<?xml version="1.0" standalone="yes"?>
<Paper uid="H05-1043">
  <Title>Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP), pages 339-346, Vancouver, October 2005. c(c)2005 Association for Computational Linguistics Extracting Product Features and Opinions from Reviews</Title>
  <Section position="3" start_page="339" end_page="339" type="intro">
    <SectionTitle>
2 Terminology
</SectionTitle>
    <Paragraph position="0"> A product class (e.g., Scanner) is a set of products (e.g., Epson1200). OPINE extracts the following types of product features: properties, parts, features of product parts, related concepts, parts and properties of related concepts (see Table 1 for examples of such features in the Scanner domains). Related concepts are concepts relevant to the customers' experience with the main product (e.g., the company that manufactures a scanner). The relationships between the main product and related concepts are typically expressed as verbs (e.g., &amp;quot;Epson manufactures scanners&amp;quot;) or prepositions (&amp;quot;scanners from Epson&amp;quot;). Features can be explicit (&amp;quot;good scan quality&amp;quot;) or implicit (&amp;quot;good scans&amp;quot; implies good ScanQuality).</Paragraph>
    <Paragraph position="1"> OPINE also extracts opinion phrases, which are adjective, noun, verb or adverb phrases representing customer opinions. Opinions can be positive or negative and vary in strength (e.g., &amp;quot;fantastic&amp;quot; is stronger than &amp;quot;good&amp;quot;).</Paragraph>
  </Section>
class="xml-element"></Paper>