<?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="3" start_page="0" end_page="109" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> In this paper we investigate a new problem of automatically identifying the perspective from which a document is written. By perspective we mean a &amp;quot;subjective evaluation of relative significance, a point-of-view.&amp;quot;1 For example, documents about the Palestinian-Israeli conflict may appear to be about the same topic but reveal different perspectives:  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="1"> (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="2"> Example 1 is written from an Israeli perspective; Example 2 is written from a Palestinian perspective. Anyone knowledgeable about the issues of the Israeli-Palestinian conflict can easily identify the perspectives from which the above examples were written. However, can computers learn to identify the perspective of a document given a training corpus? null When an issue is discussed from different perspectives, not every sentence strongly reflects the perspective of the author. For example, the following sentences were written by a Palestinian and an Israeli.</Paragraph>
    <Paragraph position="3">  (3) The Rhodes agreements of 1949 set them as the ceasefire lines between Israel and the Arab states.</Paragraph>
    <Paragraph position="4"> (4) The green line was drawn up at the Rhodes  Armistice talks in 1948-49.</Paragraph>
    <Paragraph position="5"> Examples 3 and 4 both factually introduce the background of the issue of the &amp;quot;green line&amp;quot; without expressing explicit perspectives. Can we develop a  system to automatically discriminate between sentences that strongly indicate a perspective and sentences that only reflect shared background information? null A system that can automatically identify the perspective from which a document is written will be a valuable tool for people analyzing huge collections of documents from different perspectives. Political analysts regularly monitor the positions that countries take on international and domestic issues. Media analysts frequently survey broadcast news, newspapers, and weblogs for differing viewpoints. Without the assistance of computers, analysts have no choice but to read each document in order to identify those from a perspective of interest, which is extremely time-consuming. What these analysts need is to find strong statements from different perspectives and to ignore statements that reflect little or no perspective.</Paragraph>
    <Paragraph position="6"> In this paper we approach the problem of learning individual perspectives in a statistical framework. We develop statistical models to learn how perspectives are reflected in word usage, and we treat the problem of identifying perspectives as a classification task. Although our corpus contains document-level perspective annotations, it lacks sentence-level annotations, creating a challenge for learning the perspective of sentences. We propose a novel statistical model to overcome this problem. The experimental results show that the proposed statistical models can successfully identify the perspective from which a document is written with high accuracy. null</Paragraph>
  </Section>
class="xml-element"></Paper>