Abstract:
Nowadays, online customer reviews become a
significant informative resource due to the rapid
development of web. In a webpage, the reviews are
written in natural language and are unstructuredfree-
texts scheme. To overcome the task of manually
scanning through large amount of review one by one,
people have interested to automatically process the
various reviews and to provide the necessary
information which is useful for both potential
customers and product manufactures, in a suitable
form. By applying dependency relations and
ontological knowledge, it can properly identify the
semantic relationships between product features and
opinions. It also finds the numeric score of all the
features using SentiWordNet. The proposed system
can specify the features in descending order of
importance. We offer an approach for considering an
alternative approach to discover the customer
opinion about tourism products, particularly hotels,
using opinions available on the Web as reviews.
