We are a Data Mining, Analytics &  Brand Engagement  Service Provider Analytics Campaigns Data Mine PeopleBrowsr – DataMine, Campaigns and Analytics
Our Core Strategy Build Web Apps and Services that look into the Data Mine: Live Data Mine of Conversations and Mentions Social Search Engagement Work Flow Real Time & Historical Analysis PeopleBrowsr – DataMine, Campaigns and Analytics
Our Customers PeopleBrowsr – Campaigns, Analytics and DataMine
Problems we solve: Measure the Effect of Traditional Channels on Social Media Manage Viral Sentiment and Customer Service Issues Influence the Conversation Filter High Velocity Streams Send Targeted  Actionable  Messages Build an engaged sticky Audience Convert Social Media into Sales Calculate ROI PeopleBrowsr – DataMine, Campaigns and Analytics
Over 100,000 Brand Mentio ns a  day  PeopleBrowsr – DataMine, Campaigns and Analytics
MetaData Stream Feeds MetaData Cloud Line between social media networks is blurring Twitter is open 28% are heavy socializers PeopleBrowsr – DataMine, Campaigns and Analytics
Media Spend on Twitter PeopleBrowsr – DataMine, Campaigns and Analytics
Data Mine Archive PeopleBrowsr – DataMine, Campaigns and Analytics Over 360 days Twitter, MySpace, Facebook and Blog Posts Archive - 1 TB Month FILTER  Tweets, BIOs, Location API access for large scale campaigns
Data Mine Live Stream Fan Pages Mentions, RTs, … Comments, Sharing,… Profiles, Comments, … Status Updates, Comments, … Pictures, Comments, … Connections, Comments PeopleBrowsr – DataMine, Campaigns and Analytics Blogs Mentions, …
A New Media Buy Media Buy: Analytics & Campaigns Print Radio TV Social Media $$$ Social Media is an efficient  Channel that is measurable  PeopleBrowsr – DataMine, Campaigns and Analytics
Hollywood Movie Company Size:  $200 Million in Revenue Social Media Spend:  $100K Goal:  Evaluate impact of Traditional Media on the Social Media sphere Build engaged audience PeopleBrowsr – DataMine, Campaigns and Analytics
Hollywood Movie Solution:  180 day Historical Analysis of Posts overlay on TV Ad spend and other channels Performance:  Identified  key performer  as branded video content 50% fluctuation on engagement  based on time of message release Targeted influencers  RTed  a combined  879 times  PeopleBrowsr – DataMine, Campaigns and Analytics
PeopleBrowsr Difference PeopleBrowsr – DataMine, Campaigns and Analytics Data Mine:  18 months of Twitter history to power services and Analytic.ly Campaigns:  Find influencers & build engaged audience to interact with brand Data Analysis:  Filtering processes to remove affiliates and spam Sentiment Analysis:  end-to-end workflow using mechanical turk to deliver up to   95% accuracy of sentiment Custom Analytics:  Customized for client needs to track CPM, demographic of  audience, conversation topics Reports:  In -depth reports from exceptional analysts
Human Sentiment Analysis We analyze 18 months of historical data and  live streams in real time We use a special algorithm and then have real people improving the result up to 95% accuracy. 95%   accuracy Vs 70-80% automation alone  PeopleBrowsr – DataMine, Campaigns and Analytics
one  we build a live stream for an industry or a group using @Names or Keywords. Eg: Foo Camp attendees and the companies that they represent or Airlines. How it works PeopleBrowsr – DataMine, Campaigns and Analytics
How it works two  we then analyze that stream with a special dictionary for the industry or group and sort the results into buckets. PeopleBrowsr – DataMine, Campaigns and Analytics
How it works three  increase quality with  real time human re-sorting PeopleBrowsr – DataMine, Campaigns and Analytics
PeopleBrowsr – DataMine, Campaigns and Analytics
Eg: Quality Improvement on June Airlines data PeopleBrowsr – DataMine, Campaigns and Analytics
PeopleBrowsr – DataMine, Campaigns and Analytics
Industry Analytics Reports PeopleBrowsr – DataMine, Campaigns and Analytics
2010 SuperBowl Analytics:  Effect of Traditional Media on Social Media Mechanical Turk to measure accurate Sentiment Metrics to measure Success: Total Mentions Positive Mentions By Volume Mullen and Radian6 PeopleBrowsr – DataMine, Campaigns and Analytics
SuperBowl Results:  103,158 Total Mentions Sampled 1000 Tweets from Every Brand and used Mechanical Turk Human Sentiment to analyze Polarized: 50% Positive 28% Negative 18% Neutral PeopleBrowsr – DataMine, Campaigns and Analytics
SuperBowl PeopleBrowsr – DataMine, Campaigns and Analytics
SuperBowl Positive Sentiment Chart PeopleBrowsr – DataMine, Campaigns and Analytics
SuperBowl Positive Sentiment Chart PeopleBrowsr – DataMine, Campaigns and Analytics
SuperBowl Most Negative: Focus on the Family GoDaddy Neutral Coca Cola Budweiser  PeopleBrowsr – DataMine, Campaigns and Analytics
PeopleBrowsr – DataMine, Campaigns and Analytics SuperBowl
O’Reilly and PeopleBrowsr Analysis:
Correlation of Tweets and Ads
By Volume Mullen and Radian6 O’Reilly and PeopleBrowsr O’Reilly and PeopleBrowsr By Volume By Positive http://www.slideshare.net/peoplebrowsr/superbowl-3231030 Contact me for an xls of the Brands Tweets  [email_address] SuperBowl PeopleBrowsr – DataMine, Campaigns and Analytics
PeopleBrowsr Campaign Process PeopleBrowsr – DataMine, Campaigns and Analytics Historical and Ongoing Sentiment Analysis Campaigns to Build  Relevant Followers Follow ,  followback  DM Offer products and services directly to consumers  Campaigns to Direct Message Reporting on ROI for traditional and Social Media Custom Monitoring Dashboards Injecting the brand  into the conversation
PeopleBrowsr Campaign Process Human-sorted Sentiment Analysis with 95% accuracy (known as mechanical turk) Upon follow-back (an voluntary opt-in), Direct Messages (DM) sent DMs offer information, promotions, or a social experience Inject the brand into the conversation Measure the impact of traditional campaigns with Social Media Key Performance Indicators Each dashboard customized to reflect dictionaries relevant to industry View competitor metrics PeopleBrowsr – DataMine, Campaigns and Analytics Initiate follow request to potential influencers and followers based on self-published preferences, activities, social, and location data
PeopleBrowsr Campaign Process STATISTIC:  15 Tb data 18 months of history 200,000 turks online at one time STATISTIC:  50-80% follow back SCORECARD: MIN New Followers:  8,000 MAX New Followers:  22,000  STATISTIC:  40-50%  click through  PeopleBrowsr – DataMine, Campaigns and Analytics
Filtering a high Velocity  Stream Seek an effective way to measure brand sentiment accurately.  The goal is to find a list of influencers speaking in both positive and negative terms and engage. Risks:  Stream includes spam, affiliates, and other non-relevant mentions.  Velocity  10,000 Mentions/day PeopleBrowsr – DataMine, Campaigns and Analytics
  Filtering Process Build a unique @name list from the extract Build spam @names with PB spam alogorithm Build affiliates list Review Spam and Affiliate @names - reinsert false positives  Finalise Spam and Affiliate list Wash spam and Affiliate list against the full stream to produce a non-Spam and Non-Affiliate cleaned Daily Stream PeopleBrowsr – DataMine, Campaigns and Analytics
Custom Dashboards and Reporting PeopleBrowsr – DataMine, Campaigns and Analytics
Social Media Metrics for ROI Audience Profile Monitor Engaged and Active Followers Optimal Time for Engagement Best Time for Engagement with Followers Geo Location of Followers CTR – 50% PeopleBrowsr – DataMine, Campaigns and Analytics
Sneak Preview: T2 – Next Gen Combine Search and Posting Provide inline Content Contextual Ads as a Post is created HyperConnected HyperLocal Integrated with other Services  Yelp Amazon Open Table PeopleBrowsr – DataMine, Campaigns and Analytics
T2 prototype PeopleBrowsr – DataMine, Campaigns and Analytics
T2 prototype PeopleBrowsr – DataMine, Campaigns and Analytics
Contact us… [email_address] PeopleBrowsr – DataMine, Campaigns and Analytics

PeopleBrowsr Gravity Summit Deck

  • 1.
    We are aData Mining, Analytics & Brand Engagement Service Provider Analytics Campaigns Data Mine PeopleBrowsr – DataMine, Campaigns and Analytics
  • 2.
    Our Core StrategyBuild Web Apps and Services that look into the Data Mine: Live Data Mine of Conversations and Mentions Social Search Engagement Work Flow Real Time & Historical Analysis PeopleBrowsr – DataMine, Campaigns and Analytics
  • 3.
    Our Customers PeopleBrowsr– Campaigns, Analytics and DataMine
  • 4.
    Problems we solve:Measure the Effect of Traditional Channels on Social Media Manage Viral Sentiment and Customer Service Issues Influence the Conversation Filter High Velocity Streams Send Targeted Actionable Messages Build an engaged sticky Audience Convert Social Media into Sales Calculate ROI PeopleBrowsr – DataMine, Campaigns and Analytics
  • 5.
    Over 100,000 BrandMentio ns a day PeopleBrowsr – DataMine, Campaigns and Analytics
  • 6.
    MetaData Stream FeedsMetaData Cloud Line between social media networks is blurring Twitter is open 28% are heavy socializers PeopleBrowsr – DataMine, Campaigns and Analytics
  • 7.
    Media Spend onTwitter PeopleBrowsr – DataMine, Campaigns and Analytics
  • 8.
    Data Mine ArchivePeopleBrowsr – DataMine, Campaigns and Analytics Over 360 days Twitter, MySpace, Facebook and Blog Posts Archive - 1 TB Month FILTER Tweets, BIOs, Location API access for large scale campaigns
  • 9.
    Data Mine LiveStream Fan Pages Mentions, RTs, … Comments, Sharing,… Profiles, Comments, … Status Updates, Comments, … Pictures, Comments, … Connections, Comments PeopleBrowsr – DataMine, Campaigns and Analytics Blogs Mentions, …
  • 10.
    A New MediaBuy Media Buy: Analytics & Campaigns Print Radio TV Social Media $$$ Social Media is an efficient Channel that is measurable PeopleBrowsr – DataMine, Campaigns and Analytics
  • 11.
    Hollywood Movie CompanySize: $200 Million in Revenue Social Media Spend: $100K Goal: Evaluate impact of Traditional Media on the Social Media sphere Build engaged audience PeopleBrowsr – DataMine, Campaigns and Analytics
  • 12.
    Hollywood Movie Solution: 180 day Historical Analysis of Posts overlay on TV Ad spend and other channels Performance: Identified key performer as branded video content 50% fluctuation on engagement based on time of message release Targeted influencers RTed a combined 879 times PeopleBrowsr – DataMine, Campaigns and Analytics
  • 13.
    PeopleBrowsr Difference PeopleBrowsr– DataMine, Campaigns and Analytics Data Mine: 18 months of Twitter history to power services and Analytic.ly Campaigns: Find influencers & build engaged audience to interact with brand Data Analysis: Filtering processes to remove affiliates and spam Sentiment Analysis: end-to-end workflow using mechanical turk to deliver up to 95% accuracy of sentiment Custom Analytics: Customized for client needs to track CPM, demographic of audience, conversation topics Reports: In -depth reports from exceptional analysts
  • 14.
    Human Sentiment AnalysisWe analyze 18 months of historical data and live streams in real time We use a special algorithm and then have real people improving the result up to 95% accuracy. 95% accuracy Vs 70-80% automation alone PeopleBrowsr – DataMine, Campaigns and Analytics
  • 15.
    one webuild a live stream for an industry or a group using @Names or Keywords. Eg: Foo Camp attendees and the companies that they represent or Airlines. How it works PeopleBrowsr – DataMine, Campaigns and Analytics
  • 16.
    How it workstwo we then analyze that stream with a special dictionary for the industry or group and sort the results into buckets. PeopleBrowsr – DataMine, Campaigns and Analytics
  • 17.
    How it worksthree increase quality with real time human re-sorting PeopleBrowsr – DataMine, Campaigns and Analytics
  • 18.
    PeopleBrowsr – DataMine,Campaigns and Analytics
  • 19.
    Eg: Quality Improvementon June Airlines data PeopleBrowsr – DataMine, Campaigns and Analytics
  • 20.
    PeopleBrowsr – DataMine,Campaigns and Analytics
  • 21.
    Industry Analytics ReportsPeopleBrowsr – DataMine, Campaigns and Analytics
  • 22.
    2010 SuperBowl Analytics: Effect of Traditional Media on Social Media Mechanical Turk to measure accurate Sentiment Metrics to measure Success: Total Mentions Positive Mentions By Volume Mullen and Radian6 PeopleBrowsr – DataMine, Campaigns and Analytics
  • 23.
    SuperBowl Results: 103,158 Total Mentions Sampled 1000 Tweets from Every Brand and used Mechanical Turk Human Sentiment to analyze Polarized: 50% Positive 28% Negative 18% Neutral PeopleBrowsr – DataMine, Campaigns and Analytics
  • 24.
    SuperBowl PeopleBrowsr –DataMine, Campaigns and Analytics
  • 25.
    SuperBowl Positive SentimentChart PeopleBrowsr – DataMine, Campaigns and Analytics
  • 26.
    SuperBowl Positive SentimentChart PeopleBrowsr – DataMine, Campaigns and Analytics
  • 27.
    SuperBowl Most Negative:Focus on the Family GoDaddy Neutral Coca Cola Budweiser PeopleBrowsr – DataMine, Campaigns and Analytics
  • 28.
    PeopleBrowsr – DataMine,Campaigns and Analytics SuperBowl
  • 29.
  • 30.
  • 31.
    By Volume Mullenand Radian6 O’Reilly and PeopleBrowsr O’Reilly and PeopleBrowsr By Volume By Positive http://www.slideshare.net/peoplebrowsr/superbowl-3231030 Contact me for an xls of the Brands Tweets [email_address] SuperBowl PeopleBrowsr – DataMine, Campaigns and Analytics
  • 32.
    PeopleBrowsr Campaign ProcessPeopleBrowsr – DataMine, Campaigns and Analytics Historical and Ongoing Sentiment Analysis Campaigns to Build Relevant Followers Follow , followback DM Offer products and services directly to consumers Campaigns to Direct Message Reporting on ROI for traditional and Social Media Custom Monitoring Dashboards Injecting the brand into the conversation
  • 33.
    PeopleBrowsr Campaign ProcessHuman-sorted Sentiment Analysis with 95% accuracy (known as mechanical turk) Upon follow-back (an voluntary opt-in), Direct Messages (DM) sent DMs offer information, promotions, or a social experience Inject the brand into the conversation Measure the impact of traditional campaigns with Social Media Key Performance Indicators Each dashboard customized to reflect dictionaries relevant to industry View competitor metrics PeopleBrowsr – DataMine, Campaigns and Analytics Initiate follow request to potential influencers and followers based on self-published preferences, activities, social, and location data
  • 34.
    PeopleBrowsr Campaign ProcessSTATISTIC: 15 Tb data 18 months of history 200,000 turks online at one time STATISTIC: 50-80% follow back SCORECARD: MIN New Followers: 8,000 MAX New Followers: 22,000 STATISTIC: 40-50% click through PeopleBrowsr – DataMine, Campaigns and Analytics
  • 35.
    Filtering a highVelocity Stream Seek an effective way to measure brand sentiment accurately. The goal is to find a list of influencers speaking in both positive and negative terms and engage. Risks: Stream includes spam, affiliates, and other non-relevant mentions. Velocity 10,000 Mentions/day PeopleBrowsr – DataMine, Campaigns and Analytics
  • 36.
    FilteringProcess Build a unique @name list from the extract Build spam @names with PB spam alogorithm Build affiliates list Review Spam and Affiliate @names - reinsert false positives Finalise Spam and Affiliate list Wash spam and Affiliate list against the full stream to produce a non-Spam and Non-Affiliate cleaned Daily Stream PeopleBrowsr – DataMine, Campaigns and Analytics
  • 37.
    Custom Dashboards andReporting PeopleBrowsr – DataMine, Campaigns and Analytics
  • 38.
    Social Media Metricsfor ROI Audience Profile Monitor Engaged and Active Followers Optimal Time for Engagement Best Time for Engagement with Followers Geo Location of Followers CTR – 50% PeopleBrowsr – DataMine, Campaigns and Analytics
  • 39.
    Sneak Preview: T2– Next Gen Combine Search and Posting Provide inline Content Contextual Ads as a Post is created HyperConnected HyperLocal Integrated with other Services Yelp Amazon Open Table PeopleBrowsr – DataMine, Campaigns and Analytics
  • 40.
    T2 prototype PeopleBrowsr– DataMine, Campaigns and Analytics
  • 41.
    T2 prototype PeopleBrowsr– DataMine, Campaigns and Analytics
  • 42.
    Contact us… [email_address]PeopleBrowsr – DataMine, Campaigns and Analytics