<?xml version="1.0" standalone="yes"?>
<Paper uid="N03-4017">
  <Title>Identifying Opinionated Sentences</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Natural language processing applications that summarize or answer questions about news and other discourse need to process information about opinions, emotions, and evaluations. For example, a question answering system that could identify opinions in the news could answer questions such as the following: Was the 2002 presidential election in Zimbabwe regarded as fair? What was the world-wide reaction to the 2001 annual U.S. report on human rights? In the news, editorials, reviews, and letters to the editor are sources for finding opinions, but even in news reports, segments presenting objective facts are often mixed with segments presenting opinions and verbal reactions. This is especially true for articles that report on controversial or &amp;quot;lightning rod&amp;quot; topics. Thus, there is a need to be able to identify which sentences in a text actually contain expressions of opinions and emotions.</Paragraph>
    <Paragraph position="1"> We demonstrate a system that identifies opinionated sentences. In general, an opinionated sentence is a sentence that contains a significant expression of an opinion, belief, emotion, evaluation, speculation, or sentiment. The system was built using data and other resources from a summer workshop on multi-perspective question answering (Wiebe et al., 2003) funded under</Paragraph>
  </Section>
class="xml-element"></Paper>