Extracting Product Features and Opinions from Reviews - Natural Language Processing and Text Mining - page 8

2
Extracting Product Features and Opinions
from Reviews
Ana-Maria Popescu and Oren Etzioni
2.1 Introduction
The Web contains a wealth of opinions about products, politicians, and more,
which are expressed in newsgroup posts, review sites, and elsewhere. As a
result, the problem of “opinion mining” has seen increasing attention over the
past three years from [1, 2] and many others. This chapter focuses on product
reviews, though we plan to extend our methods to a broader range of texts
and opinions.
Product reviews on Web sites such as amazon.com and elsewhere often
associate meta-data with each review, indicating how positive (or negative)
it is using a 5-star scale, and also rank products by how they fare in the
reviews at the site. However, the reader's taste may differ from the reviewers'.
For example, the reader may feel strongly about the quality of the gym in a
hotel, whereas many reviewers may focus on other aspects of the hotel, such
as the decor or the location. Thus, the reader is forced to wade through a
large number of reviews looking for information about particular features of
interest.
We decompose the problem of review mining into the following main sub-
tasks:
I. Identify product features . In a given review, features can be explicit
( e.g. , “the size is too big ”) or implicit ( e.g. , “the scanner is slow” refers to
the “scanner speed”).
II. Identify opinions regarding product features . For example, “the
size is too big” contains the opinion phrase “too big,” which corresponds to
the “size” feature.
III. Determine the polarity of opinions . Opinions can be positive
( e.g. , “this scanner is so great” )or negative ( e.g. , “this scanner is a complete
disappointment” ).
IV. Rank opinions based on their strength . For example, “horrible”
is a stronger indictment than “bad.”