What is Multi-Stream Retrieval?
Multi-stream retrieval is about humans querying, exploring and discovering from streams of information.
Information Retrieval systems have been evolving to human needs and the data that is being spewed out. The nature of the web is evolving away from the public web towards a personal and a social web - where we hang out with things closer to us. The way we interact with this web is different. The systems we need to build to explore this closer web also needs to be different.
The talk outlays how multi-stream retrieval is different from traditional models of information retrieval - like the traditional flat web indexes, and brings to light the challenges and opportunities of interacting with streams.
The ways you interact with the web have changed. The full web is accessed through large directories, or a search engine. Your web is more of a stream – a stream of life events that happen to people and things you care about. Streams are aggregated and presented to you. The same systems that powered your access to the full web are not good enough when you interact with “your web”. Your web is not just documents. Your web is organized around people, time, context and thoughts. They keep happening. How should you be interacting with “your web”?
What do I even mean by “interacting with your web”?
Let me ask you a few questions, that are all pertinent when you interact with “your web”.
1) Tell me all the places visited by my friends this year.
2) Look at Sony’s Android product line, and then Samsung’s Android product line. Whats common in their feature evolution, and whats different?
3) What are the top interests among people who work at Intel?
4) What industries and sectors get the most attention from the VCs of India?
5) Whats similar between what I read yesterday, and what I am reading today?
6) Now that I am looking at this resume, what have I read in the recent past that may be interesting to him?
Do you get the idea? The nature of these searches are very different. They are all working on data that is very “close” to you. The objects of these questions are of interest to you. They all have their streams – and they are all emitting out data into the wild. You want to gather interesting aspects of these streams – that is not as straight forward as just searching on the web for some document. The results often lie across documents, and across streams!
This is multi-stream retrieval. For the uninitiated, Multi-stream retrieval is about humans querying, exploring and discovering from streams of information.
My linkedin profile: http://in.linkedin.com/in/bharathkumarmohan
I am an information dissemination enthusiast, having worked for more than 10 years studying how information spreads, the channels it uses and the way it is explored and absorbed. I got a Phd in this topic - mining nurturers in evolving social networks, and later on worked at Google, as part of Google News ranking news sources for authoritative reporting.
At Insieve, a startup I co-founded, we work on multi-stream retrieval - the ability to explore, analyse and discover from the streams that are dear to you. Whether you are an information geek, or a marketer, our systems help you gather insights from the living streams of data.
- A blog on this topic: http://blog.pugmarks.me/2013/04/04/what-is-multi-stream-retrieval/