Saturday 9 April 2016

Live US Jobs Stream

Live US Jobs Stream

Live Jobs 

Take a look at my web page showing a live stream of jobs in North America.

Jobs Stream and Description
On the right side of the page there is a live stream of jobs found in Twitter messages. The log is refreshing automatically once new jobs are found.

See it all here.

Mechanics



Service is working using PubNub queue as source of messages. Python script subscribes to PubNub queue and listens for twitter messages. Once message comes it asks GEO Clustering service to find which cluster a message belongs to. If message belongs to North America cluster it asks text classification service if it contains a job offer. If there is a job offer in it the message it is published to output queue.

We can now subscribe to output queue consume job offers showing them on the web page. There can be many consumers subscribed to the queue.

Conclusions

  • ML engines talking to PubNub queues allow to build chains of services in very easy way.
  • Any kind of text classification is available at hand. It allows for many use cases related to finding information in streams of data.
  • Any kind of clustering is available at hand. GEO heat maps are very easy to implement.

Next

An engine finding sentiment information could be very useful. Stay tuned. Adding it to the chain will give a lot of flexibility.