NLP Classifying Positive & Negative Restaurant Reviews

(Bag of Words Model)

BACHELOR OF TECHNOLOGY
DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING
N.B.K.R INSTITUTE OF SCIENCE AND TECHNOLOGY
(Autonomous)
(Approved by AICTE: Accredited by NBA: Affiliated to JNTUA, Ananthapuramu)
An ISO 9001-2000 Certified Institution
Vidyanagar- 524413, Tirupati District, Andhra Pradesh, India
(2019-2023)

TEAM
P. VARSHITHA - 19KB1A05C5 UNDER THE GUIDANCE OF
P. POORNIMA - 19KB1A05B9 Mr. K. Penchalaiah, B.Tech., M.Tech.,
P. SAI VARDHAN - 19KB1A05C0 Asst. Professor, Dept. of CSE
P. SAI -19KB1A05C6
Contents:  Abstract
 Introduction
 Existing system
 Literature Survey
 Proposed system
 Modules
 UML Diagrams
 System Architecture
 Requirements
 Snapshots
 Conclusion
 Future enhancements
 References
ABSTRACT:
Stock price movement is non-linear and complex. Several research works have been carried out
to predict stock prices. Traditional approaches such as Linear Regression and Support Vector
Regression were used but accuracy was not adequate. Researchers have tried to improve stock
price prediction using ARIMA. Due to very high variations in stock prices, deep learning techniques
are applied due to its proven accuracy in various analytics fields.
Artificial Neural Network was deployed to predict stock prices but as stock prices are time-series
based, recurrent neural network was applied to further improve prediction accuracy. In RNN,
there is limitation of not able to store high dependencies and also vanishing gradient descent
issue exists. Therefore, data scientists and analysts applied LSTM to predict stock
price movement. In this paper, LSTM is compared with SVR. Experiment analysis proves that LSTM
provides better accuracy as compared to SVR.
INTRODUCTION:
• Time-series prediction is a common technique widely used in
many real-world applications such as weather forecasting
and financial market prediction. It uses the continuous data
in a period of time to predict the result in the next time unit.
Many timeseries prediction algorithms have shown their
effectiveness in practice. The most common algorithms now
are based on Recurrent Neural Networks (RNN), as well as its
special type - Long-short Term Memory (LSTM) and Gated
Recurrent Unit (GRU). Stock market is a typical area that
presents time-series data and many researchers study on it
and proposed various models. In this project, LSTM model is
used to predict the stock price.
Existing System:

• The technical and fundamental or the time series analysis is used by the most of the
stockbrokers while making the stock predictions. The programming language is used
to predict the stock market using machine learning is Python.
• Machine Learning (ML) approach that will be trained from the available stocks data
and gain intelligence and then uses the acquired knowledge for an accurate
prediction a machine learning technique called Support Vector Machine (SVM)
and also an artificial neural network technique long short term memory (lstm) to
predict stock prices for the large and small capitalizations
Literature Survey:

The research work done by M. Mekayel Anik · M. Shamsul Arefin (B) Department of Computer Science and Engineering, Chittagong
University of Engineering and Technology, Chittagong, Bangladesh. A stock market is a loose network of economic transactions
between buyers and sellers based on stocks also known as shares. In stock markets, stocks represent the ownership claims on
businesses. 
These may include securities listed on a stock exchange as well as those only traded privately. A stock exchange is a place where
brokers can buy and/or sell stocks, bonds, and other securities. Stock market is a very vulnerable place for investment due to its
volatile nature. In the near past, we faced huge financial problems due to huge drop in price of shares in stock markets worldwide.
This phenomenon brought a heavy toll on the international as well as on our national financial structure. Many people lost their last
savings of money on the stock market. In 2010–2011 financial year, Bangladeshi stock market faced massive collapse [1].
This phenomenon can be brought under control especially by strict monitoring and instance stock market analysis. If we can analyse
stock market correctly in time, it can become a field of large profit and may become comparatively less vulnerable for the investors.
Stock market is all about prediction and rapid decision making about investment, which cannot be done without thorough analysis of
the market. If we can predict the stock market by analysing historical data properly, we can avoid the consequences of serious market
collapse and to be able to take necessary steps to make market immune to such situations.
Proposed System:

• In stock price prediction they have already implemented using long short
term memory (lstm) and support vactor regression (svr) methods
to predict future value of a stock.
• Now we are implementing future stock price by collecting data from
website and adding visualizing techniques.
Modules:
USER
• Login
• Gives Feedback about the restaurant
• Exists for the session
SYSTEM ADMIN
• Login
• Collection of reviews
• Pre-processing the data
• Analysis and returns the output.
MANAGER
• Gives raw data to the system admin
• Manages the restaurant
Activity  DIAGRAM:
SYSTEM ARCHITETURE:
REQUIREMENTS:

 HARDWARE:
RAM: 4 GB
 Storage: 500 GB 
• CPU: 2 GHz or faster 
• Architecture: 32-bit or 64-bit
SOFTWARE:
• Python 3.5 in Google Colab is used for data pre-processing, model training and prediction. 
•  Operating System: windows 7 and above or Linux based OS or MAC OS
SNAPSHOTS
dataset
Import dataset from website
Visualizing  price
MinMaxScale
r
Training
the dataset
LSTM
prediction
Conclusion:
• In this project, we are predicting closing stock price of any
given organization,
• We have applied datasets belongs to yahoo which gets
better accuracy
Future
• We want to extend this application for
Enhancements: predicting cryptocurrency trading.
•  • We want to add sentiment analysis for
better analysis.
References:

• Stock Price Prediction Using LSTM on Indian Share Market by Achyut Ghosh, Soumik
Bose1, Giridhar Maji, Narayan C. Debnath, Soumya Sen 
• S. Selvin, R. Vinayakumar, E. A. Gopalkrishnan, V. K. Menon and K. P. Soman, "Stock price
prediction using LSTM, RNN and CNN-sliding window model," in International Conference
on Advances in Computing, Communications and Informatics, 2017. 
• Murtaza Roondiwala, Harshal Patel, Shraddha Varma, “Predicting Stock Prices Using
LSTM” in Undergraduate Engineering Students, Department of Information Technology,
Mumbai University, 2015.