Show simple item record

Mining Political Blogs With Network Based Topic Models

dc.contributor.advisor Banks, David L
dc.contributor.author Liang, Jiawei
dc.date.accessioned 2014-05-14T19:23:09Z
dc.date.available 2014-05-14T19:23:09Z
dc.date.issued 2014
dc.identifier.uri https://hdl.handle.net/10161/8860
dc.description.abstract <p>We develop a Network Based Topic Model (NBTM), which integrates a Random</p><p>Graph model with the Latent Dirichlet Allocation (LDA) model. The NBTM assumes that the topic proportion of a document has a xed variance across the document corpus with author dierences treated as random eects. It also assumes that the links between documents are binary variables whose probabilities depend upon the author random eects. We t the model to political blog posts during the calendar year 2012 that mention Trayvon Martin. This paper presents the topic extraction results and posterior prediction results for hidden links within the blogosphere.</p>
dc.subject Statistics
dc.subject Political Science
dc.title Mining Political Blogs With Network Based Topic Models
dc.type Master's thesis
dc.department Statistical and Economic Modeling


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record