<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-2915">
  <Title>Which Side are You on? Identifying Perspectives at the Document and Sentence Levels</Title>
  <Section position="9" start_page="114" end_page="114" type="ackno">
    <SectionTitle>
Acknowledgment
</SectionTitle>
    <Paragraph position="0"> This material is based on work supported by the Advanced Research and Development Activity (ARDA) under contract number NBCHC040037.</Paragraph>
    <Paragraph position="1"> A Gibbs Samplers Based the model specification described in Section 4.2 we derive the Gibbs samplers (Chen et al., 2000) for the Latent Sentence Perspective Model as follows,  where dbinom and dmultinom are the density functions of binomial and multinomial distributions, respectively. The superscript t indicates that a sample is from the t-th iteration. We run three chains and collect 5000 samples. The first half of burn-in samples are discarded.</Paragraph>
  </Section>
class="xml-element"></Paper>