Scribd Logo
Upload

Welcome to Scribd!

  • 12 views

    Sentiment Analysis of Restaurant Reviews-1

    Uploaded by

    SINIGI RAMYA SRI

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd

    Sentiment Analysis of Restaurant Reviews-1

    Uploaded by

    SINIGI RAMYA SRI
    12 views18 pages

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    12 views18 pages

    Sentiment Analysis of Restaurant Reviews-1

    Uploaded by

    SINIGI RAMYA SRI

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 18

    SENTIMENT

    ANALYSIS
    OF
    RESTAURAN
    T REVIEWS
    GUIDE
    PROF. KASUKURTHI VENKATA RAO
    HEAD OF DEPARTMENT(CSSE)

    TEAM
    • B. NANDHA KRISHNA SAI 320106410009
    • B. SRI NITISH 320106410010
    • B. VENKATA BALA NAGA SAI PREETHI 320106410011
    • D. YUVAREKHA 320106410012
    2
    TABLE OF
    CONTENTS
     INTRODUCTION
     ABSTRACT
     EXISTING SYSTEM
     DRAWBACKS
     PROPOSED SYSTEM
     RESULTS
     REFERENCES
    SENTIMENT ANALYSIS

    Sentiment analysis, also known as


    opinion mining, is the process of
    analyzing and categorizing opinions
    expressed in text data to determine
    the sentiment conveyed, whether
    positive and negative

    4
    INTRODUCTION
     Online review platforms have revolutionized
    consumer feedback for businesses, particularly
    in the restaurant industry.
     Sentiment analysis, a subfield of NLP, is crucial
    for understanding customer satisfaction and
    areas for improvement.
     The project aims to analyze restaurant reviews
    using machine learning and NLP to categorize
    sentiments as positive or negative.
     The research seeks to contribute to customer
    feedback analysis, aiding restaurant owners in
    data-driven decision-making for enhanced
    satisfaction and business performance.

    5
    ABSTRACT
     Sentiment analysis of restaurant reviews for
    actionable insights
     Utilizing advanced natural language processing
    (NLP) methodologies
     Examining sentiment: positive and negative
     Methodology involves preprocessing, feature
    extraction, and sentiment classification
     Empowering data-driven decision-making
     Involved in optimization of customer satisfaction
    and operational strategies

    6
    EXISTING SYSTEM
     Feedback analysis was labor-
    intensive, often relying on
    manual reading and
    TIME CONSUMING
    interpretation.
     Inefficient processes made it
     Processing feedback manually challenging to handle large
    resulted in delays in volumes of feedback
    identifying customer effectively.
    sentiments and issues
     Feedback collection was
    constrained by geographical
    MANUAL ANALYSIS
    proximity and accessibility

    7
    DRAWBACKS
     Limited Scalability: Manual analysis
    methods struggle to handle large
    volumes of data efficiently, limiting
    scalability as businesses grow.
     Human Error
     Time-Consuming
     Incomplete Insights: Manual analysis
    may overlook nuanced sentiments and
    trends present in customer feedback.
     Lack of Automation

    8
    PROPOSED
    SYSTEM
     Implementing automated sentiment analysis
    tools using Natural language processing (NLP)
    techniques.
     Leveraging machine learning algorithms for
    accurate classification.
     Streamlined Data Processing.
     Comprehensive Feature Extraction.
     Enabling real-time analysis.
     Designing a scalable architecture capable of
    handling large volumes.
     Providing actionable insights and
    recommendations to business performance.

    9
    Implementation
    Data Processing:
     Data is read from a CSV file using pandas (pd.read_csv).
     Text preprocessing is performed using regular
    expressions (re.sub), NLTK for tokenization, stopword
    removal, and stemming (nltk.corpus,
    nltk.stem.porter.PorterStemmer,
    nltk.corpus.stopwords).
    Machine Learning:
     CountVectorizer from sklearn is used to convert text
    data into numerical features.
     Naive Bayes (GaussianNB) is used for sentiment analysis
    classification.

    10
    Implementation
    GUI Development:
     GUI elements are created using tkinter (Tk(), Label(), Button(), Entry(), Checkbutton(), etc.).
    Functionality:
     The code includes functionalities like taking reviews from customers, sentiment analysis, owner verification,
    viewing and clearing data, and displaying results in a GUI.
     Initial data setup is done using init_data() function for inserting default values into the database.
    User Interface:
     The UI includes options for customers to submit reviews and for owners to verify and manage restaurant data.
     Different UI elements like labels, buttons, entry fields, checkboxes, and message boxes are used.
    Execution Flow:
     The main flow starts with the welcome page, where users choose between being a customer or an owner.
     Depending on the choice, appropriate actions and interfaces are presented.

    11
    RESULTS
     Achieved high Classification Accuracy.
     Uncovered valuable insights into customer
    sentiments across various aspects of dining
    experiences.
     Identified specific areas for improvement
    based on customer feedback.
     Demonstrated the potential impact of
    sentiment analysis on business performance
    through improved customer satisfaction.
     Empowered restaurant stakeholders with
    data-driven insights to make strategic
    adjustments.
     Identified potential avenues for future
    research.

    12
    Customer or Owner Selection

    13
    Customer Review Submission Form

    14
    Validating Owner

    15
    Customer Feedback Analysis by Owner

    16
    REFERENCES
    [1] R. Sarno and M. Fikri," A relative Study of Sentiment Analysis using SVM and SentiWordNet,"Indonesian Journal of
    Electrical Engineering and Computer Science ( lJEECS), vol. 13,no., 2019.

    [2] B. Rintyarna, R. Sarno, and C. Fatichah," Enhancing the performance of sentiment analysis task on product reviews by
    handling both original and global terrain," International Journal of Information and Decision lores, vol., 2018.

    [3] D. L. Gupta, A. K Malviya, and S. Singh," Performance analysis of classification tree learning algorithms," International
    Journal of Computer operations, vol. 55,no., 2012.

    [4] B. Agarwal, N. Mittal and P. Bansal," novelettish analysis environmental information," Computational intelligence and
    neuro wisdom, vol. 2015, p. 30, 2015.

    [5] K. Ilieska," customer satisfaction index-- as a base for strategic marketing operation," TEM Journal, vol. 2, no. 4, p. 327,
    2013.

    [6] Mikel Joaristi, Edoardo Serra, Francesca Spezzano “assessing the Impact of Social Media in Detecting the caffs Violating
    the Health morals” In 2016 IEEE/ ACM international Conference on Advances in Social Networks Analysis and Mining.
    17
    THANK YOU!
    FLORA@CONTOSO.COM

    HTTP://WWW.CONTOSO.COM/

    You might also like