SentiMetrix offers Good Publicity…for a Price
July 21st, 2010We need positive word of mouth about our products, services, and even political candidates if we are to win in the marketplace or at the polls November 2nd.
To make it easy, SentiMetrix has, for a limited time, a $29/mo feed for your website. You’ll get news and social media posts from over 70,000 sources that have favorable comments or reviews toward your brand.
For those unfamiliar with the science behind the art of good PR, here is an explanation of how Sentiment Analysis Technology can add value your brand
What Sentiment Analysis is and does
Sentiment Analysis is a form of qualitative measurement using a combination of natural language processing and statistical algorithms in a textual medium.
Opinions toward objects (nouns or noun groups) selected by the user can be measured over time to determine whether that object is becoming more or less favored by a particular audience and why.
Presently, Sentiment Analysis technologies are used to measure positive and negative opinions and the degree of change. This can be particularly useful to any brand dependent on word of mouth advertising, and will give your brand the opportunity to promote itself by highlighting the positive reviews it is already receiving. Over 70,000 sources are analyzed to deliver twice daily updated positive reviews about your company, product, candidate or service. An RSS feeds with clickable URLs back to the original source are provided to ensure authenticity of posts.
Additional Services: SentiMetrix™ gathers open source opinions and has several years of archives of news and blogs for historic positive to help you analyze trends. SentiMetrix™ can also process your data sets or message boards on a local or national basis to provide qualitative analysis on an extremely granular level as to what an audience is thinking and wants.
For more information, contact Laurel Earhart, Vice President of Business Development at SentiMetrix: 520-390-1421. Or email her at Earhart@SentiMetrix.com
Resting on Laurels
April 17th, 2010
Now that I’ve had a chance to kick off my high heels, here are some of my reflections and observations based on the Sentiment Analysis Symposium aka #SAS10 that took place April 13, 2010 in NYC.
An Introduction
I am sitting in a room full of people I realize would have creamed me on the SATs in high school.
I am sending fawning, swooning appreciative texts to my engineers back home because I actually get what they are doing on a much deeper level and realize we’ve nailed some of the issues I was concerned about.
They text me back and ask what I am smoking.
My colleague, Bob Valeiko, confides… “It’s not like ‘absent that day’ missed it… some of the stuff I heard them talking about last night at the cocktail party was really weird!
How so?
He showed me a business card that had some dots on it connected by lines. “Do you have any idea what this is?”
I don’t.
“It’s a protein molecule. This guy was talking to Leslie (Barrett) about it, and she jumped right in, knew what it was. She said ‘Oh yeah, and you put it in a vector…’
They start getting into it and I have absolutely no idea what they’re talking about.”
Welcome to Seth Grimes’ Sentiment Analysis Symposium in New York.
Or, for those of us who went through base camp together: #SAS10.
Who was there? Four categories:
1. Research Scientists & Students
2. Press & Bloggers
3. Sentiment Analysis tool & service reps SERVING the SA industry (yes, folks, there is a subcategory. I guess that means we’re official.)
4. Clients & Consultants who use Sentiment Analysis tools.
At one point I quipped to Seth Grimes, (via Twitter, of course):
…Loving the #SAS10 conference, the IQ in this room is in the stratosphere… But have you seen the movie “Best in Show”?
For those of us with non-stratospheric IQs, here are five takeaways from the conference & five things we’re doing to move the industry forward.
The five main points:
1. What is Sentiment Analysis actually for? It’s to look for outliers. An analyst should NOT use Sentiment Analysis on its own and expect to find all the answers. She should look for spikes as indicators. For example, Apple’s sentiment rose and fell based on the release of the iPad. A ‘blip’ should be a signal to ‘look here’ and find out why the change happened. Sentiment Analysis in and of itself is useless without a human to interpret and make the result actionable.
2. Machine based sentiment analysis will never nail correct sentiment 100% of the time…and that’s perfectly NORMAL. In any given situation, human beings don’t consistently agree as to whether something is positive/neutral or negative/neutral and occasionally positive/negative. The generally accepted standard is 82%, meaning: between human beings, there will be 82% agreement on determining whether sentiment expressed toward something (positive, neutral, negative) is the same. Machines won’t do any better than the human standard.
3. We’re in the wild west: we’re all using different terms and standards. Just as in the days of early internet advertising, of which I am a proud veteran, we have problems with everything from being able to describe what a score is to claims of x% accuracy. Just what does it all mean?
4. Different kinds of Sentiment Analysis exist: Counting adjectives is what I originally thought this industry entailed. And that may be fine for certain applications. But Natural Language Processing, & Statistical Analysis & Artificial Intelligence (NLP&SA&AI) give you much better shades of nuance. We understand which types of methods work with which kinds of data, and therefore which may be a better application for which industry. And this is NOT an easy business, nor is it easy to build from scratch, hence the love letters to my confused but grateful engineers. I wholeheartedly agree with the principle of being able to kick the tires and try before you buy. On that note, to try something today, I invite you to go to www.Sentimetrix.com and register for a free account (to the right of the graph); play with it on your own or request a demo and I’ll walk you through the less obvious features. We’re trying a few new things and would love your feedback.
5. SA currently rocks a few core industries: financial, pharma, reputation management. Make no mistake, if you are in these industries, you simply HAVE to have this technology now or you will be toast. Each industry has its own particular requirements (i.e. speed and accuracy in financial, broad reaching ‘we don’t know what we’re looking for yet’ in pharma). My prediction on the next ‘must have’ industry? You guessed it: politics.
The five big things on the horizon:
1. Battle of the Bands (not!): Matthias Tyrberg of Saplo proposed side by side testing of the vendors to let us duke it out. Or, as Nathan Gilliatt enthused, “It’s Thunderdome. Two go in, one comes out.” Seth Grimes wisely talked us down, insisting there could not possibly be a fair competition because of tuning requirements.
However… What do you think about a a Sentiment Analysis petting zoo for vendors at next year’s symposium?
2. Extraordinary research by some of the finest minds in the space: I am very excited about the opportunity to bring back ideas to my technical team such as Shlomo Argamon’s automated authorship profiling (gender, age, native language, education level). I’m giddy to think of how this will yield results in the elections space. My new friend Leslie Barrett talked about polarities beyond positive and negative: i.e. sweet vs sour, hot vs. cold. We have a prospective client asking for just that, and because our engine is language agnostic, I’m eager to test her premises against a multinational backdrop(what is ‘hot’ in terms of taste compared to ‘mild’ may differ considerably from country to country).
3. Call for standards in the industry: It feels like we need something in this space. Matthias Tyrberg and I raised our hands to start feeling our way forward and figure out what needs to be defined. I am so thankful to have met Marshall Sponder at the conference and to be able to learn from his experience in the web analytics space. Do you want to participate? Do you have any suggestions? Respond to this post and we’ll get started.
4. Foreign languages: This is an urgent need. And the methodologies differ greatly. I predict this is the space where we will see the most development in the next year.
5. Consolidation: This conference was very open and friendly. There was no 500lb gorilla in the room to be afraid of. We’re all pioneers and there is room for everyone. For now… but on the horizon we see Google. Microsoft. IBM (and yes, they were there.) True giants in the space are now turning their eyes and patents in our direction. Microsoft is expected to launch a service in six months. Seth seemed to know a bit about it and said we are in for a surprise. I think as we all looked around at each other, the feeling was: Today, competitors, tomorrow, collaborators or even, …ahem, …subsidiaries? Be nice to everybody.
I glance back at Seth. He’s tweeting, but I haven’t seen a reply to my snarky comment.
I look around at the 90 or so people in the room and realize that next year’s symposium won’t be quite so intimate; the field is booming. And Seth has been a huge part of our collective success. He has been a tremendous advocate for us. He’s generous with his time, contacts, and advice. We’re lucky to have him and this conference in a class by itself.
My best in show comment got a retweet. And of course, I want to do an air punch “YESsssss!” OMG, I got retweeted by Seth Grimes!!! ::psych::
Then I look back at my own comment. I slap my forehead. I feel like I have become one of the totally neurotic characters in “Best in Show”. (http://www.imdb.com/title/tt0218839/)
Woof.
Laurel Earhart is Vice President of Business Development at SentiMetrix, which offers Sentiment Analysis tools and services to industries that require highly granular, extremely high speed, multilingual capabilities. The company was developed out of a project to serve the DOD following an incident after 9-11 and now offers its services to clients inside and outside the beltway. She can be reached at earhart@Sentimetrix.com. Or follow her on Twitter - she tweets from SentiMetrix.
What Does a Sentiment Analysis Score Mean?
April 8th, 2010By Laurel Earhart
The most frequently asked question pertaining to Sentiment Analysis is: What does a score mean?
Sentiment Analysis engines measure opinions in social media online or in textual sources such as news and journal articles.
A single score, in and of itself, means nothing. To understand the value of the score, one must understand the system it is built upon. Here are five issues to consider:
1. A Sentiment Analysis system has a “scale” or, the absolute highest or lowest value of a descriptive term pertaining to an object in question. Simply knowing that something scored a “.25” means nothing if you don’t know if the scale of scores was from -1 to +1 or from 1 to 10.
2. A Sentiment Analysis system requires the ability to understand “velocity” or how sharply sentiment is changing over time. This allows a researcher to identify tipping points and hone in on the events that triggered changes in sentiment. Again, if something’s scored a .25 for the last week, but prior to that it had been rising sharply, that signals something has happened to level off rising public opinion.
3. Sentiment Analysis system requires the ability to demonstrate “relativity”, or, how sentiment has changed over time, is different between sources, or between objects. It allows the researcher to determine, for example, if blogs or news are more favorable to a particular political candidate, and whether that candidate should spend more time on interviews or on her social media campaign. By contrast, some systems may have “normalized” scores, so 0.5 means something like “half the mentions were positive”. Understanding what a score is relative TO is extremely important.
4. A Sentiment Analysis system should provide “granularity” – how subtle a shift can be detected? Does the system provide “positive – neutral – negative” rankings or a more sensitive analysis? If something declines from .8 to a .25 it is still positive, yet it represents a sharp decline.
5. A Sentiment Analysis system has “accuracy” – who decided these were the scores, anyway? Many systems were designed to replicate human scoring as closely as possible, and tested against human subjects in a variety of applications. SentiMetrix was tested at the University of Maryland and was determined to be comparable to human scoring. It was also similarly tested in government applications. If a system is not designed to replicate human scoring, what exactly is it designed to do?
Trying to figure out a score without understanding the system is like trying to figure out which way is North without a compass or any earthly cues.
Once the system is understood, then the scores make sense.
Five Reasons Political Candidates Need Sentiment Analysis to Win in November
March 7th, 2010My colleague, Todd Herman, of the Republican National Committee said it best:
“Polls are like watching animals in a zoo. You can obtain perfect specimens, observe them from every angle, but then you wonder why they aren’t mating.
Sentiment Analysis is like watching those animals in their natural habitat.”
I think we all have a lot to learn from this statement.
Polls are important, but as you’re developing a social media strategy, consider what sentiment analysis can do for you to win in November.
1. Track virtually real-time opinions in traditional and social media about what people are saying about YOU and your opponent.
By watching trends over time, you’ll know soon whether your education policy or your courtesy in the face of mudslinging is giving you an edge. In fact, good scoring techniques allow you to see which terms associated with your name are giving you that edge.
2. Understand that there is more to Sentiment Analysis than a “positive-negative-neutral” score. The more granular the scoring, the better the opportunity to shore up a campaign against negativity or to capitalize on an opportunity. Granularity matters. Would you rather know that people have a positive opinion about you? Or that last night it was +.61 and this afternoon it is +.42. Both are still positive scores. But now you know there might be a problem.
3. Is there a believability gap between traditional and social media? Does the press hate you and love your opponent?
Do the social media measurements trend the same way? Knowing the answers to these questions will tell you if you should be buying more ads, talking to reporters, kissing babies or… maybe even keeping your day job.
4. Have you discovered something you want to share?
Syndication of charts comparing and contrasting you and your opponent, specific issues, and social media or traditional media is now possible! You can email a chart, publish it on a web page or on Facebook, or send it off to the Twittersphere.
5. Mobilize your volunteers: What issues do they care about?
You do support those issues, right? Now your volunteers can champion you and their pet causes through these social media sharing tools and be part of a viral marketing campaign for you, all the while generating publicity for your campaign.
These tools are free. Just go to http://tinyurl.com/sentimetrix-elections
and register for a new account to get started. Type in the name of a politician and toggle between blogs and news or both to see what’s news. You may want to start with “Obama” as there is more data and issues about him than anyone. Then click on any of the “ancillary” issues on the left to see how those issues are trending.
Laurel Earhart is Vice President of Business Development at SentiMetrix and is the former Director of Business Development of the News and Politics channel at America Online, Inc.
New Year, new launch
January 6th, 2010With all the hoopla around the mythical Apple tablet and the marginally more useful Google phone, only the real social media connoisseurs have noticed that they can now register for free accounts on www.sentimetrix.com.
Let’s spread the word - we are live!
A 1-minute registration is all you need to access SentiGrade (c) sentiment charts. Explore the topics that interest you, compare scores for different brands, products, celebrities… go ahead! Satisfy your curiosity! There is a lot of data behind these charts, coming from over 50,000 traditional and social media sources, so it is likely that we have an answer to your query. And we add more sources every day.
As the year progresses, we’ll be rolling out new features: - widgets, RSS feeds, alerting capabilities, advanced analytics and reporting, additional languages, open API and more. But first - we want to know what you think. Drop us a note and tell us what you like and what you want, and, what additions would, in your opinion, make the site more useful.
Do you have an great idea for using sentiment data? Share it, and let’s make it a reality together.
2010 is the year of sentiment. SentiMetrix invites you be a part of it. Welcome aboard!
SentiMetrix team.
New Jersey and Virginia: Tuesday is the day
November 3rd, 2009New Jersey: Sentiment for Governor Jon Corzine (D) is higher by a razor-tight margin in a close race with Chris Christie (R) and Chris Daggett (I). The battle for NJ continues even on the last day before the elections.
Corzine up by a razon-thin margin
In Virginia, sentiment for Governor Bob McDonnell (R) is trending higher than scores for Creigh Deeds (D).
Deeds vs McDonnell
SentiMetrix recently expanded its data set to include a larger number of news and blog sources to capture a broader array of opinions pertaining to these important elections.
Voter and Media Sentiment toward Daggett still strong
October 24th, 2009By Laurel Earhart
In the past few days, Chris Daggett’s Sentiment Scores have improved considerably in the media and in blogs due to voters expressing their strong support for Daggett and dissatisfaction with their other candidate choices.
Voter and Media Sentiment toward Chris Daggett relatively positive in the last few days
Voter Sentiment toward Corzine Improves, Chris Daggett added
October 20th, 2009By Laurel Earhart
In response to a request from a reader, we have decided to begin tracking Chris Daggett in our Sentiment Analysis trend charts in New Jersey. The race appears close again in Virginia, where McDonnell and Deeds sentiment are very similar.
Deeds improves in Virginia, New Jersey race still close
October 17th, 2009By Laurel Earhart
Sentiment toward Deeds improves largely due to discussion about Obama coming to Virginia to campaign for him. In New Jersey, Sentiment toward Chris Christie remains relatively unchanged while sentiment toward Corzine decreases somewhat into negative territory for the first time in days. This is largely due to the candidates’ performance on the debates held on the 16th.
Would you like to learn more about how our tools work? Email me at laurelearhart@aol.com for details and information on our twice weekly online tutorials.
NJ and VA Governor Candidate Sentiment Trending Similarly
October 16th, 2009October 16, 2009
By Laurel Earhart
As the days leading up to the November 3rd election grow shorter, we’re seeing similar sentiment of voters and media toward each candidate. As our results are continuously updated, we will provide examples of blogs and news stories that validate this trend. There are several mayoral elections happening on November 3rd as well, if you would like to see us track these, please email me at Earhart@Sentimetrix.com
Blog
Opinion Tracking in the Web 2.0 World
Opinion Tracking in the Web 2.0 World
The world has fundamentally changed as the Internet has become a universal means of communication and the dominant force in advertising and brand management. The blogosphere is a huge “echo chamber” for individual opinions and online social networking is influencing every aspect of life. Word of mouth marketing is increasingly driving purchasing decisions, brand loyalty and customer attitudes. The Internet contains a wealth of data that can be mined for valuable opinions – with implications for companies and national security agencies alike. Web 2.0 companies need to better leverage and monetize the huge volume of opinions expressed, successful product companies must constantly monitor where they stand online and government agencies need better tools to tap this valuable source of intelligence data.
SentiMetrix software enables companies to analyze and capitalize on the explosion of individual opinions expressed online — in traditional and new “social media” sites, blogs, online discussions, customer generated ratings, etc. SentiMetrix provides precise, real-time quantitative data on user opinions. The system’s highly accurate sentiment analysis engine leverages patent pending algorithms that have been independently validated. SentiMetrix software provides precise sentiment scoring, attribute level opinion analysis and supports nine languages.
