<?xml version="1.0" standalone="yes"?>
<Paper uid="N06-3005">
  <Title>Identifying Perspectives at the Document and Sentence Levels Using Statistical Models</Title>
  <Section position="3" start_page="0" end_page="227" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> In this paper we investigate the problem of automatically identifying the perspective from which a document was written. By perspective, we mean &amp;quot;subjective evaluation of relative significance, a point-of-view.&amp;quot; For example, documents about the Palestinian-Israeli conflict may appear to be about the same topic, but reveal different perspectives: [?]This is joint work with Theresa Wilson, Janyce Wiebe, and Alexander Hauptmann, and supported by the Advanced Research and Development Activity (ARDA) under contract number NBCHC040037.</Paragraph>
    <Paragraph position="1"> (1) The inadvertent killing by Israeli forces of Palestinian civilians - usually in the course of shooting at Palestinian terrorists - is considered no different at the moral and ethical level than the deliberate targeting of Israeli civilians by Palestinian suicide bombers.</Paragraph>
    <Paragraph position="2"> (2) In the first weeks of the Intifada, for example, Palestinian public protests and civilian demonstrations were answered brutally by Israel, which killed tens of unarmed protesters.</Paragraph>
    <Paragraph position="3"> Example 1 is written from a Israeli perspective; Example 2 is written from a Palestinian perspective .</Paragraph>
    <Paragraph position="4"> We aim to address a research question: can computers learn to identify the perspective of a document given a training corpus of documents that are written from different perspectives? When an issue is discussed from different perspectives, not every sentence in a document strongly reflects the perspective the author possesses. For example, the following sentences are written by one Palestinian and one Israeli:  (3) The Rhodes agreements of 1949 set them as the ceasefire lines between Israel and the Arab states.</Paragraph>
    <Paragraph position="5"> (4) The green line was drawn up at the Rhodes  Armistice talks in 1948-49.</Paragraph>
    <Paragraph position="6"> Example 3 and 4 both factually introduce the background of the issue of the &amp;quot;green line&amp;quot; without expressing explicit perspectives. Can computers automatically discriminate between sentences that strongly express a perspective and sentences that only reflect shared background information?  A system that can automatically identify the perspective from which a document written will be a highly desirable tool for people analyzing huge collections of documents from different perspectives. An intelligence analyst regularly monitors the positions that foreign countries take on political and diplomatic issues. A media analyst frequently surveys broadcast news, newspapers, and web blogs for different viewpoints. What these analysts need in common is that they would like to find evidence of strong statements of differing perspectives, while ignoring statements without strong perspectives as less interesting.</Paragraph>
    <Paragraph position="7"> In this paper we approach the problem of learning perspectives in a statistical learning framework. We develop statistical models to learn how perspectives are reflected in word usage, and evaluate the models by measuring how accurately they can predict the perspectives of unseen documents. Lacking annotation on how strongly individual sentences convey a particular perspective in our corpus poses a challenge on learning sentence-level perspectives. We propose a novel statistical model, Latent Sentence Perspective Model, to address the problem.</Paragraph>
  </Section>
class="xml-element"></Paper>