Klea Global

Search this site

Navigation

Klea Labs

Toys and Games

At Klea Global we invent really cool toys and applications. We though you would like to play with some of them too. Of course some of them work well and some are - well, not so good. Some just plain don't work any more!

Semantic Web Experiments

We have been working on Latent Semantic Indexing for nearly a decade but now we are looking at a range of
other ways the semantic web can offer practitioners insights.

This is an experiment that dynamically identifies an ontology. The objective here will be to allow the practitioner to drill down further and further to find out who is affected and involved with an entity in a web page (e.g. news story).
You can try it out for yourself her http://entitymap.appspot.com/



Monitor your news

This is a really cool tool. It monitors the news for you and delivers it by email or instant messenger.
I expect we will upgrade it soon to go onto Iphone and Android phone.


Track Stuff Now

This is a development tool designed to seek out sites that are significant for the search term you provide.


You can access it at http://www.trackstuffnow.com




Reputation Wall

This is a development we have taken a very long way. It searches for pages about a search topic, opens up the web pages, normalises the texts, parses the texts of all the pages for semantic concepts (latent semantic indexing - we have our own software to do this) and then looks for the most powerful concepts month by month going back a year.

You can create your own 'Reputation Wall' here http://reputationwall.appspot.com





Track This Now

A media story or picture comes to prominance and you want to now where in the world it is popular right now. Well, here is the service that gives you an instant world and regional snap shot.



You can find your news of the moment here



Blogger Finder

Its easy to find all the blogs that mention a client, brans, issues etc. Its not quite as easy to find the blogger with a big audience in a particular country, who frequently writes about the
subject at hand and has done so in the last few weeks or months. We have built a pre-beta blogger finder which works every second Tuesday in months with 31 days (or so it seems).

You may like to go and have a look at it here http://bloggerfinder.appspot.com/

If it is having an off day and does not work, give me a call and I will see if we can get it up and running again (there is a full blown product in development but it won't be launched for a while).


Finding Semantic Concepts

This tool was used to discover relationships between people and organisations in a big research project. You can enter a lot of website URL's into it and it will return the 50 most significant semantic concepts in the corpora. 

 I find it is more manageable if you remove the URL's and then paste the words into a programme like TagCrowd to generate a semantic word map.

CrowdMoods

From time to time we are invited to find out what the world thinks is cool. This was an example that started offwith music and morphed into cricket (so now you know what our coders do all day!).

You can find out what is really fascinating for most of the world here http://crowdmoods.appspot.com/


Value Systems Analysis

This software levers the semantic analysis of pages and looks at bigger corpora. In this case current Google News, Blogs and natural search. The analysis shows values in bold in the texts. 

The software was developed as a series of software developments for academic research. In this case the  software was part of the development for building the values theory in PR. The outcome was presented at theBled symposium in 2009:


Web Page Text Analysis

One of the hard things to do is to re-construct web pages to extract the text and then find the sematic concepts
and much more.
This tool is really clever because it shows the steps involved. You can extract the text on web pages with this tool too.



Web Page value comparisons

We know a lot about the web pages that have advertisements because publications tell us. We know about reach and linkto v number of pages ratios and all that stuff. So perhaps it is reasonable to apply those measure
to other pages and then look at how much such a page might be valued at if it were to carry advertising. In a word the adversing value of the web page. Well, We thought we would try to build the algorithm and test it out. Its not too bad. A Wikipedia page is worth and ad, the algorithm says, costing £283,000. I guess some pages are worth more than others and we have not got much further than this. The benchmark site is the Telegraph.co.uk. 
You can try it for fun.
 

Twitter story making

Yes, I know. More applications that you can imagine for Twitter. 

This one, part of our work to find relevant 
tweets when multiple word search does not yield results, is a cool tool for turning Twitter tweets into a story. 


Video News

Finding the latest video is harder than you think. There are so many channels.

We thought that it would be a good idea to have them all in one place and this was the first part of developing a special type of search which you can see in NewsRokit.

You can play with the software here http://crowdmint.appspot.com/


Google Hourly Search to CSV

Everyone want to get a spreadsheet of the latest pages indexed by Google. This toy allows you to just the last
hour's worth of pages indexed by Google.

To try it yourself here is the URL http://search2csv.appspot.com/



Summariser

Did you want to make a quick summary of a web page?

This may help.




Reputation Quotient

We have been working on this for a while. 
The idea is quite simple. We asked, What are the elements of reputation, lets see if they are available online and can be made into a programme.
The algorithm so fare includes: 
  • We count the number of citations
  • We analyse each citation for richness of  content (why? For example Twitter reach may be huge but convey very little but an Economist article may have less reach but has significance for reputation).
  • We count the reach (unique visits) for citation's web sites and look at them as a ratio of visits to site pages
  • We count the number of positive paragraphs and subtract the number of negative paragraphs
  • We count the number of citations in each media type and return the number of types above the median (+) and below the median (-)
  • We count the inlinks ratio to pages for citations' web sites for network measurement.
We also 'normalise' the numbers into measures of 1:10, 1:100, 1:1000 so that we can compare the data on a single chart and add up all the normalized numbers into a single quotient.

Soon, we will have a  widget for you to try out. Its fun comparing reputation between  two competitors and even more fun tracking over time.

NewsRokits

NewsRokits have now moved from pre-beta to beta. Now that is something!

Here is an example http://www.web30journal.com/

Here is where you can create your very own online journal, newspaper or magazine without having to be a full time editor.





Klea Insight

Now in beta and available for commercial use, Klea Insight should not really be on this page but, because everyone has a monitoring service with a cute dashboard, I simply had to show ours off too.

You can find out much more about Klea Insight if you drop me a line but, in the meantime here is the pretty picture and the link http://insight.nextmention.com/