Third Brownbag of the Semester – February 8, 2013

Johan Bollen

Social Media Analytics to Gauge Public Sentiment and Predict Socio-economic Indicators             

Johan Bollen is associate professor at the Indiana University School of Informatics and Computing. He was formerly a staff scientist at the Los Alamos National Laboratory from 2005-2009, and an Assistant Professor at the Department of Computer Science of Old Dominion University from 2002 to 2005. He obtained his PhD in Experimental Psychology from the Vrije Universiteit Brussel (VUB) in 2001. He has published more than 75 articles on computational social science, social media analytics, informetrics, and digital libraries. His research has been funded by the NSF, IARPA, and Andrew W. Mellon Foundation.

Professor Bollen reviewed his very interesting research on the power of Twitter as an indicator of mood. Natural language processing can be used to assign tweets to different mood categories, such as anxious or elated. Bollen grabs huge datasets (10m tweets and more) and tracks mood frequency through time. He then checks whether Twitter mood predicts important socio-economic indicators; it does. The findings are useful in that Twitter data are available in large bundles in near-real time, whereas surveys of public attitudes are available in small samples with significant delay. Bollen’s work puts our finger directly on the pulse.

For scholars in Communication, this talk demonstrates an exciting new way of doing research. Rather than rely solely on small-N lab studies and time-intensive content analyses, we can also use large data sets, machine learning, and natural language processors to track and possibly predict communication effects at the macro level.

– Edward Castronova

Advertisements
Previous Post
Next Post
Leave a comment

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: