@twtrcon#twtrcontwtrcon.comsocialmediaatwork.com
Thank You to Our SponsorsANCHOR SPONSORSPLATINUM SPONSORSRESEARCH SPONSORRECEPTION SPONSORGOLD SPONSORSSILVER SPONSORSPlease visit our sponsors and exhibitors during the breaks!
Real Time Tools Mini SessionMaria Ogneva, Director of Social Media, Attensity| @themaria | @Attensity360
Attensity360 Overview for TWTRCONJune 14, 2010
Over 10 billion tweets so far.
Over 20% of tweets concern products and brands.http://live.psu.edu/story/41446
There are over 200,000,000blogs34%of bloggers post opinions about products and brands
The ProblemUntil now, “social media” applications have been largely focused on collecting and tracking customer conversations and leaving the rest up to individuals to do.Manually analyze for deeper analysisManually route and respond to individual conversationsManually add gleaned knowledge to company knowledgebasesThis approach is not scalable for the enterprise….
DemoAttensityListen across customer conversation channelsAnalyze accurately and efficientlyRelate this information to other informationAct on the informationWe call this the LARA methodology
The Social CustomerWho is talking about me?What do they think about my company?What problems are they having?What do they like about me vs. the competition?What new ideas do they have?Who is thinking of switching?Who is ready to buy?11
Easy setupProximity operators for recall and precision balanceEntities help disambiguate queries
Benchmark yourcoverage againstyour competition’s…
View tweets, posts, news, etc. on a specific topic…All in one placeDisplays impact, reach, sentiment for each postSort by date, impact, reach, or sentimentAttensity360
Prioritize Twitter outreach with user metadata and influence metrics.
Integrated EngagementView full post and assign for follow-up;Integrates with mail programs
Attensity360: Top Influencers ReportsSee where people are talking about you
See who istalking about you
…and what they have to say
See the most common terms in conjunction with your topic
Click to view all posts on that topic
DemoAttensityListen across customer conversation channelsAnalyzeaccurately and efficientlyRelate this information to other informationAct on the informationWe call this the LARA methodology
Attensity Analyze: Deeper, Cross-Channel AnalysisExtracts key entities, events, relationships,actions, purchasing reasons, intent and sentiment
DemoAttensityListen across customer conversation channelsAnalyze accurately and efficientlyRelate this information to other informationAct on the informationWe call this the LARA methodology
Listen, Analyze, Relate, Act: Data FlowsBroad Web CoverageThrough Attensity360Attensity AnalyzeServerDeeper Dive Web Through Attensity ScrapeInput of Email, surveys, etc Through Attensity AdaptersAttensity 5 RepositoryAttensity VOC DiscoverReporting Repository
DemoAttensityListen across customer conversation channelsAnalyze accurately and efficientlyRelate this information to other informationAct on the informationWe call this the LARA methodology
Attensity Respond: Scalable, Automated Routing & Response Tracking for All Customer Communications and ChannelsResponseManagementResponses can be reviewed by agent before sendingHotel hardship refund policy? Email“hardship refund” email response auto-generatedRouted to Customer Service for Follow-up and ResolutionService issue tweetAttensity “reads” text and extracts knowledge about what the doc is sayingPeoplePlacesEventsTopicsSentiment …Automatically routed to legal for reviewThinking of suing posting
For example, here you can see a unanswered “cry for help” being routed to a customer service agent for response. They can see the message, and can click to respond quickly.
Here’s an example of an intent-to-purchase being routed to the sales department. Collaboration features enable multiple people to work to solve the customer’s issues before sending a resolution message.
Within the system, you can also respond directly to the poster on the forum with a simple “click to post”. The system can suggest a response based on your corporate knowledgebase or you can create a response on your own.
ListenAnalyzeRelateActWelcome to the Open Enterprise
A Few Words About AttensityOver 20 years experience understanding customer conversations in text; 6 patents in natural language processingSuite of applications for Social Media Monitoring, Customer Analysis, Response Self-Service/Agent Service and ResearchOver 500 installations worldwide
LondonAntwerpParisGermanyZurichPalo AltoSalt Lake CityWashington D.C.Global Coverage and Strength

TWTRCON NY 10 Real-Time Tools: Attensity | Maria Ogneva

  • 1.
  • 2.
    Thank You toOur SponsorsANCHOR SPONSORSPLATINUM SPONSORSRESEARCH SPONSORRECEPTION SPONSORGOLD SPONSORSSILVER SPONSORSPlease visit our sponsors and exhibitors during the breaks!
  • 3.
    Real Time ToolsMini SessionMaria Ogneva, Director of Social Media, Attensity| @themaria | @Attensity360
  • 4.
    Attensity360 Overview forTWTRCONJune 14, 2010
  • 6.
    Over 10 billiontweets so far.
  • 7.
    Over 20% oftweets concern products and brands.http://live.psu.edu/story/41446
  • 8.
    There are over200,000,000blogs34%of bloggers post opinions about products and brands
  • 9.
    The ProblemUntil now,“social media” applications have been largely focused on collecting and tracking customer conversations and leaving the rest up to individuals to do.Manually analyze for deeper analysisManually route and respond to individual conversationsManually add gleaned knowledge to company knowledgebasesThis approach is not scalable for the enterprise….
  • 10.
    DemoAttensityListen across customerconversation channelsAnalyze accurately and efficientlyRelate this information to other informationAct on the informationWe call this the LARA methodology
  • 11.
    The Social CustomerWhois talking about me?What do they think about my company?What problems are they having?What do they like about me vs. the competition?What new ideas do they have?Who is thinking of switching?Who is ready to buy?11
  • 12.
    Easy setupProximity operatorsfor recall and precision balanceEntities help disambiguate queries
  • 13.
  • 14.
    View tweets, posts,news, etc. on a specific topic…All in one placeDisplays impact, reach, sentiment for each postSort by date, impact, reach, or sentimentAttensity360
  • 15.
    Prioritize Twitter outreachwith user metadata and influence metrics.
  • 16.
    Integrated EngagementView fullpost and assign for follow-up;Integrates with mail programs
  • 17.
    Attensity360: Top InfluencersReportsSee where people are talking about you
  • 18.
  • 19.
    …and what theyhave to say
  • 20.
    See the mostcommon terms in conjunction with your topic
  • 21.
    Click to viewall posts on that topic
  • 22.
    DemoAttensityListen across customerconversation channelsAnalyzeaccurately and efficientlyRelate this information to other informationAct on the informationWe call this the LARA methodology
  • 23.
    Attensity Analyze: Deeper,Cross-Channel AnalysisExtracts key entities, events, relationships,actions, purchasing reasons, intent and sentiment
  • 24.
    DemoAttensityListen across customerconversation channelsAnalyze accurately and efficientlyRelate this information to other informationAct on the informationWe call this the LARA methodology
  • 25.
    Listen, Analyze, Relate,Act: Data FlowsBroad Web CoverageThrough Attensity360Attensity AnalyzeServerDeeper Dive Web Through Attensity ScrapeInput of Email, surveys, etc Through Attensity AdaptersAttensity 5 RepositoryAttensity VOC DiscoverReporting Repository
  • 26.
    DemoAttensityListen across customerconversation channelsAnalyze accurately and efficientlyRelate this information to other informationAct on the informationWe call this the LARA methodology
  • 27.
    Attensity Respond: Scalable,Automated Routing & Response Tracking for All Customer Communications and ChannelsResponseManagementResponses can be reviewed by agent before sendingHotel hardship refund policy? Email“hardship refund” email response auto-generatedRouted to Customer Service for Follow-up and ResolutionService issue tweetAttensity “reads” text and extracts knowledge about what the doc is sayingPeoplePlacesEventsTopicsSentiment …Automatically routed to legal for reviewThinking of suing posting
  • 28.
    For example, hereyou can see a unanswered “cry for help” being routed to a customer service agent for response. They can see the message, and can click to respond quickly.
  • 29.
    Here’s an exampleof an intent-to-purchase being routed to the sales department. Collaboration features enable multiple people to work to solve the customer’s issues before sending a resolution message.
  • 30.
    Within the system,you can also respond directly to the poster on the forum with a simple “click to post”. The system can suggest a response based on your corporate knowledgebase or you can create a response on your own.
  • 31.
  • 32.
    A Few WordsAbout AttensityOver 20 years experience understanding customer conversations in text; 6 patents in natural language processingSuite of applications for Social Media Monitoring, Customer Analysis, Response Self-Service/Agent Service and ResearchOver 500 installations worldwide
  • 33.
    LondonAntwerpParisGermanyZurichPalo AltoSalt LakeCityWashington D.C.Global Coverage and Strength

Editor's Notes

  • #7 Catherine
  • #8 Catherine
  • #9 Catherine
  • #12 Because it’s document-centric and relies on keywords, it’s hard with search to get the big picture. How can you look at a set of search results and get answers like “what do people think about my company?” “What problems are they having”? What do they like about me vs my competition? What ideas do they have? Who is thinking of switching and so forth. It’s a very manual process.
  • #24 All of this analysis should be available to you in a rich, graphical environment that lets you explore sentiment and top issues as easily as you can report on sales figures today. So, for example, not only can you see that the top complaints about your hotel are that your hotel is dirty…. It reads through documents, extracts the key entities, relationships, and sentiments from that text, and then gives that text a unique barcode of all of that information that can be used in downstream operations.Text analysis extracts the Entities (brands, people, locations, times, products…) from that sentence, so you can do things like report on how many people are posting about Gucci scarves.Attensity also extracts actions, purchasing reasons, and sentiment…I first bought a Geico policy for my son16 years ago. He really likes the service he’s received, but he ended up cancelling his policy because he decided he didn’t like owning a car now that he lives in San Francisco.Entities (brands, people, locations, times, products…)Events and relationships: action and purchasing reasonSentiment (extreme positive, positive, negative, extreme negative) related on a clausal level[Attensity also can relate the “she” in the second sentence to “mom” in the first : this is called anaphora resolution]I first bought a Geico policy for my son5 years ago. He really liked the service he received, but he ended up cancelling his policy because he decided he didn’t like owning a car now that he lives in San Francisco.I wishGeico offered home insurance policies too. IfGeico offered home insurance, I would buy it in a heartbeat.Entities (brands, people, locations, times, products…)Events and relationshipsSentiment (extreme positive, positive, negative, extreme negative)Suggestions (in this case, one that should be followed up with a sales call!)Intent (to purchase, to leave)
  • #30 Here’s an example of an intent-to-purchase being routed to the sales department. Collaboration features enable multiple people to work to solve the customer’s issues before sending a resolution message.