Online product Opinion and Ranking System
ABSTRACT
A major concern when incorporating large sets of diverse ngram features for sentiment classification is the presence of noisy,
irrelevant, and redundant attributes. These concerns can often
make it difficult to harness the augmented discriminatory potential
of extended feature sets. We propose a rule-based multivariate
text feature selection method called Feature Relation Network
(FRN) that considers semantic information and also leverages the
syntactic relationships between n-gram features. FRN is intended
to
efficiently
heterogeneous
enable
n-gram
the
inclusion
features
for
of
extended
enhanced
sets
of
sentiment
classification. Experiments were conducted on three online review
test beds in comparison with methods used in prior sentiment
classification
research.
FRN
outperformed
the
comparison
univariate, multivariate, and hybrid feature selection methods; it
was able to select attributes resulting in significantly better
classification accuracy irrespective of the feature subset sizes.
Furthermore, by incorporating syntactic information about n-gram
relations, FRN is able to select features in a more computationally
efficient manner than many multivariate and hybrid techniques.
ALGORITHM - The FRN algorithm
EXISTING SYSTEM:
The existing feature selection methods do not adequately address
attribute relevance and redundancy issues, which are critical for text
sentiment analysis.
PROPOSED SYSTEM:
We propose the use of a rich set of n-gram features spanning many
fixed and variable n-gram categories. We couple the extended feature set
with a feature selection method capable of efficiently identifying an
enhanced subset of n-grams for opinion classification. The proposed Feature
Relation Network is a rule-based multivariate n-gram feature selection
technique that efficiently removes redundant or less useful n-grams,
allowing for more effective n-gram feature sets. Experimental results reveal
that the extended feature set and proposed feature selection method can
improve opinion classification performance over existing selection methods.
Advantage:
1. The
proposed
feature
selection
method
can
improve
opinion
classification performance.
2. The proposed Feature Relation Network is a rule-based multivariate ngram feature selection technique that allowing for more effective ngram feature sets.
MODULES
1. Admin Module.
2. Search Module.
3. Comments Module.
4. Rating Module.
Admin Module:
The Administrator can upload the mobile details as well as see the user
comments and rating. The admin can manage the mobile details such as edit
the mobile information and delete the mobile details.
Search Module:
In this module, the search consists of companies name, mobile prices,
mobile features and mobile screen types. The search result is providing in
the format of dynamic links. If the user clicks the dynamic link and then
view the corresponding mobile details.
Comments Module:
The user is giving comments to the particular mobile. Based on the
user comment it will move to the positive or negative opinion. While entering
the comments, user must enter the following details such as, user name,
email id and user comment. The admin can view user comments and details.
Rating Module:
The percentage within-one accuracy was incorporated since multiclass
opinion classification, involving three or more classes, can be challenging
given the relationship and subtle differences between semantically adjacent
classes. Based on the user comments, the admin provides the rating for the
particular mobile model.
SYSTEM SPECIFICATION
Hardware Requirements:
•
System
:
Pentium IV 2.4 GHz.
•
Hard Disk
:
40 GB.
•
Floppy Drive
:
1.44 Mb.
•
Monitor
:
14’ Colour Monitor.
•
Mouse
:
Optical Mouse.
•
Ram
:
512 Mb.
•
Keyboard
:
101 Keyboard.
Software Requirements:
•
Operating system
:
Windows XP.
•
Coding Language
:
ASP.Net with C#
•
Data Base
:
SQL Server 2005.