[Air-L] ICA Preconference: Crowdsourcing as a Content Analysis Tool

[Lei Guo]

ICA Preconference: Crowdsourcing as a Content Analysis Tool


May 24, 13:00 - 17:00

Hilton Prague

Crowdsourcing is a popular method in computer science for categorizing and
classifying text and objects. This preconference introduces crowdsourcing
for communication researchers as an emerging content analysis method.
Rather than rely on a few human coders to carry out a content analysis, the
crowdsourcing approach outsources coding tasks to numerous people online
(e.g., multiple people code the same item), and applies an aggregation
policy to make a decision on a given item.

Through a hands-on workshop and research presentations, this preconference
explores:

1) Different crowdsourcing platforms to carry out a project. A
demonstration will be given to show how to use two different crowdsourcing
platforms: Amazon’s Mechanical Turk (MTurk), a well-established service,
and Crowdflower, an emerging service. In the hands-on workshop, attendees
will set up their own project on one of the platforms, and be guided in the
steps, from set-up to extracting and analyzing the crowdworkers’ results.

2) Crowdsourcing as a method that is both cheaper and more efficient than
manual content analysis. Can it also be as valid and reliable? Research
presentations on both “crowdcoding” and traditional manual coding will be
given, as well as a discussion about cost structure and features to ensure
quality results. The Speakers/Panelists include:

Hajo Boomgaarden, Professor of empirical social science method, University
of Vienna

Brendan Watson, Assistant professor of journalism, Michigan State University

Lei Guo, Assistant professor of emerging media studies, Boston University

Margrit Betke, Professor of computer science, Boston University

Kate Mays, Ph.D. student in emerging media studies, Boston University

This is a half-day preconference. For questions, contact Dr. Lei Guo (
guolei at bu.edu).
To register, follow this link
<http://www.icahdq.org/event/PC24_Crowdsourcing>.