Visualizing the #nonato Twitter hashtag – time series and top users

May 21, 2012

(This article was first published on Bommarito Consulting » r, and kindly contributed to R-bloggers)

style="text-align: justify;">  The title="NATO summit" href="" >NATO summit is currently being held in Chicago, and, as is typical for NATO or G# summits, the streets and tweets are full of dissent.  In the spirit of my past investigations of online dissent ( title="Visual Summary of #jan25 Twitter Activity" href="" >#jan25, title="Dataset: 5 Days of #25bahman" href="" >#25bahman, title="Twitter Hashtag Battle Royale – #(feb|fev)12 vs. #12(feb|fev)" href="" >#12fev, title="Dataset: Wisconsin Union Protester Tweets #wiunion" href="" >#wiunion, title="Plotting 3D Graphs with Python, igraph, and Cairo: #cn220 Example" href="" >#cn220, title="A quick look at #march11 / #saudi tweets" href="" >#march15), I thought I would investigate the #nonato tag, where Twitter users around the world are currently voicing their opinions on NATO, the NATO summit, and related topics.  Visualizing Twitter data is a simple and informative way to better understand these movements.

style="text-align: justify;">  The chart below shows the available history of the #nonato hashtag, beginning with title="cliffpotts" href="" >@cliffpotts at midnight UTC on May 12 and ending at 10:30 UTC this morning.  The time series shows a daily cycle with highest frequency during the late afternoon and night for Eastern/Central users.  Furthermore, while the summit only began on Sunday the 20th, organizing traffic on the hashtag increased significantly day-over-day on the 18th and 19th.  While the height of each bar indicates the total number of tweets every half hour, the color of each bar also indicates the number of unique users participating in the conversation.  We see that the traffic prior to the 20th was primarily driven by a small number of users, whereas the 20th and 21st saw a greater diversity of users participating.


href=""> class="aligncenter size-large wp-image-803" title="#nonato Twitter time series" src="" alt="" width="550" height="366" />

style="text-align: justify;">  Most Twitter movements, though large and somewhat decentralized, do have leaders or organizers.  The easiest way to identify these individuals outside of a network context is to simply count the highest frequency users.  The chart below shows the top 25 Twitter users over this period, including href="" >@sickjew, href="" >@cliffpotts, href="" >@OccupyChicago, href="" >@exileinflyville, and href="" >@laurapcd1.

href=""> class="aligncenter size-large wp-image-805" title="Top Twitter users on #nonato" src="" alt="" width="550" height="366" />

style="text-align: justify;">  If you’re interested in more information about how the data and charts were produced, please see posts like title="Charting Twitter time series data with tweet and unique user counts" href="">#1, title="Archiving Tweets with Python" href="">#2, or title="Visual Summary of #jan25 Twitter Activity" href="">#3.  If you’d like a report or analysis like this for your own purposes, please title="Contact" href="">feel free to contact me for more information.

To leave a comment for the author, please follow the link and comment on his blog: Bommarito Consulting » r. offers daily e-mail updates about R news and tutorials on topics such as: visualization (ggplot2, Boxplots, maps, animation), programming (RStudio, Sweave, LaTeX, SQL, Eclipse, git, hadoop, Web Scraping) statistics (regression, PCA, time series, trading) and more...

If you got this far, why not subscribe for updates from the site? Choose your flavor: e-mail, twitter, RSS, or facebook...

Tags: , , , , , , , ,

Comments are closed.