This week, we released OpenAmplify Version 3.0, which we like to call “NLP in HD” and here’s why…
Priority one for OpenAmplify has always been to bring out more meaning from text. We go deeper into the meaning of conversation by pulling out more dimension and color—sentiment, intent—and now, descriptors.
Firstly, we always orbit around the topic by telling you which are the most important in the conversation. We build sentiment on that--how do the commenters feel about the top topics. And now with v3.0’s Topic Descriptions, we can add how they describe the top topics when expressing their love or hate. Topic Descriptions is the important “why” dimension of the social conversation because it shows you what is contributing to positivity or negativity.
Let’s say you were running a chain of restaurants. A treemap created from OpenAmplify data of the social conversation around your establishment might look like this:
Cool, right? It’s a very useful snapshot of what is stirring up the conversation. Logically, your next burning question would be: Why are people are so positive about the topic dinner and negative about service?
Why do your customers love dinner and hate service?
Thanks to v3.0’s new Topic Descriptions signal, no social media professional will have to die of curiosity . Let’s look at a breakdown of what customers are saying, in their own words:
With these Topic Description insights, you have the right ingredients to create your next promo, develop your new creative or craft your staff training so you can keep serving up what your customers love about you…a romantic dinner spot, sans rude wait person.Want to learn more about OpenAmplify v3.0? Easy-peasy, just drop us a request here (be sure to pick “Insights API”).
Sometimes, I really wonder. The concept of Sentiment Analysis is so obvious and so useful, and yet people who experience these technologies often seem to be left with an overwhelming smell of snake oil. Huh? How did we get this result? What’s happening? Why?
At OpenAmplify, we’ve never subscribed to the ‘mystery box’ approach. We have always presented sentiment data in the context of a TOPIC. The way people talk is inherently complex, and we think it’s really important to understand what sentiment applies to which topics. Think about it:
In this case, you need to understand that...TOPIC: iPhone = good TOPIC: battery = bad
Aggregating this positive and negative to some sort of neutral score is, literally, meaningless.
Transparency is key. Confidence comes from understanding the what, and the why. And that’s why we have taken the next step with our latest API release, OpenAmplify v3.0. With our new Signal called TOPIC DESCRIPTION, you are now able to see which words have caused the sentiment scoring. For example, in the previous quote, OpenAmplify will now tell you that:
TOPIC DESCRIPTION lets you understand what is actually driving the positivity and negativity. Across potentially millions of comments per day, you can understand how people describe your products. How they actually and naturally talk about them. No more guess work. No more mystery box.
Sentiment analysis will never be perfect, but we are making strides every day to improve precision with transparent data you can use. Τέλειος ;-)
We’re pleased to announce the general availability of the newest release of our best-of-breed natural language processing (NLP) and text analysis (TA) platform, OpenAmplify Version 3.0.
Building on our strength in topic-level sentiment analysis, OpenAmplify Version 3.0 includes unique new capabilities for large scale, commercial applications. Major enhancements and improvements include:
- Topic Descriptions Signal - Exposes how topics are described in conversations and comments across social channels. Surfacing the descriptors and adjectives attached to topics and sentiment helps to answer why they love your brand. For example, a positively regarded topic “phone” might have references to “cool” or “dependable”. Topic Descriptions allows marketers to check for alignment between their brand messaging and the unvarnished voice of the social customer. For product developers, it can be a tool for discovering which product features and attributes are missing the mark and driving negativity.
- Co-Referencing “It” – OpenAmplify has been the pioneer in linking multiple sentences via pronouns, without which sentiment and other signals cannot be as accurate. Version 3.0 cracks the linguistic challenge of linking the pronoun “it” to the correct topic. Unlike the pronouns “she” and “he,” “it” is notoriously difficult to properly associate with a topic. For example, “I went to a new restaurant. It was great” versus “…It was raining.” Being able to properly link “it” improves accuracy in weighting of topics across millions of conversations.
- Social-grade improvements spanning four areas: 1) the range/depth of the analysis; 2) the quality/precision of the analysis, 3) speed of processing and 4) The ability of production systems to aggressively scale to meet demand.
Users of version 2.1 may upgrade to version 3.0 by simply altering the AmplifyWeb_v21 reference in their OpenAmplify URL to AmplifyWeb_v30. No other changes are required. Full documentation on OpenAmplify Version 3.0 features is available here.
Supported OpenAmplify Versions starting today March 12, 2013:
We will continue to offer support for the current version of OpenAmplify and the one previous version:
Discontinuation of OpenAmplify version 2.0
OpenAmplify version 2.0 is discontinued and will no longer be supported. Users of version 2.0 may upgrade to version 2.1 by simply altering the AmplifyWeb_v20 reference in their OpenAmplify URL to AmplifyWeb_v21. No other changes are required.Technical Support
For more information, please contact firstname.lastname@example.orgNew to OpenAmplify? Welcome!
Grab an API key and build something your customers will love with OpenAmplify Version 3.0!
OpenAmplify’s was invited to guest blog for Salesforce Marketing Cloud this week. Check out this post via the link below and join the conversation!
We'd love to hear from you. If you'd like more information on OpenAmplify conversation analysis or our offerings on Salesforce Marketing Cloud: OpenAmplify Insights and OpenAmplify Customer Service, please contact us for a demo. Thanks!
The OpenAmplify team just got back from a hectic week at Dreamforce 2012 and here are some reflections from Mark Redgrave, OpenAmplify CEO.
Dreamforce gets bigger and bigger every year. Now 90,000 attendees strong, it’s the largest tech conference on the planet. With so many great people and great companies under one roof for three days of mayhem, it really is an amazing experience.
One of the biggest pieces of news this year was the announcement of the new Marketing Cloud. This perfectly complements the existing Sales and Service Clouds, and completes the ‘set’. Salesforce’s mission is to be the one-stop-shop for the enterprise, and they are doing a pretty impressive job of giving companies the tools they need to succeed in this social world. Although Radian6 has been onboard for 12 months already, Buddy Media was only acquired three months ago...so this new product suite has come together in super-quick time. Pretty incredible. As a founding partner of the Radian6 insights platform, OpenAmplify has a key role in the new Marketing Cloud. As Marcel LeBrun demo’d in front of a huge audience on Thursday, OpenAmplify’s data is key to automating marketing processes: like automatically identifying product advocates from the flood of social brand engagement, so those individuals can automatically be rewarded and then automatically added to social outreach programs to expand campaign reach. Advocates promoting brands. Automagically. Powerful stuff.
Marketing Cloud is just getting started. “Keep your arms inside the car and hold on to your seats” ;-)
OpenAmplify’s partner Visual Intelligence was recently featured by analytics giant TIBCO Spotfire for their mash-up of our advanced NLP and text analysis with the Spotfire platform for data visualization. The result of this mash-up is SocialView—a tool that speeds time to insight and makes self-exploration of conversation analysis possible like never before.
“The collaboration between Spotfire and OpenAmplify is a perfect match,” says Cristian Ilie, Founder and Chief Innovation Officer, Visual Intelligence. “Both companies have very deep analytic experience – OpenAmplify with its ability to make sense of social media conversations and Spotfire, with its very innovative ways to consume and analyze unstructured data.”
Our clients rely on us to dig deeply into the meaning of millions of online conversation and text. And now with SocialView, they can see, explore, and measure their conversation data to answer precisely how social is impacting their brand. Cristian and his team set out to design a tool that allows for dynamic and flexible self-exploration of social data. They leverage all the meaning data we provide so you can slice, dice, and consume the social conversation analysis the way you need to. With SocialView, you can drill down into the data as you wish to get at tangible measures--quantitatively and qualitatively.
How we used two social-grade tools to measure, benchmark the impact of social on a major automotive brand
What would you do with 17.9 days?That’s how long it would take to read 15,108 comments to a popular Chrysler ad online. For over three workweeks, your full-time job for seven hours a day would be reading, non-stop. You would have 30 seconds per comment, then you’d have to go back to understand, analyze, and make sense of it all. Thankfully, we didn’t have to do that to answer these two important questions: What was the impact of this social video on the brand? Did the creative strike a chord? Check out this presentation: Introducing SocialView: Super Bowl 46 where we share with you how we helped to answer those two questions. You'll hear:
- An overview of Metrics that Matter™ for understanding the impact of social on your brand or campaign
- A fly-by of two social-grade tools used in this case study: 1) OpenAmplify Reactions for data collection, tracking, and measurement of on-site and off-site social engagement; 2) SocialView™ for analytics and data visualization of Awareness, Preference, Intent, and other key social metrics
- How OpenAmplify is Making Sense of Social™ using its advanced natural language processing (NLP) platform so you can measure ROI and benchmark the performance of your social campaigns
Using these advanced tools, 15,108 comments were automatically processed for understanding to put powerful key metrics at your fingertips. Now, you can do something strategic and creative with your 17.9 days.
If you'd like to learn more about how you can use OpenAmplify Reactions and SocialView™ to track and measure your social campaigns, please get in touch. Whether you want to analyze engagement on your Facebook brand pages or conduct sentiment analysis on social assets like Twitter hashtags or even analyze a competitor's YouTube campaign, we can help. Talk to us; we'd love to hear from you!
The way we talk is both beautiful and messy, because people are quite inventive communicators. New words are constantly emerging, just as old ones fall out of use. So there’s really no point in trying to list all the words in the entire English language. (But in case you were interested, the Global Language Monitor estimated, for January 1, 2012, that there are 1,013,913 words in the English language…and counting.) To find out how OpenAmplify keeps up with changes in the English language, I chatted with Alexandra Stålnacke, OpenAmplify’s Director of Linguistics. This is how she summed it up:
Language is alive and forever changing. Every year about 25,000 new words are introduced into English. To keep up with its evolvement, our linguists do daily updates to the resource files that support the text analysis system in the core of OpenAmplify. So, based on lists of known words, endings and entities, and the context they appear in, OpenAmplify can correctly recognize an innumerable set of words we use today, plus ones that have not yet been “invented.”
For the task of daily additions, we’ve examined how language users instinctively follow specific rules when being creative in their forming of new words and expressions. We take people’s lead to find new words or phrases that evolve naturally. The OpenAmplify discovery process makes it possible to catch the correct part-of-speech of an unknown word, based on its textual context and its ending.
For example, you can most likely guess that a made up word “grubbly” is an adjective, used to describe a person, place, or thing. Or that “klomping” is most likely—but not necessarily—an action word. OpenAmplify’s engine examines its context:
- The boys have been klomping all day - most likely a verb (an action word)
- My new car has a beautiful klomping - quite probably a noun (a thing)
So as alive as the English language is, OpenAmplify’s NLP and text analysis engine is built to keep up with this dynamism. And that's a beautiful thing.
Listen in and chime into the conversation this Thursday, Feb. 23. 2PM EST during a webinar hosted by our friends at Radian6, a Salesforce company. OpenAmplify's CEO, Mark Redgrave has been invited to join this panel to discuss what's next in the rapidly changing social listening space. Mark will be speaking more specifically about how OpenAmplify's NLP engine delivers unique insights on "intent" which what your social customers express about how they want to engage with your brands and products.
For more details and how to register, please see below.
The Evolution of Social Media Monitoring: Integrating Deeper Intelligence into Listening Solutions
View it here!
Mark Redgrave, CEO, OpenAmplify
Dana Martin, Supervisor, Social Media, McDonald's Corporation
Andrew Grill, CEO, Kred
Host: Genevieve Coates, Radian6 Community Manager
Social Monitoring has evolved beyond volume and trends, even beyond simple sentiment analysis. The next generation of social media monitoring involves enhancing conversations with meaningful insights – on the authors, sources, and content itself – to get even more value from the social web. Join Radian6 and some of our partners for an online roundtable discussion on how innovative social data is helping organizations like yours overcome real obstacles. OpenAmplify, the market leader in natural language processing and semantic web analysis, will discuss how computers can mimic human understanding of language and even recognize subtleties like people’s intentions. Kred, a sophisticated social scoring system, will explain how someone’s ability to inspire action online can be married with “real life” for a more complete representation of influence. All that and much more in this 1-hour webinar on February, 23rd at 2pm ET. Sign up now to learn how revolutionary social insights like these can help you make more sense of social conversations and redefine what social media can bring to your business.
We recently completed an analysis, in collaboration with Kantar Video, on social conversations around Super Bowl game-day commercials. For OpenAmplify’s contribution, we focused on one of the largest category of advertisers: automotive. As part of their annual study on what’s dubbed as “Big Game Advertising,” Kantar Video examined online video viewership and social activity to determine earned media value. Building on important viewership metrics, a closer look at what people are actually saying about the commercials seemed like the logical next step. What could we learn through these conversations and how do they inform the creative process for next year’s round of commercials? To find out, we dove into the conversations using SocialView, a new and powerful data analysis tool that has the full force of OpenAmplify’s NLP engine under its hood (automotive pun intended).
Through SocialView, we were able to see plainly how consumers naturally referred to products and brands, plus what the top associated topics of conversation were. We looked at a total of 36 themes among the six commercials. Some were obvious as intended by the advertisers—“Ferris Bueller’s Day Off” in the Honda commercial, for example. In other cases, a topic like “couch” or “sofa” bubbled up within the larger theme of Toyota’s “Reinvented” which contained several sub-themes in their vignettes. Kantar Video published a chart of top performers in the area of “Social Recall” by theme and a ranking of the six automotive advertisers in the order of their relative success at getting commenters to talk specifically about and mention their respective brands.
There certainly is a ton to learn by examining—at the topic level—the conversations generated by millions of views. As noted in a post by Trevor Wolfe of Kantar Video, discovering that the topic of “vampire” outperformed “Jerry Seinfeld” is informative for advertisers to balance investing in a celebrity with a compelling creative that resonates with their target audience. Now let’s look at the Chrysler ad, which did very well in the earned media ROI metric. But why were they last in the ranking for social recall of brand? The clue is in conversation. One of their commercial’s themes, “America,” was in the top five, reflecting the political slant of the majority of the conversations. Quite possibly that in a highly charged election year, taking on that theme was enough to sideline “Chrysler” as a topic, thus their ranking in the social recall by brand.
What do you think? Share your opinions, hunches or hypotheses around this year’s crop of Super Bowls commercials and we can go back to the comments to see how they play out.
Clearly, for businesses gone social, the pressure is on to measure the efforts and investments around it. This will be a hot topic at next week’s conference Socialize West (Oct 20-21 in San Francisco), which OpenAmplify is sponsoring. The conference has a terrific line up of speakers around the four themes: gamify, mobilize, optimize and monetize.
I expect loads of discussions around very social behaviors like playing (gaming), being on the go (mobile), shopping (monetization). At OpenAmplify, we're particularly interested in what people are sharing when they play, move/travel, and buy on the social web. And how we can help social businesses by making sense of it.
Watch this space for some nuggets from the sessions “Social Media: Harvesting Intent for Better ROI” and “Measuring Social Media Success.” I think I’ll also sit in on “Your Tweets Hurt my Facebook when I am LinkedIn: How to Monetize Social Media for Business Results”—which wins the funniest title award.