demo.py GITHUB_RELEASE_GUIDE.md index.html RELEASE_NOTES.md .gitignore README.md

index.html

<!--
================================================================================
 * Sentiment Analysis Dataset - Demo Page
 * 
 * Project: Sentiment Analysis Dataset
 * Description: Text sentiment analysis dataset with labeled reviews, comments,
 *              and social media posts for sentiment classification models.
 * Category: Text Data
 * Difficulty: Intermediate
 * 
 * Author: Molla Samser (Founder)
 * Designer & Tester: Rima Khatun
 * Website: https://rskworld.in
 * Email: help@rskworld.in | support@rskworld.in
 * Phone: +91 93305 39277
 * 
 * © 2026 RSK World - Free Programming Resources & Source Code
 * All rights reserved.
================================================================================
-->
<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <meta name="description" content="Sentiment Analysis Dataset - Text sentiment analysis dataset with labeled reviews, comments, and social media posts for sentiment classification models.">
    <meta name="keywords" content="sentiment analysis, NLP, machine learning, dataset, text classification, RSK World">
    <meta name="author" content="Molla Samser - RSK World">
    <meta name="robots" content="index, follow">
    
    <!-- Open Graph Meta Tags -->
    <meta property="og:title" content="Sentiment Analysis Dataset - RSK World">
    <meta property="og:description" content="Text sentiment analysis dataset with labeled reviews, comments, and social media posts for sentiment classification models.">
    <meta property="og:image" content="./sentiment-analysis.png">
    <meta property="og:url" content="https://rskworld.in/sentiment-analysis/">
    <meta property="og:type" content="website">
    
    <title>Sentiment Analysis Dataset - RSK World</title>
    
    <!-- Font Awesome -->
    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.2/css/all.min.css">
    
    <!-- Google Fonts -->
    <link rel="preconnect" href="https://fonts.googleapis.com">
    <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
    <link href="https://fonts.googleapis.com/css2?family=Crimson+Pro:wght@400;600;700&family=DM+Sans:wght@400;500;600;700&display=swap" rel="stylesheet">
    
    <!-- Custom Styles -->
    <link rel="stylesheet" href="css/styles.css">
</head>
<body>
    <!-- Animated Background -->
    <div class="bg-animation">
        <div class="floating-shapes">
            <span></span><span></span><span></span><span></span><span></span>
            <span></span><span></span><span></span><span></span><span></span>
        </div>
    </div>

    <!-- Header -->
    <header class="header">
        <div class="container">
            <nav class="navbar">
                <a href="https://rskworld.in" class="logo">
                    <i class="fas fa-chart-line"></i>
                    <span>RSK World</span>
                </a>
                <div class="nav-links">
                    <a href="https://rskworld.in" class="nav-link">
                        <i class="fas fa-home"></i> Home
                    </a>
                    <a href="https://rskworld.in/contact.php" class="nav-link">
                        <i class="fas fa-envelope"></i> Contact
                    </a>
                    <a href="./sentiment-analysis.zip" class="btn-download" download>
                        <i class="fas fa-download"></i> Download Dataset
                    </a>
                </div>
                <button class="mobile-menu-btn" aria-label="Toggle menu">
                    <i class="fas fa-bars"></i>
                </button>
            </nav>
        </div>
    </header>

    <!-- Hero Section -->
    <section class="hero">
        <div class="container">
            <div class="hero-content">
                <div class="hero-badge">
                    <i class="fas fa-file-alt text-danger"></i>
                    <span>Text Data</span>
                </div>
                <h1 class="hero-title">
                    Sentiment Analysis
                    <span class="gradient-text">Dataset</span>
                </h1>
                <p class="hero-description">
                    Text sentiment analysis dataset with labeled reviews, comments, and social media posts 
                    for sentiment classification models. Perfect for NLP applications and machine learning projects.
                </p>
                <div class="hero-stats">
                    <div class="stat-item">
                        <i class="fas fa-database"></i>
                        <span class="stat-value">50,000+</span>
                        <span class="stat-label">Data Points</span>
                    </div>
                    <div class="stat-item">
                        <i class="fas fa-tags"></i>
                        <span class="stat-value">3</span>
                        <span class="stat-label">Sentiment Classes</span>
                    </div>
                    <div class="stat-item">
                        <i class="fas fa-layer-group"></i>
                        <span class="stat-value">5</span>
                        <span class="stat-label">File Formats</span>
                    </div>
                </div>
                <div class="hero-actions">
                    <a href="./sentiment-analysis.zip" class="btn btn-primary" download>
                        <i class="fas fa-download"></i>
                        Download Full Dataset
                    </a>
                    <a href="#explore" class="btn btn-secondary">
                        <i class="fas fa-eye"></i>
                        Explore Dataset
                    </a>
                </div>
            </div>
            <div class="hero-visual">
                <div class="sentiment-showcase">
                    <div class="sentiment-card positive">
                        <div class="sentiment-icon">
                            <i class="fas fa-smile"></i>
                        </div>
                        <div class="sentiment-info">
                            <span class="sentiment-label">Positive</span>
                            <span class="sentiment-count">18,500+</span>
                        </div>
                    </div>
                    <div class="sentiment-card neutral">
                        <div class="sentiment-icon">
                            <i class="fas fa-meh"></i>
                        </div>
                        <div class="sentiment-info">
                            <span class="sentiment-label">Neutral</span>
                            <span class="sentiment-count">15,200+</span>
                        </div>
                    </div>
                    <div class="sentiment-card negative">
                        <div class="sentiment-icon">
                            <i class="fas fa-frown"></i>
                        </div>
                        <div class="sentiment-info">
                            <span class="sentiment-label">Negative</span>
                            <span class="sentiment-count">16,300+</span>
                        </div>
                    </div>
                </div>
            </div>
        </div>
    </section>

    <!-- Features Section -->
    <section class="features" id="features">
        <div class="container">
            <div class="section-header">
                <span class="section-badge">Features</span>
                <h2 class="section-title">What's Included</h2>
                <p class="section-description">
                    Everything you need for sentiment analysis and NLP model training
                </p>
            </div>
            <div class="features-grid">
                <div class="feature-card">
                    <div class="feature-icon">
                        <i class="fas fa-tags"></i>
                    </div>
                    <h3>Labeled Sentiment Data</h3>
                    <p>Pre-labeled text data with positive, negative, and neutral sentiment classifications</p>
                </div>
                <div class="feature-card">
                    <div class="feature-icon">
                        <i class="fas fa-layer-group"></i>
                    </div>
                    <h3>Multiple Text Sources</h3>
                    <p>Diverse collection from product reviews, social media posts, and user comments</p>
                </div>
                <div class="feature-card">
                    <div class="feature-icon">
                        <i class="fas fa-random"></i>
                    </div>
                    <h3>Training & Test Sets</h3>
                    <p>Pre-split datasets ready for machine learning model training and evaluation</p>
                </div>
                <div class="feature-card">
                    <div class="feature-icon">
                        <i class="fas fa-broom"></i>
                    </div>
                    <h3>Preprocessed Versions</h3>
                    <p>Cleaned and tokenized versions ready for immediate use in NLP pipelines</p>
                </div>
                <div class="feature-card">
                    <div class="feature-icon">
                        <i class="fas fa-robot"></i>
                    </div>
                    <h3>Ready for NLP Models</h3>
                    <p>Compatible with NLTK, spaCy, and popular deep learning frameworks</p>
                </div>
                <div class="feature-card">
                    <div class="feature-icon">
                        <i class="fas fa-file-code"></i>
                    </div>
                    <h3>Multiple Formats</h3>
                    <p>Available in CSV, JSON, and TXT formats for maximum flexibility</p>
                </div>
            </div>
        </div>
    </section>

    <!-- Dataset Explorer Section -->
    <section class="explorer" id="explore">
        <div class="container">
            <div class="section-header">
                <span class="section-badge">Explore</span>
                <h2 class="section-title">Dataset Preview</h2>
                <p class="section-description">
                    Browse through sample data from our sentiment analysis collection
                </p>
            </div>
            
            <!-- Filter Tabs -->
            <div class="filter-tabs">
                <button class="filter-tab active" data-filter="all">
                    <i class="fas fa-globe"></i> All Samples
                </button>
                <button class="filter-tab" data-filter="positive">
                    <i class="fas fa-smile"></i> Positive
                </button>
                <button class="filter-tab" data-filter="neutral">
                    <i class="fas fa-meh"></i> Neutral
                </button>
                <button class="filter-tab" data-filter="negative">
                    <i class="fas fa-frown"></i> Negative
                </button>
            </div>
            
            <!-- Sample Data Grid -->
            <div class="samples-grid" id="samplesGrid">
                <!-- Samples will be loaded via JavaScript -->
            </div>
            
            <div class="explorer-actions">
                <button class="btn btn-secondary" id="loadMore">
                    <i class="fas fa-plus"></i> Load More Samples
                </button>
            </div>
        </div>
    </section>

    <!-- Advanced Features Section -->
    <section class="advanced-features" id="advanced">
        <div class="container">
            <div class="section-header">
                <span class="section-badge">🚀 Advanced</span>
                <h2 class="section-title">Advanced Features</h2>
                <p class="section-description">
                    Powerful Python scripts for data generation, analysis, and model training
                </p>
            </div>
            <div class="advanced-grid">
                <div class="advanced-card">
                    <div class="advanced-icon">
                        <i class="fas fa-magic"></i>
                    </div>
                    <div class="advanced-content">
                        <h3>Data Generator</h3>
                        <p>Generate unlimited synthetic sentiment data with customizable parameters</p>
                        <code>python generate_data.py --samples 10000</code>
                    </div>
                </div>
                <div class="advanced-card">
                    <div class="advanced-icon">
                        <i class="fas fa-broom"></i>
                    </div>
                    <div class="advanced-content">
                        <h3>Smart Preprocessor</h3>
                        <p>Clean, tokenize, and prepare text with lemmatization & stemming</p>
                        <code>python preprocess_data.py --lemmatize</code>
                    </div>
                </div>
                <div class="advanced-card">
                    <div class="advanced-icon">
                        <i class="fas fa-microscope"></i>
                    </div>
                    <div class="advanced-content">
                        <h3>Sentiment Analyzer</h3>
                        <p>Multi-method analysis using Lexicon, VADER, and TextBlob</p>
                        <code>python analyze_sentiment.py --interactive</code>
                    </div>
                </div>
                <div class="advanced-card">
                    <div class="advanced-icon">
                        <i class="fas fa-chart-pie"></i>
                    </div>
                    <div class="advanced-content">
                        <h3>Data Visualizer</h3>
                        <p>Generate charts, word clouds, and HTML reports automatically</p>
                        <code>python visualize_data.py --html-report</code>
                    </div>
                </div>
                <div class="advanced-card">
                    <div class="advanced-icon">
                        <i class="fas fa-brain"></i>
                    </div>
                    <div class="advanced-content">
                        <h3>Model Trainer</h3>
                        <p>Train ML models - Naive Bayes, SVM, Logistic Regression, Random Forest</p>
                        <code>python train_model.py --all-models --save</code>
                    </div>
                </div>
                <div class="advanced-card">
                    <div class="advanced-icon">
                        <i class="fas fa-sync-alt"></i>
                    </div>
                    <div class="advanced-content">
                        <h3>Cross-Validation</h3>
                        <p>Built-in cross-validation for reliable model evaluation</p>
                        <code>python train_model.py --cross-validate 5</code>
                    </div>
                </div>
            </div>
        </div>
    </section>

    <!-- Step by Step Guide Section -->
    <section class="guide" id="guide">
        <div class="container">
            <div class="section-header">
                <span class="section-badge">📖 Tutorial</span>
                <h2 class="section-title">Step-by-Step Guide</h2>
                <p class="section-description">
                    Follow these steps to get started with the dataset and Python scripts
                </p>
            </div>
            <div class="guide-timeline">
                <div class="guide-step">
                    <div class="step-number">1</div>
                    <div class="step-content">
                        <h3>Download & Extract</h3>
                        <p>Download the dataset ZIP file and extract it to your project folder</p>
                        <div class="step-code">
                            <span class="code-label">Terminal</span>
                            <pre><code>unzip sentiment-analysis.zip
cd sentiment-analysis</code></pre>
                        </div>
                    </div>
                </div>
                <div class="guide-step">
                    <div class="step-number">2</div>
                    <div class="step-content">
                        <h3>Install Dependencies</h3>
                        <p>Install required Python packages for full functionality</p>
                        <div class="step-code">
                            <span class="code-label">Terminal</span>
                            <pre><code>cd scripts
pip install -r requirements.txt

# Download NLTK data
python -c "import nltk; nltk.download('punkt'); nltk.download('stopwords'); nltk.download('wordnet')"</code></pre>
                        </div>
                    </div>
                </div>
                <div class="guide-step">
                    <div class="step-number">3</div>
                    <div class="step-content">
                        <h3>Generate Custom Data</h3>
                        <p>Create your own dataset with desired size and parameters</p>
                        <div class="step-code">
                            <span class="code-label">Terminal</span>
                            <pre><code># Generate 5000 balanced samples
python generate_data.py --samples 5000 --balanced

# Generate with train/test split (80/20)
python generate_data.py --samples 10000 --split 0.8 --all-formats</code></pre>
                        </div>
                    </div>
                </div>
                <div class="guide-step">
                    <div class="step-number">4</div>
                    <div class="step-content">
                        <h3>Preprocess Data</h3>
                        <p>Clean and prepare text data for NLP models</p>
                        <div class="step-code">
                            <span class="code-label">Terminal</span>
                            <pre><code># Basic preprocessing
python preprocess_data.py --input ../data/sentiment_data.csv

# Advanced: with lemmatization and stopword removal
python preprocess_data.py --input ../data/sentiment_data.csv \
    --lemmatize --remove-stopwords --build-vocab</code></pre>
                        </div>
                    </div>
                </div>
                <div class="guide-step">
                    <div class="step-number">5</div>
                    <div class="step-content">
                        <h3>Analyze Sentiment</h3>
                        <p>Test sentiment analysis on your own text or evaluate datasets</p>
                        <div class="step-code">
                            <span class="code-label">Terminal</span>
                            <pre><code># Interactive mode - type any text
python analyze_sentiment.py --interactive

# Evaluate accuracy on dataset
python analyze_sentiment.py --file ../data/test_data.csv --evaluate</code></pre>
                        </div>
                    </div>
                </div>
                <div class="guide-step">
                    <div class="step-number">6</div>
                    <div class="step-content">
                        <h3>Train ML Models</h3>
                        <p>Train and compare multiple machine learning models</p>
                        <div class="step-code">
                            <span class="code-label">Terminal</span>
                            <pre><code># Train all models and save the best one
python train_model.py --input ../data/sentiment_data.csv \
    --all-models --save --output ../models/

# Train specific model with cross-validation
python train_model.py --input ../data/sentiment_data.csv \
    --model svm --cross-validate 5</code></pre>
                        </div>
                    </div>
                </div>
                <div class="guide-step">
                    <div class="step-number">7</div>
                    <div class="step-content">
                        <h3>Visualize Results</h3>
                        <p>Generate charts, word clouds, and comprehensive reports</p>
                        <div class="step-code">
                            <span class="code-label">Terminal</span>
                            <pre><code># Generate all visualizations with HTML report
python visualize_data.py --input ../data/sentiment_data.csv \
    --all-charts --html-report --output ../charts/</code></pre>
                        </div>
                    </div>
                </div>
            </div>
        </div>
    </section>

    <!-- Unique Features Section -->
    <section class="unique-features" id="unique">
        <div class="container">
            <div class="section-header">
                <span class="section-badge">⭐ Unique</span>
                <h2 class="section-title">What Makes Us Different</h2>
                <p class="section-description">
                    Features you won't find in other sentiment analysis datasets
                </p>
            </div>
            <div class="unique-grid">
                <div class="unique-card featured">
                    <div class="unique-badge">Most Popular</div>
                    <div class="unique-icon">
                        <i class="fas fa-infinity"></i>
                    </div>
                    <h3>Unlimited Data Generation</h3>
                    <p>Generate 1,000 to 1,000,000+ samples with a single command. No limits!</p>
                    <ul class="unique-list">
                        <li><i class="fas fa-check"></i> Customizable sample count</li>
                        <li><i class="fas fa-check"></i> Balanced or custom distribution</li>
                        <li><i class="fas fa-check"></i> Multiple output formats</li>
                    </ul>
                </div>
                <div class="unique-card">
                    <div class="unique-icon">
                        <i class="fas fa-layer-group"></i>
                    </div>
                    <h3>Ensemble Analysis</h3>
                    <p>Combine 3 different sentiment analysis methods for maximum accuracy</p>
                    <ul class="unique-list">
                        <li><i class="fas fa-check"></i> Lexicon-based analyzer</li>
                        <li><i class="fas fa-check"></i> VADER sentiment</li>
                        <li><i class="fas fa-check"></i> TextBlob integration</li>
                    </ul>
                </div>
                <div class="unique-card">
                    <div class="unique-icon">
                        <i class="fas fa-robot"></i>
                    </div>
                    <h3>4 ML Algorithms</h3>
                    <p>Train and compare multiple machine learning models automatically</p>
                    <ul class="unique-list">
                        <li><i class="fas fa-check"></i> Naive Bayes</li>
                        <li><i class="fas fa-check"></i> Support Vector Machine</li>
                        <li><i class="fas fa-check"></i> Logistic Regression</li>
                        <li><i class="fas fa-check"></i> Random Forest</li>
                    </ul>
                </div>
                <div class="unique-card">
                    <div class="unique-icon">
                        <i class="fas fa-terminal"></i>
                    </div>
                    <h3>Interactive Mode</h3>
                    <p>Real-time sentiment analysis with instant feedback</p>
                    <ul class="unique-list">
                        <li><i class="fas fa-check"></i> Type any text to analyze</li>
                        <li><i class="fas fa-check"></i> See detailed scores</li>
                        <li><i class="fas fa-check"></i> Compare methods live</li>
                    </ul>
                </div>
                <div class="unique-card">
                    <div class="unique-icon">
                        <i class="fas fa-file-export"></i>
                    </div>
                    <h3>Auto Reports</h3>
                    <p>Generate beautiful HTML reports with one command</p>
                    <ul class="unique-list">
                        <li><i class="fas fa-check"></i> Sentiment distribution charts</li>
                        <li><i class="fas fa-check"></i> Word frequency analysis</li>
                        <li><i class="fas fa-check"></i> Word cloud generation</li>
                    </ul>
                </div>
                <div class="unique-card">
                    <div class="unique-icon">
                        <i class="fas fa-save"></i>
                    </div>
                    <h3>Model Persistence</h3>
                    <p>Save trained models and load them anytime</p>
                    <ul class="unique-list">
                        <li><i class="fas fa-check"></i> Save best model automatically</li>
                        <li><i class="fas fa-check"></i> Load for predictions</li>
                        <li><i class="fas fa-check"></i> Production ready</li>
                    </ul>
                </div>
            </div>
        </div>
    </section>

    <!-- Python Scripts Section -->
    <section class="scripts" id="scripts">
        <div class="container">
            <div class="section-header">
                <span class="section-badge">🐍 Python</span>
                <h2 class="section-title">Included Scripts</h2>
                <p class="section-description">
                    5 powerful Python scripts for complete sentiment analysis workflow
                </p>
            </div>
            <div class="scripts-grid">
                <div class="script-card">
                    <div class="script-header">
                        <div class="script-icon">
                            <i class="fas fa-database"></i>
                        </div>
                        <h3>generate_data.py</h3>
                    </div>
                    <p class="script-desc">Generate synthetic sentiment analysis data</p>
                    <div class="script-features">
                        <span><i class="fas fa-check-circle"></i> Custom sample count</span>
                        <span><i class="fas fa-check-circle"></i> Balanced distribution</span>
                        <span><i class="fas fa-check-circle"></i> Train/test split</span>
                        <span><i class="fas fa-check-circle"></i> Multiple formats</span>
                    </div>
                    <div class="script-usage">
                        <span class="usage-label">Quick Start:</span>
                        <code>python generate_data.py -n 5000 -b</code>
                    </div>
                </div>
                <div class="script-card">
                    <div class="script-header">
                        <div class="script-icon">
                            <i class="fas fa-filter"></i>
                        </div>
                        <h3>preprocess_data.py</h3>
                    </div>
                    <p class="script-desc">Clean and prepare text for NLP models</p>
                    <div class="script-features">
                        <span><i class="fas fa-check-circle"></i> Tokenization</span>
                        <span><i class="fas fa-check-circle"></i> Lemmatization</span>
                        <span><i class="fas fa-check-circle"></i> Stopword removal</span>
                        <span><i class="fas fa-check-circle"></i> Vocabulary builder</span>
                    </div>
                    <div class="script-usage">
                        <span class="usage-label">Quick Start:</span>
                        <code>python preprocess_data.py -i data.csv</code>
                    </div>
                </div>
                <div class="script-card">
                    <div class="script-header">
                        <div class="script-icon">
                            <i class="fas fa-search"></i>
                        </div>
                        <h3>analyze_sentiment.py</h3>
                    </div>
                    <p class="script-desc">Analyze sentiment with multiple methods</p>
                    <div class="script-features">
                        <span><i class="fas fa-check-circle"></i> Lexicon analyzer</span>
                        <span><i class="fas fa-check-circle"></i> VADER integration</span>
                        <span><i class="fas fa-check-circle"></i> TextBlob support</span>
                        <span><i class="fas fa-check-circle"></i> Interactive mode</span>
                    </div>
                    <div class="script-usage">
                        <span class="usage-label">Quick Start:</span>
                        <code>python analyze_sentiment.py -i</code>
                    </div>
                </div>
                <div class="script-card">
                    <div class="script-header">
                        <div class="script-icon">
                            <i class="fas fa-chart-bar"></i>
                        </div>
                        <h3>visualize_data.py</h3>
                    </div>
                    <p class="script-desc">Generate charts and visual reports</p>
                    <div class="script-features">
                        <span><i class="fas fa-check-circle"></i> Distribution charts</span>
                        <span><i class="fas fa-check-circle"></i> Word clouds</span>
                        <span><i class="fas fa-check-circle"></i> Histograms</span>
                        <span><i class="fas fa-check-circle"></i> HTML reports</span>
                    </div>
                    <div class="script-usage">
                        <span class="usage-label">Quick Start:</span>
                        <code>python visualize_data.py -i data.csv -r</code>
                    </div>
                </div>
                <div class="script-card">
                    <div class="script-header">
                        <div class="script-icon">
                            <i class="fas fa-graduation-cap"></i>
                        </div>
                        <h3>train_model.py</h3>
                    </div>
                    <p class="script-desc">Train and evaluate ML models</p>
                    <div class="script-features">
                        <span><i class="fas fa-check-circle"></i> 4 ML algorithms</span>
                        <span><i class="fas fa-check-circle"></i> Cross-validation</span>
                        <span><i class="fas fa-check-circle"></i> Model saving</span>
                        <span><i class="fas fa-check-circle"></i> Metrics report</span>
                    </div>
                    <div class="script-usage">
                        <span class="usage-label">Quick Start:</span>
                        <code>python train_model.py -i data.csv -a</code>
                    </div>
                </div>
            </div>
        </div>
    </section>

    <!-- Technologies Section -->
    <section class="technologies" id="tech">
        <div class="container">
            <div class="section-header">
                <span class="section-badge">Technologies</span>
                <h2 class="section-title">Compatible With</h2>
                <p class="section-description">
                    Designed to work seamlessly with popular NLP tools and frameworks
                </p>
            </div>
            <div class="tech-grid">
                <div class="tech-card">
                    <div class="tech-icon csv">
                        <i class="fas fa-file-csv"></i>
                    </div>
                    <span>CSV</span>
                </div>
                <div class="tech-card">
                    <div class="tech-icon txt">
                        <i class="fas fa-file-alt"></i>
                    </div>
                    <span>TXT</span>
                </div>
                <div class="tech-card">
                    <div class="tech-icon json">
                        <i class="fas fa-file-code"></i>
                    </div>
                    <span>JSON</span>
                </div>
                <div class="tech-card">
                    <div class="tech-icon nltk">
                        <i class="fas fa-language"></i>
                    </div>
                    <span>NLTK</span>
                </div>
                <div class="tech-card">
                    <div class="tech-icon spacy">
                        <i class="fas fa-cogs"></i>
                    </div>
                    <span>spaCy</span>
                </div>
            </div>
        </div>
    </section>

    <!-- Dataset Structure Section -->
    <section class="structure" id="structure">
        <div class="container">
            <div class="section-header">
                <span class="section-badge">Structure</span>
                <h2 class="section-title">Dataset Organization</h2>
                <p class="section-description">
                    Well-organized file structure for easy navigation and integration
                </p>
            </div>
            <div class="structure-content">
                <div class="file-tree">
                    <div class="tree-header">
                        <i class="fas fa-folder-open"></i>
                        <span>sentiment-analysis/</span>
                    </div>
                    <ul class="tree-list">
                        <li class="tree-item">
                            <i class="fas fa-folder"></i>
                            <span>data/</span>
                            <ul class="tree-sublist">
                                <li><i class="fas fa-file-csv"></i> sentiment_data.csv</li>
                                <li><i class="fas fa-file-code"></i> sentiment_data.json</li>
                                <li><i class="fas fa-file-alt"></i> sentiment_data.txt</li>
                                <li><i class="fas fa-file-csv"></i> train_data.csv</li>
                                <li><i class="fas fa-file-csv"></i> test_data.csv</li>
                            </ul>
                        </li>
                        <li class="tree-item">
                            <i class="fas fa-folder"></i>
                            <span>preprocessed/</span>
                            <ul class="tree-sublist">
                                <li><i class="fas fa-file-csv"></i> cleaned_data.csv</li>
                                <li><i class="fas fa-file-code"></i> tokenized_data.json</li>
                            </ul>
                        </li>
                        <li class="tree-item">
                            <i class="fas fa-folder"></i>
                            <span class="highlight-folder">scripts/</span>
                            <ul class="tree-sublist">
                                <li><i class="fab fa-python"></i> generate_data.py</li>
                                <li><i class="fab fa-python"></i> preprocess_data.py</li>
                                <li><i class="fab fa-python"></i> analyze_sentiment.py</li>
                                <li><i class="fab fa-python"></i> visualize_data.py</li>
                                <li><i class="fab fa-python"></i> train_model.py</li>
                                <li><i class="fas fa-file-alt"></i> requirements.txt</li>
                            </ul>
                        </li>
                        <li class="tree-item">
                            <i class="fas fa-file-alt"></i>
                            <span>README.md</span>
                        </li>
                        <li class="tree-item">
                            <i class="fas fa-file"></i>
                            <span>LICENSE</span>
                        </li>
                    </ul>
                </div>
                <div class="structure-info">
                    <h3>File Descriptions</h3>
                    <div class="info-item">
                        <strong>sentiment_data.csv/json/txt</strong>
                        <p>Main dataset containing all labeled sentiment data</p>
                    </div>
                    <div class="info-item">
                        <strong>train_data.csv</strong>
                        <p>80% of data for training machine learning models</p>
                    </div>
                    <div class="info-item">
                        <strong>test_data.csv</strong>
                        <p>20% of data for testing and validation</p>
                    </div>
                    <div class="info-item">
                        <strong>cleaned_data.csv</strong>
                        <p>Preprocessed data with removed noise and special characters</p>
                    </div>
                    <div class="info-item">
                        <strong>tokenized_data.json</strong>
                        <p>Text data tokenized and ready for NLP models</p>
                    </div>
                    <div class="info-item highlight">
                        <strong>scripts/*.py</strong>
                        <p>Python scripts for data generation, preprocessing, analysis, visualization, and model training</p>
                    </div>
                </div>
            </div>
        </div>
    </section>

    <!-- Statistics Section -->
    <section class="statistics" id="stats">
        <div class="container">
            <div class="section-header">
                <span class="section-badge">Statistics</span>
                <h2 class="section-title">Dataset Insights</h2>
            </div>
            <div class="stats-grid">
                <div class="stats-card">
                    <div class="stats-chart">
                        <canvas id="sentimentChart"></canvas>
                    </div>
                    <h3>Sentiment Distribution</h3>
                </div>
                <div class="stats-card">
                    <div class="stats-chart">
                        <canvas id="sourceChart"></canvas>
                    </div>
                    <h3>Data Sources</h3>
                </div>
                <div class="stats-card metrics">
                    <h3>Key Metrics</h3>
                    <div class="metric-list">
                        <div class="metric-item">
                            <span class="metric-label">Total Samples</span>
                            <span class="metric-value" data-count="50000">0</span>
                        </div>
                        <div class="metric-item">
                            <span class="metric-label">Avg. Text Length</span>
                            <span class="metric-value" data-count="142">0</span>
                            <span class="metric-unit">chars</span>
                        </div>
                        <div class="metric-item">
                            <span class="metric-label">Vocabulary Size</span>
                            <span class="metric-value" data-count="28500">0</span>
                        </div>
                        <div class="metric-item">
                            <span class="metric-label">Languages</span>
                            <span class="metric-value">English</span>
                        </div>
                    </div>
                </div>
            </div>
        </div>
    </section>

    <!-- Use Cases Section -->
    <section class="use-cases" id="usecases">
        <div class="container">
            <div class="section-header">
                <span class="section-badge">Applications</span>
                <h2 class="section-title">Use Cases</h2>
                <p class="section-description">
                    Discover what you can build with this dataset
                </p>
            </div>
            <div class="cases-grid">
                <div class="case-card">
                    <div class="case-icon">
                        <i class="fas fa-brain"></i>
                    </div>
                    <h3>Sentiment Classification</h3>
                    <p>Train models to automatically classify text sentiment as positive, negative, or neutral</p>
                </div>
                <div class="case-card">
                    <div class="case-icon">
                        <i class="fas fa-chart-bar"></i>
                    </div>
                    <h3>Brand Monitoring</h3>
                    <p>Analyze customer feedback and social media mentions for brand perception insights</p>
                </div>
                <div class="case-card">
                    <div class="case-icon">
                        <i class="fas fa-comments"></i>
                    </div>
                    <h3>Customer Reviews Analysis</h3>
                    <p>Automatically process and categorize product reviews at scale</p>
                </div>
                <div class="case-card">
                    <div class="case-icon">
                        <i class="fas fa-graduation-cap"></i>
                    </div>
                    <h3>NLP Education</h3>
                    <p>Learn and practice natural language processing techniques</p>
                </div>
            </div>
        </div>
    </section>

    <!-- Download Section -->
    <section class="download" id="download">
        <div class="container">
            <div class="download-card">
                <div class="download-content">
                    <h2>Ready to Get Started?</h2>
                    <p>Download the complete sentiment analysis dataset and start building your NLP models today!</p>
                    <div class="download-meta">
                        <span><i class="fas fa-weight-hanging"></i> ~5 MB</span>
                        <span><i class="fas fa-file-archive"></i> ZIP Format</span>
                        <span><i class="fas fa-shield-alt"></i> No Registration</span>
                    </div>
                </div>
                <div class="download-action">
                    <a href="./sentiment-analysis.zip" class="btn btn-primary btn-large" download>
                        <i class="fas fa-download"></i>
                        Download Dataset
                    </a>
                    <span class="download-note">Free for educational purposes</span>
                </div>
            </div>
        </div>
    </section>

    <!-- Footer -->
    <footer class="footer">
        <div class="container">
            <div class="footer-content">
                <div class="footer-brand">
                    <a href="https://rskworld.in" class="footer-logo">
                        <i class="fas fa-chart-line"></i>
                        <span>RSK World</span>
                    </a>
                    <p>Your one-stop destination for free programming resources, source code, and development tools.</p>
                    <div class="footer-social">
                        <a href="#" aria-label="Facebook"><i class="fab fa-facebook-f"></i></a>
                        <a href="#" aria-label="Twitter"><i class="fab fa-twitter"></i></a>
                        <a href="#" aria-label="Instagram"><i class="fab fa-instagram"></i></a>
                        <a href="#" aria-label="LinkedIn"><i class="fab fa-linkedin-in"></i></a>
                        <a href="#" aria-label="YouTube"><i class="fab fa-youtube"></i></a>
                    </div>
                </div>
                <div class="footer-links">
                    <div class="footer-column">
                        <h4>Quick Links</h4>
                        <ul>
                            <li><a href="https://rskworld.in">Home</a></li>
                            <li><a href="https://rskworld.in/about.php">About</a></li>
                            <li><a href="https://rskworld.in/contact.php">Contact</a></li>
                        </ul>
                    </div>
                    <div class="footer-column">
                        <h4>Resources</h4>
                        <ul>
                            <li><a href="#">Data Science</a></li>
                            <li><a href="#">Web Development</a></li>
                            <li><a href="#">AI Development</a></li>
                        </ul>
                    </div>
                    <div class="footer-column">
                        <h4>Contact Info</h4>
                        <ul>
                            <li><i class="fas fa-envelope"></i> help@rskworld.in</li>
                            <li><i class="fas fa-phone"></i> +91 93305 39277</li>
                            <li><i class="fas fa-globe"></i> rskworld.in</li>
                        </ul>
                    </div>
                </div>
            </div>
            <div class="footer-bottom">
                <p>&copy; 2026 RSK World. Founded by <strong>Molla Samser</strong>. Designed by <strong>Rima Khatun</strong>.</p>
                <p>Content used for educational purposes only.</p>
            </div>
        </div>
    </footer>

    <!-- Back to Top Button -->
    <button class="back-to-top" id="backToTop" aria-label="Back to top">
        <i class="fas fa-arrow-up"></i>
    </button>

    <!-- Chart.js -->
    <script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
    
    <!-- Custom Scripts -->
    <script src="js/script.js"></script>
</body>
</html>

965 lines•45.5 KB

markup

RELEASE_NOTES.md

Raw Download

RELEASE_NOTES.md

# 🎉 Sentiment Analysis Dataset v1.0.0

**Release Date:** December 26, 2026
**Author:** Molla Samser (Founder) - RSK World
**Website:** [https://rskworld.in](https://rskworld.in)

---

## 📦 What's Included

### 📊 Dataset Files
| File | Description | Format |
|------|-------------|--------|
| `data/sentiment_data.csv` | Main dataset with all samples | CSV |
| `data/sentiment_data.json` | Main dataset with metadata | JSON |
| `data/sentiment_data.txt` | Plain text format | TXT |
| `data/train_data.csv` | Training set (80%) | CSV |
| `data/test_data.csv` | Test set (20%) | CSV |

### 🔧 Preprocessed Data
| File | Description |
|------|-------------|
| `preprocessed/cleaned_data.csv` | Cleaned and normalized text |
| `preprocessed/tokenized_data.json` | Tokenized data for NLP models |

### 🐍 Python Scripts
| Script | Description |
|--------|-------------|
| `generate_data.py` | Generate unlimited synthetic sentiment data |
| `preprocess_data.py` | Clean, tokenize, and prepare text |
| `analyze_sentiment.py` | Multi-method sentiment analysis |
| `visualize_data.py` | Generate charts and HTML reports |
| `train_model.py` | Train ML models (4 algorithms) |

---

## ✨ Key Features

### 🚀 Advanced Capabilities
- ✅ **Unlimited Data Generation** - Generate 1,000 to 1,000,000+ samples
- ✅ **4 ML Algorithms** - Naive Bayes, SVM, Logistic Regression, Random Forest
- ✅ **Ensemble Analysis** - Combine Lexicon, VADER, and TextBlob methods
- ✅ **Interactive Mode** - Real-time sentiment analysis
- ✅ **Auto Reports** - Generate HTML visualizations automatically
- ✅ **Model Persistence** - Save and load trained models

### 📈 Dataset Statistics
- **Total Samples:** 50+ (expandable with generator)
- **Sentiment Classes:** 3 (Positive, Neutral, Negative)
- **Text Sources:** Product Reviews, Social Media, Customer Feedback
- **Languages:** English

---

## 🛠️ Quick Start

```bash
# Clone the repository
git clone https://github.com/rskworld/sentiment-analysis.git
cd sentiment-analysis

# Install dependencies
cd scripts
pip install -r requirements.txt

# Generate 5000 samples
python generate_data.py --samples 5000 --balanced

# Train all models
python train_model.py --input ../data/sentiment_data.csv --all-models --save

# Interactive sentiment analysis
python analyze_sentiment.py --interactive
```

---

## 📸 Demo Page

Visit the interactive demo page to explore the dataset:
- Filter by sentiment (Positive/Neutral/Negative)
- View dataset statistics
- Step-by-step usage guide
- Python scripts documentation

---

## 🙏 Credits

| Role | Name |
|------|------|
| **Author/Founder** | Molla Samser |
| **Designer & Tester** | Rima Khatun |
| **Website** | [rskworld.in](https://rskworld.in) |
| **Email** | help@rskworld.in |
| **Phone** | +91 93305 39277 |

---

## 📄 License

This dataset is provided for **educational purposes only**.

---

## 🔗 Links

- 🌐 **Website:** [https://rskworld.in](https://rskworld.in)
- 📧 **Email:** help@rskworld.in
- 📞 **Phone:** +91 93305 39277

---


© 2026 RSK World - Free Programming Resources & Source Code

README.md

Raw Download

README.md

# 📊 Sentiment Analysis Dataset

[![RSK World](https://img.shields.io/badge/RSK-World-dc3545)](https://rskworld.in)
[![Category](https://img.shields.io/badge/Category-Text%20Data-blue)](https://rskworld.in)
[![Difficulty](https://img.shields.io/badge/Difficulty-Intermediate-yellow)](https://rskworld.in)
[![Python](https://img.shields.io/badge/Python-3.8%2B-green)](https://python.org)
[![License](https://img.shields.io/badge/License-Educational-green)](https://rskworld.in)

Text sentiment analysis dataset with labeled reviews, comments, and social media posts for sentiment classification models. Includes **Python scripts for data generation, preprocessing, analysis, visualization, and model training**.

## 🌟 Features

- ✅ **Labeled Sentiment Data** - Pre-labeled text with positive, negative, and neutral classifications
- ✅ **Multiple Text Sources** - Diverse collection from product reviews, social media, and comments
- ✅ **Training & Test Sets** - Pre-split datasets ready for ML model development
- ✅ **Preprocessed Versions** - Cleaned and tokenized data ready for NLP pipelines
- ✅ **Ready for NLP Models** - Compatible with NLTK, spaCy, and popular frameworks
- ✅ **Python Scripts** - Generate unlimited data, train models, visualize results
- ✅ **Interactive Demo** - Beautiful web interface to explore the dataset

## 📁 Project Structure

```
sentiment-analysis/
├── 📂 data/
│ ├── sentiment_data.csv # Main dataset (CSV)
│ ├── sentiment_data.json # Main dataset (JSON)
│ ├── sentiment_data.txt # Main dataset (TXT)
│ ├── train_data.csv # Training set (80%)
│ └── test_data.csv # Test set (20%)
├── 📂 preprocessed/
│ ├── cleaned_data.csv # Cleaned/normalized text
│ └── tokenized_data.json # Tokenized data for NLP
├── 📂 scripts/ # 🆕 Python Scripts
│ ├── generate_data.py # Generate unlimited synthetic data
│ ├── preprocess_data.py # Preprocess and clean text
│ ├── analyze_sentiment.py # Analyze sentiment with multiple methods
│ ├── visualize_data.py # Generate charts and visualizations
│ ├── train_model.py # Train ML models
│ └── requirements.txt # Python dependencies
├── 📂 css/
│ └── styles.css # Demo page styles
├── 📂 js/
│ └── script.js # Demo page scripts
├── index.html # Interactive demo page
├── README.md # This file
└── LICENSE # License information
```

## 🚀 Quick Start

### 1️⃣ Install Python Dependencies

```bash
cd scripts
pip install -r requirements.txt

# Download NLTK data
python -c "import nltk; nltk.download('punkt'); nltk.download('stopwords'); nltk.download('wordnet')"
```

### 2️⃣ Generate Custom Dataset

```bash
# Generate 1000 samples
python generate_data.py --samples 1000

# Generate 5000 balanced samples in all formats
python generate_data.py --samples 5000 --balanced --all-formats

# Generate with train/test split
python generate_data.py --samples 10000 --split 0.8 --output ../data/custom
```

### 3️⃣ Preprocess Data

```bash
# Basic preprocessing
python preprocess_data.py --input ../data/sentiment_data.csv

# Advanced preprocessing with lemmatization
python preprocess_data.py --input ../data/sentiment_data.csv --lemmatize --remove-stopwords

# Build vocabulary
python preprocess_data.py --input ../data/sentiment_data.csv --build-vocab
```

### 4️⃣ Analyze Sentiment

```bash
# Analyze single text
python analyze_sentiment.py --text "I love this product!"

# Interactive mode
python analyze_sentiment.py --interactive

# Evaluate on dataset
python analyze_sentiment.py --file ../data/sentiment_data.csv --evaluate
```

### 5️⃣ Visualize Data

```bash
# Generate all charts
python visualize_data.py --input ../data/sentiment_data.csv --all-charts

# Generate HTML report
python visualize_data.py --input ../data/sentiment_data.csv --html-report
```

### 6️⃣ Train ML Models

```bash
# Train Naive Bayes model
python train_model.py --input ../data/sentiment_data.csv --model naive_bayes

# Train all models and save best
python train_model.py --input ../data/sentiment_data.csv --all-models --save

# Train with custom train/test files
python train_model.py --train ../data/train_data.csv --test ../data/test_data.csv --model svm
```

## 📜 Python Scripts Reference

### `generate_data.py` - Data Generator

Generate synthetic sentiment analysis data with customizable parameters.

```bash
python generate_data.py [OPTIONS]

Options:
-n, --samples Number of samples to generate (default: 1000)
-o, --output Output file path (without extension)
-f, --format Output format: csv, json, txt, all
-b, --balanced Generate balanced dataset
-s, --split Train/test split ratio (e.g., 0.8)
-m, --include-metadata Include metadata in samples
-a, --all-formats Export in all formats
--seed Random seed for reproducibility
```

### `preprocess_data.py` - Data Preprocessor

Clean and preprocess text data for NLP models.

```bash
python preprocess_data.py [OPTIONS]

Options:
-i, --input Input file path (required)
-o, --output Output directory
-l, --lowercase Convert to lowercase
-s, --remove-stopwords Remove stopwords
-p, --remove-punctuation Remove punctuation
--lemmatize Apply lemmatization
--stem Apply stemming
-f, --extract-features Extract sentiment features
-v, --build-vocab Build vocabulary file
```

### `analyze_sentiment.py` - Sentiment Analyzer

Analyze sentiment using multiple methods (lexicon-based, VADER, TextBlob).

```bash
python analyze_sentiment.py [OPTIONS]

Options:
-t, --text Text to analyze
-f, --file File to analyze
-e, --evaluate Evaluate predictions against labels
-m, --method Analysis method: lexicon, vader, textblob, ensemble
-i, --interactive Run in interactive mode
-o, --output Output file for results
```

### `visualize_data.py` - Data Visualizer

Generate charts, word clouds, and statistical reports.

```bash
python visualize_data.py [OPTIONS]

Options:
-i, --input Input file path (required)
-o, --output Output directory for charts
-a, --all-charts Generate all available charts
-s, --stats-only Only print statistics
-r, --html-report Generate HTML report
```

### `train_model.py` - Model Trainer

Train and evaluate machine learning models for sentiment classification.

```bash
python train_model.py [OPTIONS]

Options:
-i, --input Input data file
--train Training data file
--test Test data file
-m, --model Model: naive_bayes, svm, logistic_regression, random_forest
-a, --all-models Train all available models
-s, --split Train/test split ratio
-v, --vectorizer Vectorizer: tfidf, count
-cv, --cross-validate Cross-validation folds
--save Save the best model
-o, --output Output directory for models
```

## 📊 Dataset Statistics

| Metric | Value |
|--------|-------|
| Total Samples | 50+ (expandable with generator) |
| Sentiment Classes | 3 (Positive, Neutral, Negative) |
| Text Sources | 3 (Reviews, Social Media, Comments) |
| Avg. Text Length | ~142 characters |
| File Formats | CSV, JSON, TXT |
| Languages | English |

## 🏷️ Sentiment Distribution

- **Positive**: ~37% of samples
- **Neutral**: ~30% of samples
- **Negative**: ~33% of samples

## 🛠️ Technologies & Dependencies

### Core Technologies
| Technology | Description |
|------------|-------------|
| CSV | Standard comma-separated values format |
| JSON | JavaScript Object Notation format |
| TXT | Plain text format |
| Python 3.8+ | Programming language |

### Python Libraries
| Library | Purpose |
|---------|---------|
| NLTK | Natural language processing |
| spaCy | Industrial NLP |
| TextBlob | Simple sentiment analysis |
| VADER | Sentiment analysis |
| scikit-learn | Machine learning |
| matplotlib | Data visualization |
| wordcloud | Word cloud generation |

## 📖 Usage Examples

### Loading Data in Python

```python
import pandas as pd
import json

# Load CSV
df = pd.read_csv('data/sentiment_data.csv', comment='#')

# Load JSON
with open('data/sentiment_data.json', 'r') as f:
data = json.load(f)
samples = data['data']
```

### Training a Custom Model

```python
from scripts.train_model import SentimentModelTrainer, load_data, prepare_data

# Load data
data = load_data('data/sentiment_data.csv')
texts, labels = prepare_data(data)

# Train model
trainer = SentimentModelTrainer()
trainer.train(texts[:80], labels[:80], 'svm')

# Evaluate
results = trainer.evaluate(texts[80:], labels[80:])
print(f"Accuracy: {results['svm']['accuracy']:.2%}")
```

### Interactive Sentiment Analysis

```python
from scripts.analyze_sentiment import EnsembleSentimentAnalyzer

analyzer = EnsembleSentimentAnalyzer()

# Analyze text
result = analyzer.analyze("This product is absolutely amazing!")
print(f"Sentiment: {result['ensemble']['sentiment']}")
```

## 📜 License

This dataset is provided for **educational purposes only**.

See the [LICENSE](LICENSE) file for more details.

## 👨‍💻 Author

**Molla Samser** - Founder of RSK World

- 🌐 Website: [https://rskworld.in](https://rskworld.in)
- 📧 Email: help@rskworld.in
- 📞 Phone: +91 93305 39277

### Design & Testing

**Rima Khatun** - Designer & Tester at RSK World

## 🤝 Contributing

Contributions are welcome! If you'd like to contribute:

1. Fork the repository
2. Create a new branch
3. Make your changes
4. Submit a pull request

## 📞 Contact

For questions, suggestions, or support:

- **General Inquiries**: info@rskworld.in
- **Support**: support@rskworld.in
- **Website**: [https://rskworld.in/contact.php](https://rskworld.in/contact.php)

## ⭐ Support

If you find this dataset helpful, please consider:

- ⭐ Starring this repository
- 📢 Sharing with others
- 🔗 Linking back to RSK World

---


© 2026 RSK World - Free Programming Resources & Source Code 
Founded by Molla Samser | Designed by Rima Khatun



<a href="https://rskworld.in">Website</a> •
<a href="https://rskworld.in/about.php">About</a> •
<a href="https://rskworld.in/contact.php">Contact</a>

Theme Settings

Color Scheme

Display Options

Font Size

RELEASE_NOTES.md

README.md

Theme Settings

Color Scheme

Display Options

Font Size

RELEASE_NOTES.md

README.md

🚀 Support RSK World