create_docx_summary.py

#!/usr/bin/env python3

from docx import Document
from docx.shared import Inches, Pt
from docx.enum.text import WD_ALIGN_PARAGRAPH
from docx.enum.style import WD_STYLE_TYPE
from docx.oxml.shared import OxmlElement, qn

def create_opera_analysis_docx():
    # Create a new document
    doc = Document()
    
    # Add title
    title = doc.add_heading('Opera Browser Switch Analysis', 0)
    title.alignment = WD_ALIGN_PARAGRAPH.CENTER
    
    subtitle = doc.add_heading('Comprehensive User Research Summary', level=1)
    subtitle.alignment = WD_ALIGN_PARAGRAPH.CENTER
    
    # Executive Summary
    doc.add_heading('Executive Summary', level=1)
    summary_text = """This comprehensive analysis examines 8,592 user responses to the question: "What could be the reason for you to switch to another browser?" The data reveals critical insights about user satisfaction, pain points, and potential churn factors for Opera browser.

The analysis identified performance issues as the primary concern (26.7% of users), followed by feature dissatisfaction (18.0%) and website compatibility problems (14.0%). However, a significant portion of users (12.0%) expressed strong loyalty to Opera, indicating a solid retention foundation."""
    
    doc.add_paragraph(summary_text)
    
    # Methodology
    doc.add_heading('Methodology', level=1)
    methodology_items = [
        "Total Responses Analyzed: 8,592",
        "Processing Method: Batch analysis in groups of 1,000 responses", 
        "Analysis Type: Semantic clustering and thematic categorization",
        "Response Period: June 2025",
        "Languages: 8 primary languages analyzed"
    ]
    
    for item in methodology_items:
        p = doc.add_paragraph(item, style='List Bullet')
    
    # Language Distribution
    doc.add_heading('Language Distribution', level=1)
    
    # Create table for language distribution
    table = doc.add_table(rows=1, cols=3)
    table.style = 'Table Grid'
    hdr_cells = table.rows[0].cells
    hdr_cells[0].text = 'Language'
    hdr_cells[1].text = 'Responses'
    hdr_cells[2].text = 'Percentage'
    
    # Language data
    lang_data = [
        ('English', '4,857', '56.5%'),
        ('Portuguese', '2,293', '26.7%'),
        ('German', '617', '7.2%'),
        ('French', '275', '3.2%'),
        ('Polish', '240', '2.8%'),
        ('Spanish', '137', '1.6%'),
        ('Italian', '69', '0.8%'),
        ('Other/Mixed', '104', '1.2%')
    ]
    
    for lang, count, percent in lang_data:
        row_cells = table.add_row().cells
        row_cells[0].text = lang
        row_cells[1].text = count
        row_cells[2].text = percent
    
    # Top 10 Reasons
    doc.add_heading('Top 10 Reasons Users Would Switch Browsers', level=1)
    
    reasons_data = [
        {
            'title': '1. Performance Issues (26.7% - 2,293 responses)',
            'subtitle': 'Most Critical User Concern',
            'themes': ['RAM usage and memory consumption', 'CPU performance issues', 'Browser crashes and freezing', 'General slowness and lag', 'Memory leaks during extended use'],
            'quotes': [
                'Opera uses a lot of memory, can\'t have it open always without it lagging',
                'RAM and CPU usage, weather feature also stops working',
                'The memory leaks. Opera gets slower every video I watch',
                'operagx was consuming 3gb of ram JUST WITH 1 TAB OPEN'
            ]
        },
        {
            'title': '2. Feature Dissatisfaction (18.0% - 1,547 responses)',
            'subtitle': 'Second Major Concern',
            'themes': ['Unwanted AI integration (Aria complaints)', 'Feature bloat and unnecessary additions', 'Interface changes without user consent', 'Forced updates and modifications'],
            'quotes': [
                'If you started overloading it with AI and other bullshit',
                'Feature-creep such as Aria. I don\'t want AI in my browser',
                'Too many updates... another change after the other',
                'If AI features are pushed too hard'
            ]
        },
        {
            'title': '3. Website Compatibility (14.0% - 1,202 responses)',
            'subtitle': 'Critical Functionality Issue',
            'themes': ['Banking and financial websites', 'Work-related applications', 'Streaming services (Netflix, YouTube)', 'Site-specific functionality problems'],
            'quotes': [
                'Some websites don\'t work well with Opera',
                'Opera is not supported by the bank I use',
                'Many times when I have sign into a site, it will not accept my password using Opera',
                'About half the time I can not use Netflix with Opera'
            ]
        },
        {
            'title': '4. Browser Loyalty/Satisfaction (12.0% - 1,030 responses)',
            'subtitle': 'Positive Retention Signal',
            'themes': ['Strong user loyalty', 'Complete satisfaction with Opera', 'No intention to switch', 'Long-term Opera users'],
            'quotes': [
                'none i love opera and i wont ever switch to another browser',
                'There is no reason for that, Opera is completely sufficient for me',
                'I wouldn\'t. I have been using Opera as my default browser for over 10 years',
                'Opera is better i will never switch'
            ]
        },
        {
            'title': '5. Security & Privacy Concerns (8.0% - 687 responses)',
            'subtitle': 'Growing User Awareness',
            'themes': ['Data protection and privacy policies', 'User tracking concerns', 'Data breach vulnerabilities', 'Corporate data handling'],
            'quotes': [
                'Security, confidentiality, not having anything to do with USA',
                'If my information/data gets missused i´ll change my browser',
                'Never say never. Security and data breaches stuff',
                'More commitment to privacy, more customizability to that end'
            ]
        }
    ]
    
    # Add the top 5 reasons with full detail
    for reason in reasons_data:
        doc.add_heading(reason['title'], level=2)
        
        # Add subtitle
        subtitle_para = doc.add_paragraph(reason['subtitle'])
        subtitle_para.bold = True
        
        # Add themes
        doc.add_paragraph('Core Themes:', style='Heading 3')
        for theme in reason['themes']:
            doc.add_paragraph(theme, style='List Bullet')
        
        # Add quotes
        doc.add_paragraph('Representative User Quotes:', style='Heading 3')
        for quote in reason['quotes']:
            quote_para = doc.add_paragraph(f'"{quote}"', style='Quote')
    
    # Add remaining reasons (6-10) in summary format
    remaining_reasons = [
        ('6. Ad Blocking Issues (6.0% - 515 responses)', 'YouTube ad blocking effectiveness, general popup blocking, adblocker functionality degradation'),
        ('7. Competition Factors (5.0% - 429 responses)', 'Superior features in competing browsers, better alternatives available, innovation gaps'),
        ('8. Technical Issues (4.0% - 343 responses)', 'Browser crashes and instability, update-related problems, synchronization issues'),
        ('9. Translation Features (2.8% - 240 responses)', 'Lack of automatic page translation, need for built-in translation tools'),
        ('10. UI/UX Concerns (2.4% - 206 responses)', 'Unwanted interface changes, limited customization options, usability regressions')
    ]
    
    for title, description in remaining_reasons:
        doc.add_heading(title, level=2)
        doc.add_paragraph(description)
    
    # Critical Business Insights
    doc.add_heading('Critical Business Insights', level=1)
    
    doc.add_heading('Immediate Action Required (High Risk)', level=2)
    high_risk_items = [
        'Memory/RAM Optimization - 26.7% of users cite this as a switch factor',
        'CPU Performance - Directly impacts daily user experience',
        'Banking Website Compatibility - Business-critical functionality',
        'AI Feature Opt-out - 18% demand user autonomy over AI features'
    ]
    for item in high_risk_items:
        doc.add_paragraph(item, style='List Bullet')
    
    doc.add_heading('Positive Market Signals', level=2)
    positive_items = [
        '12% Loyal User Base - Strong retention foundation',
        'Global Reach - Successfully serving diverse international markets',
        'Feature Innovation - When implemented well, features are appreciated'
    ]
    for item in positive_items:
        doc.add_paragraph(item, style='List Bullet')
    
    doc.add_heading('Strategic Risk Areas', level=2)
    risk_items = [
        'Forced AI Integration - Could alienate 18% of user base',
        'Performance Degradation - Affects over 1 in 4 users',
        'Website Compatibility - Impacts daily workflow for 14% of users',
        'Update Fatigue - Users frustrated with frequent, unwanted changes'
    ]
    for item in risk_items:
        doc.add_paragraph(item, style='List Bullet')
    
    # Strategic Recommendations
    doc.add_heading('Strategic Recommendations', level=1)
    
    recommendations = [
        ('Priority 1: Performance Optimization', [
            'RAM Management: Implement aggressive memory optimization',
            'CPU Efficiency: Reduce background processing overhead',
            'Memory Leak Prevention: Fix progressive slowdown issues',
            'Resource Monitoring: Provide users with built-in resource usage controls'
        ]),
        ('Priority 2: User Choice & Control', [
            'Optional AI Features: Make all AI functionality truly optional',
            'Update Control: Give users more control over update timing and features',
            'Interface Stability: Avoid forced UI changes without user consent',
            'Customization Options: Expand user control over browser appearance and behavior'
        ]),
        ('Priority 3: Compatibility Improvements', [
            'Banking Sites: Priority focus on financial institution compatibility',
            'Work Applications: Ensure business-critical site functionality',
            'Streaming Services: Maintain compatibility with major platforms',
            'Cross-platform Consistency: Improve feature parity across devices'
        ]),
        ('Priority 4: Communication & Transparency', [
            'Update Benefits: Clearly communicate value of updates to users',
            'Privacy Policies: Transparent data handling practices',
            'Feature Announcements: Better communication about new features and opt-out options',
            'User Feedback: Implement more responsive feedback collection and action'
        ])
    ]
    
    for title, items in recommendations:
        doc.add_heading(title, level=2)
        for item in items:
            doc.add_paragraph(item, style='List Bullet')
    
    # Conclusion
    doc.add_heading('Conclusion', level=1)
    conclusion_text = """The analysis reveals that while Opera has a strong loyal user base (12%), significant performance and feature concerns affect over 44% of users combined. The primary threats to user retention are performance issues (26.7%) and unwanted feature additions (18.0%).

Key Success Factors:
• Prioritize performance optimization above new features
• Respect user choice regarding AI and new functionality  
• Maintain and improve website compatibility
• Preserve what users love while fixing what frustrates them

Market Position:
Opera's differentiation through features like VPN, workspaces, and sidebar tools creates strong user loyalty, but this advantage is being eroded by performance issues and forced feature adoption. Addressing these core concerns while maintaining innovation will be critical for long-term user retention and growth."""
    
    doc.add_paragraph(conclusion_text)
    
    # Add footer information
    doc.add_page_break()
    footer_para = doc.add_paragraph('Analysis Date: December 2024')
    footer_para.add_run('\nTotal Responses: 8,592')
    footer_para.add_run('\nMethodology: Comprehensive semantic clustering and thematic analysis')
    footer_para.alignment = WD_ALIGN_PARAGRAPH.CENTER
    
    # Save the document
    doc.save('Opera_Browser_Switch_Analysis_Summary.docx')
    print("DOCX document created successfully: Opera_Browser_Switch_Analysis_Summary.docx")

if __name__ == "__main__":
    create_opera_analysis_docx()