
http://ieeexplore.ieee.org/iel5/2/4623205/04623231.pdf?tp=&arnumber=4623231&isnumber=4623205

http://www.fi.upm.es/?pagina=737&idioma=english

“Researchers from the Validation and Business Applications Group based at the Universidad Politécnica de Madrid’s School of Computing (FIUPM) have developed a new method for building multilingual ontologies that can be applied to the Semantic Web.”

So ontologies are the cool thing to be developing these days given the promise of the Semantic web looming over us.  But up until yesterday, a big limitation with ontologies was that they were relatively single-minded when it came to language.  “The application of ontologies to the Internet comes up against serious problems triggered by linguistic breadth and diversity. This diversity stands in the way of users making intelligent use of the web.”

People have tried to bridge the gap, but strategies like expert-based terminology (ahem, Svenonius, ahem) and using one language as the “pivot”, have failed miserably.  But these researchers claim to have created a method for building ontologies IRRESPECTIVE of language. And their secret weapons appear to be universal words and the assumption that “any text has implicit ontological relations that can be extracted by analysing certain grammatical structures of the sentences making up the text“. (I mean, I could’ve told them that, but whatever)

Interesting stuff, and will probably be even more interesting when I finally grasp what an ontology actually is. 😛 (just kidding) (sort of)

A Case Study in Employee Social Networking at Sabre

http://www.socialcomputingmagazine.com/viewcolumn.cfm?colid=601

With the explosive popularity of social networking sites in the last few years, business analysts have been scrambling to find a way to incorporate employee networking into their companies. The task of improving efficiency of communication and building corporate culture for large companies with thousands of employees stretched across the world might be best achieved with these emerging platforms.

In “A Case Study in Employee Social Networking at Sabre” Toby Ward, Founder and CEO of Prescient Digital Media, documents some of the impacts a strong employee social network has made on the airline reservation company Sabre. He notes that while email is still the dominant application for company communication, more value can be delivered when a single employee can communicate “both actively and passively” to all connected employees. Users of “SabreTown”, Sabre’s employee networking platform allows for most of the features any social network platform does: employee profiles, photo sharing, blogs, comments, etc.

SabreTown and other platforms might just be more than another excuse to ride the Web 2.0 and social networking wave. As users complete their profile; write, comment on and edit blogs; ask and answer questions, the platform engine compiles and categorizes relevant information in order to improve employee search and helps “members find the right people with the right answers.” Sounds a lot like Google’s quest to display the exact result the user wants at the number one spot by collecting as much data about the user as possible.

Somewhat obvious is that these emerging platforms will become increasingly useful in industrial and public service domains. When I was teaching, I had my students complete MySpace profiles for characters from Romeo and Juliet. They had to fill out their profile according the specific details of each character as well as comment and send messages to other characters. As oft-nebulous Shakespeare characters began to have personalities they could relate to, my students became more engaged and enjoyed reading the play much more.

14. SOCIAL / DISTRIBUTED CATEGORIZATION (10/15)