What You'll Learn
By the end of this guide, you'll know how to:
- Track trending topics and conversations
- Monitor hashtag campaigns
- Analyze sentiment at scale
- Understand how content goes viral
Estimated time: 10 minutes
Trending Topic Analysis 🔥
Sample Query
Search for tweets about "artificial intelligence" from the past 7 days. Show me the top 50 most engaging posts, identify key themes, and create a timeline of how the conversation evolved.
What You Get
Real-time Trend Detection:
- Volume of tweets over time
- Peak activity periods
- Trending subtopics
- Emerging narratives
Engagement Metrics:
- Total reach and impressions
- Engagement rates
- Top performing content
- Viral moments
Key Influencers:
- Most retweeted accounts
- Thought leaders in the space
- New voices gaining traction
- Network connectors
Theme Clustering:
- Main conversation topics
- Related discussions
- Sentiment by theme
- Topic evolution
Example Output
🔍 Analysis Results: "artificial intelligence" Period: Oct 28 - Nov 4, 2024 📊 Overview: • Total Tweets: 847,293 • Unique Authors: 234,567 • Total Engagement: 24.5M interactions • Peak Hour: Nov 2, 3 PM EST 🌟 Top Engaging Tweet: @TechCEO: "Just launched our new AI model..." ├─ Retweets: 125.4K ├─ Replies: 23.1K ├─ Likes: 876.3K └─ Impressions: 15.2M 📈 Key Themes Identified: 1. GPT-5 Speculation (28%) 2. AI Regulation Debate (22%) 3. OpenAI DevDay (18%) 4. AI in Healthcare (15%) 5. Ethics Concerns (17%) ⏰ Timeline of Events: Oct 28: Discussion starts on new model release Oct 30: Regulation news spikes conversation Nov 1: DevDay announcements dominate Nov 3: Healthcare AI breakthrough shared Nov 4: Ethics debate intensifies
Hashtag Campaign Tracking 📢
Sample Query
Track the #ClimateAction hashtag from the past month. Calculate total engagement, identify top contributors, analyze posting patterns, and measure campaign reach and effectiveness.
Campaign Performance Metrics
Volume Metrics:
- Total Tweets: 1,234,567
- Unique Contributors: 678,234
- Daily Tweet Volume
- Peak Activity Days
Reach Metrics:
- Total Reach: 450M users
- Total Impressions: 2.1B
- Unique Viewers: 125M
- Geographic Distribution
Engagement Metrics:
- Engagement Rate: 3.8%
- Total Engagements: 45M
- Retweets: 15M
- Replies: 8M
- Likes: 22M
Top Contributors:
1. @ClimateOrg - 12.4K tweets, 45M reach
2. @GreenFuture - 8.7K tweets, 32M reach
3. @EcoWarrior - 6.2K tweets, 28M reach
4. @SustainableNow - 5.1K tweets, 22M reach
5. @PlanetSaver - 4.8K tweets, 19M reach
Example Output
📢 Campaign Analytics: #ClimateAction 🎯 Campaign Performance: • Duration: 30 days • Total Tweets: 1,234,567 • Unique Contributors: 678,234 • Total Reach: 450M users • Engagement Rate: 3.8% 👥 Top 10 Contributors: 1. @ClimateOrg - 12.4K tweets, 45M reach 2. @GreenFuture - 8.7K tweets, 32M reach 3. @EcoWarrior - 6.2K tweets, 28M reach 4. @SustainableNow - 5.1K tweets, 22M reach 5. @PlanetSaver - 4.8K tweets, 19M reach 📅 Daily Tweet Volume: Oct 5: 52K tweets Oct 12: 78K tweets (Earth Day spike) Oct 19: 45K tweets Oct 26: 63K tweets Nov 2: 89K tweets (UN Summit) 🌍 Geographic Distribution: • North America: 35% • Europe: 28% • Asia: 22% • South America: 10% • Others: 5% 💡 Content Insights: • Photos/Videos: 45% higher engagement • Peak posting time: 6-9 PM local time • Most used co-hashtags: #SaveThePlanet, #GoGreen • Average tweet length: 187 characters
Sentiment Analysis 😊
Sample Query
Analyze sentiment for tweets mentioning "Tesla" over the past week. Categorize as positive, neutral, or negative. Show trending sentiment changes and identify what's driving each sentiment category.
Sentiment Distribution
Overall Breakdown:
- Positive: 45%
- Neutral: 35%
- Negative: 20%
Positive Sentiment (45%)
Key Drivers:
- New model announcement
- Sales figures exceeding expectations
- Innovation and technology praise
- Customer satisfaction stories
Example Tweets:
- "Incredible range on the new Model 3!"
- "Best EV on the market, hands down"
- "Tesla's autopilot is game-changing"
Neutral Sentiment (35%)
Key Drivers:
- Factual reporting
- Price comparisons
- Technical specifications
- News aggregation
Example Tweets:
- "Tesla reports Q3 earnings"
- "Comparing Tesla to competitors"
- "New charging station locations announced"
Negative Sentiment (20%)
Key Drivers:
- Quality control concerns
- Price increases
- Customer service issues
- Delivery delays
Example Tweets:
- "Build quality issues with my new Tesla"
- "Price hike is disappointing"
- "Service center wait times are too long"
Viral Content Analysis 🚀
Sample Query
Analyze tweet ID 1234567890 and track how it went viral. Show all retweets, quote tweets, and replies. Map the spread pattern, identify key amplifiers, and calculate viral velocity.
Viral Metrics
Spread Statistics:
- Total Retweets: 456,789
- Quote Tweets: 89,234
- Replies: 123,456
- Total Reach: 87.5M users
Viral Velocity:
- Hour 1: 523 RTs (organic growth)
- Hour 3: 15,234 RTs (influencer pickup)
- Hour 6: 89,456 RTs (media coverage)
- Hour 12: 234,567 RTs (peak virality)
- Hour 24: 456,789 RTs (plateau)
Key Amplifiers:
1. @MegaInfluencer (15M followers) - 2:45 PM
- Generated 123K additional retweets
2. @NewsOrg (8M followers) - 3:12 PM
- Generated 78K additional retweets
3. @CelebAccount (12M followers) - 4:30 PM
- Generated 94K additional retweets
Example Output
🚀 Viral Spread Analysis 📱 Original Tweet: Author: @ViralAccount Posted: Nov 1, 2024 at 2:34 PM Text: "This changes everything... [thread]" 📊 Viral Metrics: • Total Retweets: 456,789 • Quote Tweets: 89,234 • Replies: 123,456 • Total Reach: 87.5M users • Viral Velocity: 12,543 RTs/hour (peak) ⏱️ Spread Timeline: Hour 1: 523 RTs (organic growth) Hour 3: 15,234 RTs (influencer pickup) Hour 6: 89,456 RTs (media coverage) Hour 12: 234,567 RTs (peak virality) Hour 24: 456,789 RTs (plateau) 👥 Key Amplifiers: 1. @MegaInfluencer (15M followers) - 2:45 PM └─ Generated 123K additional retweets 2. @NewsOrg (8M followers) - 3:12 PM └─ Generated 78K additional retweets 3. @CelebAccount (12M followers) - 4:30 PM └─ Generated 94K additional retweets 🌐 Spread Pattern: • Started in Tech community • Jumped to News media (Hour 2) • Reached mainstream (Hour 4) • International pickup (Hour 8) 💬 Quote Tweet Analysis: • Supportive: 67% • Critical: 18% • Questions: 15% 📈 Engagement Quality: • Meaningful replies: 45% • Discussion threads: 12,345 • External shares: 234K+ • Bookmark rate: 8.9%
Advanced Features ⚡
🎯 Precise Filtering
Date Range Selection:
- Specific date ranges
- Relative time periods
- Event-based windows
Language Filters:
- Target specific languages
- Multi-language campaigns
- Regional analysis
Engagement Thresholds:
- Minimum retweets/likes
- Viral content only
- High-impact tweets
Author Filtering:
- Verified accounts only
- Specific user lists
- Exclude certain accounts
Media Type Filters:
- Photos only
- Videos only
- Text-only tweets
- Polls and threads
📊 Rich Analytics
Engagement Metrics:
- Retweets, replies, likes
- Quote tweets
- Bookmarks
- Impressions
Reach Calculations:
- Potential reach
- Actual impressions
- Unique viewers
- Share of voice
Growth Tracking:
- Volume over time
- Engagement trends
- Follower growth
- Campaign momentum
Trend Detection:
- Emerging topics
- Declining interest
- Cyclical patterns
- Breaking news
Pattern Analysis:
- Posting schedules
- Content types
- Audience behavior
- Network effects
🔄 Real-time Updates
Live Data Fetching:
- Current metrics
- Real-time monitoring
- Breaking news tracking
Cache Control:
- Force fresh data
- Balance speed vs. freshness
- Optimize performance
Continuous Monitoring:
- Set up alerts
- Track changes
- Monitor competitors
- Crisis detection
Use Case Examples
Brand Monitoring
Monitor all mentions of @YourBrand from the past 24 hours. Alert if negative sentiment spikes above 30%.
Competitor Tracking
Track @Competitor's campaign hashtag daily. Compare their engagement to our #OurCampaign performance.
Crisis Detection
Search for tweets mentioning @YourBrand with keywords "issue", "problem", "broken" in real-time. Alert on volume spikes.
Trend Forecasting
Analyze tweets about "sustainable fashion" over the past year. Identify emerging subtopics and predict next trends.
Influencer Discovery
Find tweets about "fintech" with 5000+ retweets from the past 3 months. Identify the top 20 authors for partnership outreach.
Best Practices
For Trend Analysis
Start with broad topic searches
Identify peak activity periods
Drill down into specific themes
Track evolution over time
Compare to historical baselines
For Campaign Tracking
Define success metrics upfront
Monitor continuously, not just at end
Compare to similar past campaigns
Track both volume and sentiment
Identify amplification opportunities
For Sentiment Analysis
Use consistent keywords/phrases
Sample enough data for accuracy
Look for sentiment shifts over time
Identify specific sentiment drivers
Cross-reference with other data
For Viral Content
Track early signals of virality
Identify key amplification moments
Analyze what made it spread
Learn from successful patterns
Apply insights to your content
Try These Queries
Beginner:
Search for tweets about "coffee" from today
Intermediate:
Find tweets with #MondayMotivation from this week, show the top 20 by engagement
Advanced:
Analyze sentiment for tweets mentioning @Starbucks vs @DunkinDonuts over the past month. Compare engagement patterns and identify what drives positive sentiment for each brand.
Next Steps
Learn More:
- Sample Prompts Library - 20 ready-to-use examples
- Business Use Cases - Real-world applications
💡 Pro Tip: Combine content analysis with user profile analysis for a complete picture. Analyze not just what's being said, but who's saying it and who's amplifying it.
Questions? Our support team can help you design the perfect query for your use case. Click the chat button to get started!