Software Requirements Specification

for
Sentimental Analysis
 1. Introduction

1.1 Purpose

The purpose of this system is to Develop natural language processing (NLP), sentiment analysis
and data mining technologies to build a public opinion analysis system to serve enterprises' need
of online public opinion detection

1.2 Document Conventions

In our system mainly two users are there; first one is user who uses a system and second is
admin. In the SRS, we are taking both users.

1.3 Intended Audience and Reading Suggestions

Audience of this SRS are other project developer, users like students, viewers that will use
system. This SRS contains detail description about the product, its functioning, different external
interfaces required, system features, Nonfunctional requirements and some additional
requirements.

1.4 Product Scope

Sentiment analysis is a uniquely powerful tool for businesses that are looking to measure
attitudes, feelings and emotions regarding their brand. To date, most sentiment analysis projects
have been conducted almost exclusively by companies and brands through the use of social
media data, survey responses and other hubs of user-generated content. By investigating and
analyzing customer sentiments, these brands can get an inside look at consumer behaviors and,
ultimately, better serve their audiences with the products, services and experiences they offer.
References

[1] Pang, B. & Lee, L. (2008), “Opinion Mining and Sentiment Analysis”. In Foundations and Trends in
Information Retrieval.
[2] Hu, M. & Lui, B. (2004), “Mining and Summarizing Customer Reviews”. In Proceedings of ACM
SIGKDD Conference on Knowledge Discovery and Data Mining 2004 (KDD-2004).
[3] Ku, L.-W., Liang, Y.-T., & Chen, H, “Opinion extraction, summarization and tracking in news and
blog corpora”. In AAAI-CAAW‟06.
[4] Kunpeng Zhang, Ramanathan Narayanan, “Voice of the Customers: Mining Online Customer
Reviews for Product”, 2010.
[5] H. Tang, S. Tan and X. Cheng, “ A survey on sentiment detection of reviews”, In Proceedings of the
Expert Systems with Applications 36, Elsevier Ltd., Beijing, 2009.
[6] Ortigosa-Hernandez Jonathan, Rodriguez Juan Diego, Alzate Leandro, Lucania Manuel, InzaInaki,
Lozano, Jose,” A. Approaching sentiment analysis by using semi-supervised learning of multi-
dimensional classifiers”Neurocomputing;92:98-115,2012.
[7] Kim S, Hovy E,” Determining the sentiment of opinions”, In: Proceedings of international conference
on Computational Linguistics (COLING‟04) - 2004.
[8] Read J, carol J.,” Weakly supervised techniques for domain independent sentiment classification”, In:
Proceeding of the 1st international CIKM workshop on topic-sentiment analysis for mass opinion; P.45-
52, 2009.
[9] Pang, B., & Lee, L. (2004). A sentimental education: Sentiment analysis using subjectivity
summarization based on minimum cuts. In Proceedings of the association for computational linguistics.
[10] Burns, N., Bi, Y., Wang, H., & Anderson, T. (2011). Sentiment analysis of customer reviews:
Balanced versus unbalanced datasets. In Knowledge based and intelligent information and engineering
systems. Lecture notes in computer science (Vol. 6881, pp. 161–170). Berlin/ Heidelberg: Springer.
2. Overall Description
2.1 Product Perspective
Public opinion is the sum of multiple emotions, wishes, attitudes and ideas among individuals
and various social groups in a certain historical stage and social space. Internet public opinion
can be developed from online speech and is a specific form of public opinion. Whether Internet
speech can develop into Internet public opinion largely depends on whether the topic of Internet
speech has strong activeness and sensitivity. Online public opinion is diversified, spread quickly
and interactive, which has the incomparable advantages over traditional media. Online public
opinion has positive and healthy aspects, as well as negative and decadent aspects

2.2 Product Functions

 Get data from multiple sources like Social Networking sites, Forums etc.
 Pre-processing is done to improve accuracy of Data.
 Machine Learning is used to improve the accuracy of System.
 Allows much more detailed sentiment analysis on each entity.
 Listen to your user/customers in real time and make data-based decisions on the go.

2.3 User Classes and Characteristics

In our system have mainly two users, first is the who uses a system and second is the admin.
 User: user can only enter search keyword and view result.
 Admin: These users has an authority to update, schedule and Configure a system.

2.4 Operating Environment

Our project is based cloud and user application runs on any web browser and platform. So, we
need desktop or android, or iOS based smart phone to run the application.
2.5 Design and Implementation Constraints
There are three major components for our system are admin panel, user panel and dataset

2.6 User Documentation

User manual will be provided with this system.

2.7 Assumptions and Dependencies

Only assumptions in the system is that user has knowledge of smartphone and internet.
3. External Interface Requirements

3.1 User Interfaces

The user must have an Android or iOS application or system with working internet connection.

3.2 Hardware Interfaces

No hardware interfaces needed except internet Connectivity.

3.3 Software Interfaces

Our project is based on cloud application so cloud account and subscription must be done.

3.4 Communications Interfaces

The internet connection plays important role which is updating the data in real-time.
4. System Features
4.1 System Feature 1
4.1.1 Description and Priority
Detect positive and Negative reviews: Priority is high
4.1.2 Stimulus/Response Sequences
 Give quick response when user enter keyword.
 Run system in using previously fetched dataset when not connected to cloud
(Internet).
4.1.3 Functional Requirements
 Signup Form – For new users to create account
 Login Form – For existing users to login into the system
 Search Page – To Perform opinion mining input fields are provided
 Report Page – To display detailed analysis and visualization
 Setting page – To create A – For existing users to login into the system PI setting for
Facebook, Twitter etc.

4.1.4 Performance Requirements

 Usability– The software should be usable, without any efforts and it should have
appropriate user interface.
 Maintainability– The software must be designed to be user-friendly to be maintained by
even person with non-IT background.
 Response Time– The software should response within the estimated time to display
results to the user.
5. Other Nonfunctional Requirements

5.1 Performance Requirements

The system should give quick result on search query.

5.2 Safety Requirements

The maintenance should not be done without taking backup.

5.3 Security Requirements

there is no need of security mechanism.

5.4 Software Quality Attributes

• Reliability
The reliability that anyone can easily perform the sentimental analysis without any special
training.
• Availability
System will available at all time until power or internet problem. If we provide backup power
supply, then we can say that our system availability is 100%.
• Maintainability
Our system usually not required maintenance until some modification to be done.
• Portability
The application is works on desktop and mobile platform.
6. Other Requirements
We require a working internet connection to update from cloud.