Page 6 - Campus Chronicles Technical Magazine 2020

Thus the developed system as well within the MODULES:
Weakly - Supervised
Deep Embedding For
Product Review
Sentiment Analysis
By Ms. Pranitha Mettu,
B. Tech (ECE) - 20UP1A0428
INTRODUCTION: People are getting used to
consuming online and writing comments about
their purchase experiences on merchant/
review Websites.
These opinionated contents are valuable
resources both to future customers for
decision-making and to merchants for
improving their products and/or service.
However, as the volume of reviews grows
rapidly, people have to face a severe
information overload problem.
EXISTING SYSTEM: Lexicon-based methods
typically take the tack of first constructing a
sentiment lexicon of opinion words (e.g.
“wonderful”, “disgusting”), and then design
classification rules based on appeared opinion
words and prior syntactic knowledge. Despite
effectiveness, this kind of methods requires
substantial efforts in lexicon construction and
rule design. Furthermore, lexicon-based
methods cannot well handle implicit opinions,
i.e. objective statements such as “I bought the
mattress a week ago, and a valley appeared
today”. As pointed out in this is also an
important form of opinions. Factual information
is usually more helpful than subjective feelings.
Lexicon-based methods can only deal with
implicit opinions in an ad-hoc way.
TECHNEWIL
CLUB
ACTIVITIES
PROPOSED SYSTEM: In this work, we propose
a novel deep learning framework for review
sentence sentiment classification. The
framework treats review ratings as weak labels
to train deep neural networks. For example,
with 5-stars scale we can deem ratings
above/below 3-stars as positive/ negative
weak labels respectively. The
Framework generally consists of two steps. In
the first step, rather than predicting sentiment
labels directly, we try to learn an embedding
space (a high level layer in the neural network)
which reflects the general sentiment
distribution of sentences, from a large number
of weakly labeled sentences.
SYSTEM STUDY: Three key considerations
1. Economical Feasibility
2. Technical Feasibility
3. Social Feasibility
ECONOMICAL FEASIBILITY: This study is
carried out to check the economic impact that
the system will have on the organization. The
amount of fund that the company can pour into
the research and development of the system is
limited. The expenditures must be justified.
Campus
CHRONICLES
Technical Magazine
budget and this was achieved because most of
the technologies used are freely available.
Only the customized products had to be
purchased.
TECHNICAL FEASIBILITY: This study is carried
out to check. Any system developed must not
have a high demand on the available technical
resources. This will lead to high demands on
the available technical resources. This will lead
to high demands being placed on the client.
The developed system must have a modest
requirement, as only minimal or null changes
are required for implementing this system.
SOCIAL FEASIBILITY: The aspect of study is to
check the level of acceptance of the system by
the user. This includes the process of training
the user to use the system efficiently. The user
must not feel threatened by the system,
instead must accept it as a necessity. The level
of acceptance by the users solely depends on
the methods that are employed to educate the
user about the system and to make him familiar
with it. His level of confidence must be raised
so that he is also able to make some
constructive criticism, which is welcomed, as
he is the final user of the system.
ARCHITECTURE:
Campus
6 7 CHRONICLES
Technical Magazine
There are five modules divided in this project in
order develop the concept of sentiment
analysis with tagging. They are listed below
1. Products Initiation
2. Products acquisition
3. Sentiment classification
4. Weak Supervision
5. Graphical Analysis
PRODUCTS INITIATION:
The First phase of the implementation of this
project is Products Initiation. In this module
admin is uploading the products which user
wants to see and purchase. Once admin
uploads the product means it stored in the
database. The products which are uploaded
are listed in website to admin in order to modify
or delete the particular product. Admin is the
only authorized person to upload the products
in this project.
PRODUCTS ACQUISITION: The second
module of this product conveys that user can
view the products which are uploaded by
admin. Then they can view the ratings and
reviews of the same products which are given
by other users who already purchased the
product. According to the help of ratings and
reviews user can purchase the product. The
ordered list is also shown in the project for the
convenience of users. The cart and checkout
facility is also available to users from this
module.
SENTIMENT CLASSIFICATION: The users who
are all purchased the products can rate product
as per their interest on one scale of five and
they are free to comment for the same. Based
on the ratings and reviews given by user
sentiment can be analyzed. There are two
sentiments maintained in this project they are
positive and negative.