Scribd Logo
Upload

Welcome to Scribd!

  • 9 views

    Fake Reviews Detector Project (132,133)

    Uploaded by

    Mark
    fake reviews detection project using python

    Copyright:

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

    Fake Reviews Detector Project (132,133)

    Uploaded by

    Mark
    9 views3 pages
    fake reviews detection project using python

    Original Title

    Fake_Reviews_Detector_Project(132,133)

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    fake reviews detection project using python

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    9 views3 pages

    Fake Reviews Detector Project (132,133)

    Uploaded by

    Mark
    fake reviews detection project using python

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 3

    A D PATEL INSTITUTE OF TECHNOLOGY

    DEPARTMENT OF INFORMATION TECHNOLOGY


    SUBJECT NAME & COURSE CODE: ARTIFICIAL INTELLIGENCE (202044503)

    Fake Reviews Detector Project


    1. Introduction
    The Fake Reviews Detector project is designed to identify whether a given review is real or fake
    using machine learning techniques. This project utilizes natural language processing (NLP) to
    preprocess the text data and build a classification model using Logistic Regression.

    2. Dataset Description
    The dataset used for this project contains two columns: 'review' and 'label'. The 'review' column
    contains the text of the review, while the 'label' column indicates whether the review is real (0) or
    fake (1).

    3. Code Overview
    The code is structured into several sections: data preprocessing, feature extraction, model
    training, evaluation, and prediction.

    4. Code Snippet
    import pandas as pd
    import numpy as np
    import re
    import nltk
    from sklearn.model_selection import train_test_split
    from sklearn.feature_extraction.text import TfidfVectorizer
    from sklearn.linear_model import LogisticRegression
    from sklearn.metrics import accuracy_score, classification_report, confusion_matrix

    nltk.download('stopwords')
    from nltk.corpus import stopwords
    from nltk.stem.porter import PorterStemmer

    def preprocess_review(review):
    review = re.sub('[^a-zA-Z]', ' ', review)
    review = review.lower()
    review = review.split()
    ps = PorterStemmer()
    review = [ps.stem(word) for word in review if word not in set(stopwords.words('english'))]
    return ' '.join(review)

    # Load your dataset


    df = pd.read_csv('reviews.csv') # Ensure this path is correct

    1
    Enrollment Numbers : 12202080601132 , 12202080601133
    Names : Patel Vaibhavi , Rana Vairagi
    A D PATEL INSTITUTE OF TECHNOLOGY
    DEPARTMENT OF INFORMATION TECHNOLOGY
    SUBJECT NAME & COURSE CODE: ARTIFICIAL INTELLIGENCE (202044503)

    # Preprocess reviews
    df['processed_review'] = df['review'].apply(preprocess_review)

    # Feature extraction
    tfidf = TfidfVectorizer(max_features=5000)
    X = tfidf.fit_transform(df['processed_review']).toarray()
    y = df['label']

    # Split dataset
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

    # Train the model


    model = LogisticRegression()
    model.fit(X_train, y_train)

    # Predictions
    y_pred = model.predict(X_test)

    # Print evaluation metrics


    print("Accuracy:", accuracy_score(y_test, y_pred))
    print("Classification Report:\n", classification_report(y_test, y_pred))
    print("Confusion Matrix:\n", confusion_matrix(y_test, y_pred))

    # Predicting a sample review


    def predict_review(review_text):
    processed_review = preprocess_review(review_text)
    review_tfidf = tfidf.transform([processed_review]).toarray()
    return model.predict(review_tfidf)

    # Example usage for prediction


    review = "This product is absolutely amazing! I love it!"
    prediction = predict_review(review)
    print("Prediction (0 = Real, 1 = Fake):", prediction[0])

    5. Expected Outputs
    The expected outputs include:
    - Accuracy of the model.
    - A classification report detailing precision, recall, and F1-score.
    - A confusion matrix indicating the number of true and false predictions.
    - Predictions for sample reviews indicating whether they are real or fake.
    2
    Enrollment Numbers : 12202080601132 , 12202080601133
    Names : Patel Vaibhavi , Rana Vairagi
    A D PATEL INSTITUTE OF TECHNOLOGY
    DEPARTMENT OF INFORMATION TECHNOLOGY
    SUBJECT NAME & COURSE CODE: ARTIFICIAL INTELLIGENCE (202044503)

    6. Conclusion
    The Fake Reviews Detector project showcases the application of machine learning and natural
    language processing to tackle the problem of fake reviews. By using this model, businesses can
    better identify and mitigate the impact of deceptive reviews.

    3
    Enrollment Numbers : 12202080601132 , 12202080601133
    Names : Patel Vaibhavi , Rana Vairagi

    You might also like