Indimeme – meme tracker for Indian blogosphere

If you closely follow technology news, TechMeme has gotta be in your daily reading list. Indimeme is a similar effort at developing a meme tracker for Indian blogosphere. The ‘hot’ stories from Indian blogosphere are presented in a semi-clustered way. The site is a project by Raj @Teknobites and currently includes 100 Indian blogs with plans to include additional blogs later.

The site is a good start but is different from Techmeme is several respects. The biggest difference is that Techmeme follows links and trackbacks from blogs and uses this link structure to build its clusters. Indimeme, meanwhile, seems to read the blog feeds and uses text summarization to build the clusters.  This method does not always generate good quality clusters and a lot boils down to how effectively the text is summarized.

It isnt very difficult to build a site that uses document clustering. Using open source software like Carrot2 & Nutch etc. you can put together a similar site as well. Its the quality of the clusters and the fine-tuning that actually matter. If document clustering sounds interesting to you, see my earlier post on document clustering algorithms and related technology.

Similar Posts

• Click, scan and fax with your mobile using Indifax
• Jobyantra – Affiliate based job board for Indian startups
• VidyaCenter – marketplace for coaching and education

Comments

7 Responses to “Indimeme – meme tracker for Indian blogosphere”

1. Sachin says:

   May 16, 2008 at 1:07 am

   wow..good news..thnx Pranav for sharing this site.
2. Paras Chopra says:

   May 16, 2008 at 4:19 am

   I’ve made a similar site on Indian Startup Scene. It currently aggregates content from 19 websites (including this blog).

   Have a look at it: http://india.startuplogic.com
3. Ram says:

   May 16, 2008 at 4:08 pm

   Pranav thanks for the review.
   Yah you are right, it is different from techmeme, it just reads feeds. The problem with following links is i will end up with all blogs, not specific to India. The site is built on open source tools and developer APIs.

   One correction i am “Ram@Teknobites” not Raj
4. Debashish says:

   May 19, 2008 at 2:16 am

   Nice analysis. Any PHP based alternative to Carrot2 & Nutch?
5. Nikhil Pahwa says:

   May 19, 2008 at 6:37 am

   I’ve been through Indimeme twice in the last hour and a half, and the top story is still the same. frequency of updates is critical.

   secondly, they’ve got to get the timing sorted out. we did a story at around 8:50am, and others followed up, and yet we’re not leading the news for that news.
6. pranav says:

   May 19, 2008 at 5:58 pm

   @ram – sorry about that…will correct it later today.

   @debashish – dont know about php alternative to nutch..but you can use carrot2 in your php code via their REST interface. I had a working model for carrot2 quite some time ago – but never got the time to fine tune the noise.

   @nikhil – indimeme, in its current form, is definitely not a killer product. thats why i didnt give it a raving review. all the stuff that you mention above — that is a part of fine-tuning the meme tracker…and it is lacking in indimeme currently.
7. Ram says:

   May 24, 2008 at 5:57 am

   @Nikhil
   “the top story is still the same.”
   where is the breaking news in India, except you and 2 or 3 other blogs no one is reporting current news in the same timeframe (with in 24 or 48 hours). That is one of the reason the front page is not changing very frequently.