<?xml version="1.0" standalone="yes"?>
<Paper uid="P02-1053">
  <Title>Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> This paper presents a simple unsupervised learning algorithm for classifying reviews as recommended (thumbs up) or not recommended (thumbs down). The classification of a review is predicted by the average semantic orientation of the phrases in the review that contain adjectives or adverbs. A phrase has a positive semantic orientation when it has good associations (e.g., &amp;quot;subtle nuances&amp;quot;) and a negative semantic orientation when it has bad associations (e.g., &amp;quot;very cavalier&amp;quot;). In this paper, the semantic orientation of a phrase is calculated as the mutual information between the given phrase and the word &amp;quot;excellent&amp;quot; minus the mutual information between the given phrase and the word &amp;quot;poor&amp;quot;. A review is classified as recommended if the average semantic orientation of its phrases is positive. The algorithm achieves an average accuracy of 74% when evaluated on 410 reviews from Epinions, sampled from four different domains (reviews of automobiles, banks, movies, and travel destinations). The accuracy ranges from 84% for automobile reviews to 66% for movie reviews.</Paragraph>
  </Section>
class="xml-element"></Paper>