tag:blogger.com,1999:blog-11752373.post4418677635598955831..comments2023-12-19T17:12:41.079+09:00Comments on The Unstoppable Force: Analytics with Twitter DataVenkathttp://www.blogger.com/profile/09538725607137736665noreply@blogger.comBlogger3125tag:blogger.com,1999:blog-11752373.post-85721477360212222792011-01-20T17:05:12.798+09:002011-01-20T17:05:12.798+09:00@Utkarsh : the idea of this post was to include al...@Utkarsh : the idea of this post was to include all these features 'as part of twitter' and not a third party app. MOst of the features are better implemented when twitter leverages its own platform; and we do not ncessarily have to depend on 3rd party apps - there are tradeoffs with the latter. For eg. i have scripts to check for #1 and #2 to check followers etc, but its a pain to maintain it, better if implemented via Twitter. Also sentiment analysis is a much studied topic - check out Mannings' group at Stanford - so many projects that students do as their projects. Patil's team at Linkedin did an excellant job with graph analysis - the advantage of such a kind of analysis is that you can launch that as a product in addition to that being 'cool'. Qwitter(or something similar ) was there present which found out when people unfollow you. <br /><br />Hope you get the drift ;)<br /><br />I would imagine this feature set as a Dashboard at Twitter than having a zillion apps running all over the place; and personally i am not a great fan of testing each and every api/app that is in the market.<br /><br />What the Web needs is consolidation, and i think that is happening.Venkathttps://www.blogger.com/profile/09538725607137736665noreply@blogger.comtag:blogger.com,1999:blog-11752373.post-51235762338825856152011-01-20T13:19:11.106+09:002011-01-20T13:19:11.106+09:00contd ...
8. Decipher moods/sentiments from the ...contd ...<br /><br /><br />8. Decipher moods/sentiments from the tweets; or other possible natural language processing techniques that can be applied on the tweets to gather interesting patterns or insights.<br /><br />People at Northwest university, among others, are <a href="http://www.ccs.neu.edu/home/amislove/twittermood/" rel="nofollow">working on it</a>. Though sentiment analysis is generally a tricky to do upfront for customers, it might give some insights on behind the curtains on anonymized data.<br /><br /><br /><br />9. Usage analysis<br /> a. Based on the day of the hour we can find out do people tweet often during mornings or evenings.<br /> b. Do people prefer the web or mobile devices for tweeeting. What % of people uses other apps?<br /> c. Who retweets you often? or what category of tweets by you get retweeted often or generate the maximum discussions.<br />10. Most famous tweets for the day/week/month - based on retweets, follow-up discussions, celebrity status of the tweeter, number of followers.<br /><br />There is <a href="www.klout.com" rel="nofollow">Klout</a> for that, though I am not sure <a href="http://www.wewillraakyou.com/2010/12/klout-is-broken/" rel="nofollow">how good they are</a>.<br /><br /><br />11. Duplicate detection of tweets. Also, automatic compression of tweets which fall in a thread. This would help a lot in reducing the information clutter.<br /><br />Threading of tweets is not easy to detect. Personal experience.<br /><br /><br />12. what is the similarity between two users - based on the nature of tweets. Corollary would be : what topics/categories does a user often tweet on?<br /><br />This, I think, is a natural extension of <a href="http://www.peerindex.net/" rel="nofollow">PeerIndex</a>.<br /><br /><br />13. Better trend analysis.<br /><br />Better, unfortunately, is very difficult to quantify. More so, they are prone to being <a href="http://www.businessinsider.com/how-to-crack-the-new-york-times-most-e-mailed-list-2010-12" rel="nofollow">gamed</a> if not done properly.<br /><br />~<br />musically_utmusically_uthttps://www.blogger.com/profile/00017318258700020690noreply@blogger.comtag:blogger.com,1999:blog-11752373.post-12275020342442212982011-01-20T13:13:33.104+09:002011-01-20T13:13:33.104+09:00Hi,
I have been playing around with Twitter of la...Hi,<br /><br />I have been playing around with Twitter of late too and here are my 2 cents on features requested (broken comments because of character limit):<br /><br /><br />1. Users who follow you, but you do'nt follow them.<br />2. Users whom you follow, but they don't follow back.<br /><br />True.<br /><br /><br />3. Notification when a user stops following you. I need to research on why Twitter does not have this - was this by design?<br /><br />There is <a href="http://who.unfollowed.me/" rel="nofollow">an app for that</a>, which apparently also got nominated for the Short Awards for one of the best Twitter Apps. However, I think that this is a <i>feature</i> which lets people still keep their Twitter accounts useful while avoiding a social confrontation. :)<br /><br /><br />4. Trend analysis of users who follow/quit you - based on the tweets that you do.<br /><br />I am not sure how to define quantitatively the causal link between what one tweeted last/15 minutes ago/1 hour ago/a day ago with what changes are happening with one's social network. The best one can do is perhaps put them all in a singular timeline showing Tweets interspersed with following/quitting. Is that what you had in mind?<br /><br /><br />5. Show the most active users and lazy users - active and lazy are defined by the number of tweets and also the popularity of the tweets.Popularity can also be measured by how much discussion a tweet generates, or how much retweets happen for that tweet.<br /><br />I think people will be heavily underwhelmed if they knew this about themselves. :)<br /><br /><br />6. Automatic lists and follow suggestion : when we follow a user, twitter can suggest which would be the most likely fit for a user based on his tweet patterns. The present Suggestion scheme is not all powerful and needs some tweaking.<br /><br />I think this is a part of the current million dollar question: how to recommend the right thing to a customer.<br />We'll be seeing improvements in it till hell freezes over.<br /><br /><br />7. Discover clusters/groups of the followers. Centrality of users - show a graph wherein this relationship can be displayed.<br /><br />Flowing data had a <a href="http://flowingdata.com/2008/03/12/17-ways-to-visualize-the-twitter-universe/" rel="nofollow">great post</a> regarding this some time ago.<br />I think it is only a matter of time before @TwitterFolks find one which suits them and employ it.<br /><br />contd ...musically_uthttps://www.blogger.com/profile/00017318258700020690noreply@blogger.com