<?xml version="1.0" standalone="yes"?>
<Paper uid="P04-1035">
  <Title>A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts</Title>
  <Section position="6" start_page="83" end_page="83" type="concl">
    <SectionTitle>
5 Conclusions
</SectionTitle>
    <Paragraph position="0"> We examined the relation between subjectivity detection and polarity classification, showing that subjectivity detection can compress reviews into much shorter extracts that still retain polarity information at a level comparable to that of the full review. In fact, for the Naive Bayes polarity classifier, the subjectivity extracts are shown to be more effective input than the originating document, which suggests 14For example, in the data we used, boundaries may have been missed due to malformed html.</Paragraph>
    <Paragraph position="1"> that they are not only shorter, but also &amp;quot;cleaner&amp;quot; representations of the intended polarity.</Paragraph>
    <Paragraph position="2"> We have also shown that employing the minimum-cut framework results in the development of efficient algorithms for sentiment analysis. Utilizing contextual information via this framework can lead to statistically significant improvement in polarity-classification accuracy. Directions for future research include developing parameterselection techniques, incorporating other sources of contextual cues besides sentence proximity, and investigating other means for modeling such information. null</Paragraph>
  </Section>
class="xml-element"></Paper>