BIOLSERV-L Archives

November 2012

BIOLSERV-L@LISTSERV.GMU.EDU

Options: Use Monospaced Font
Show HTML Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Tiffany Sandstrum <[log in to unmask]>
Reply To:
Date:
Wed, 21 Nov 2012 10:25:32 -0500
Content-Type:
multipart/alternative
Parts/Attachments:
text/plain (2357 bytes) , text/html (4 kB)

Begin forwarded message:

> From: "Jennifer L. Sturgis" <[log in to unmask]>
> Date: November 21, 2012 10:16:38 AM EST
> 
> Subject: Krasnow Monday seminar 11/26/12
> 
> 
> Please join us for the next Krasnow Monday Seminar on 11/26/12.
> Refreshments will be served at 3:30pm.  Come chat with colleagues and like-minded researchers and students prior to the talk at 4pm. 
> ---------------------------------------------------------------------
> 
> TITLE:
> Can You Accurately Gauge Sentiment With Social Media? A Comparison of Twitter Sentiment to Polling Data from the Nigerian Presidential Election of 2011
> 
> SPEAKER:  
> Clay Fink
> Senior Software Engineer
> The Johns Hopkins University Applied Physics Laboratory
> 
> DATE:  Monday, November 26, 2012
> TIME:  4:00 p.m.
> LOCATION:  Lecture Room (Room 229)
>            Krasnow Institute Building
>            George Mason University, Fairfax, VA
> 
> ABSTRACT:
> To what extent can social media be used to augment traditional opinion polling as a means of gauging political sentiment in the developing world? We investigate how well Twitter captured public opinion during  the run-up to the 2011 Nigerian Presidential election by comparing candidate mentions and extracted sentiment to official  election returns and polling data. We found significant correlations between  mentions of candidates and election results, indicating that Twitter mirrored the regional trends in the data. However, Twitter was less accurate in estimating mean levels  of support. Analysis of sentiment in tweets mirrored regional trends less accurately and showed a strong negativity bias against the incumbent president, although some correct geographic trends were still evident. This talk will discuss the techniques and methodologies used to collect Twitter data, extract sentiment from tweets, and compare this data to polling and election results. This was work done by Clay Fink, Nathan Bos, Jonathon Kopecky, and Edwina Liu, all at APL, under a grant from the Office of Naval Research.
> --------------------------------------------------------------------
> For additional directions or information call 703-993-4333 or browse to http://krasnow.gmu.edu/location/ .
> The full semester seminar schedule is at
> http://krasnow.gmu.edu/blog/category/monday-seminars/upcomingmondayseminars/ .
>  
> 
>  



ATOM RSS1 RSS2