As Jason has reported before here, sentiment analysis is a tricky thing. Even humans disagree on sentiment 15 percent of the time, so how can a computer create something more accurate? As technology evolves, sentiment analysis gets better, or so we’d like to think.

I caught up with Seth Grimes recently. He is an analytics strategist with Washington, D.C.-based Alta Plana Corporation and a contributing editor at TechWeb’s InformationWeek. He is also perhaps the leading industry analyst covering text analytics. Seth consults, writes, and speaks on business intelligence, data management and analysis systems, text mining, visualization, and related topics. With such an expert on the subject with my reach, I asked him the following:

In layman’s terms, how would you describe/define sentiment analysis?

Image representing Seth Grimes as depicted in ...

Image by Seth Grimes / Alta Plana via CrunchBase

Sentiment analysis is a set of methods, typically (but not always) implemented in computer software, that detect, measure, report, and exploit attitudes, opinions, and emotions in online, social, and enterprise information sources. (As an aside, what makes it “analysis” is that you’re doing it systematically, with some goal in mind.)

I’ll add is that sentiment analysis much more than simplistically subtracting the number of “negative” words from the number of “positive” in a document or message in order to produce a score.

What does sentiment data and analysis mean for marketers and brands? Is it only about analyzing social media conversations or does it have broader applications?

Yup, it can involve social conversations and also direct and indirect feedback (such surveys, contact-center notes, and warranty and insurance claims), online news, presentations, even scientific papers: Any information source that captures subjective information.

Sentiment analysis lets marketers (and market researchers, customer service and support staff, product managers, etc.) get at root causes, at explanations of behaviors that are captured in transaction and tracking records. Sentiment analysis means better targeted marketing, faster detection of opportunties and threats, brand-reputation protection, and the ultimate aim, profit.

What role do companies like Facebook, LinkedIn, Twitter and Google play?

Interesting choice of platforms. Facebook and Twitter are major sources of sentiment (and also of complementary social connectedness data). Facebook and Twitter accounts have profile data attached to them, but nothing that matches the detailed, usably-structured information you can find on LinkedIn. Google is the ultimate information-access engine, capable of bringing together information from a huge variety of disparate sources, including sentiment information such as product, restaurant, and hotel ratings, although when corporations wish to find, mine, and exploit sentiment they need to turn to deeper BI and analytics tools.

There’s no one-size-fits-all sentiment solution, not Google or one of the several as-a-service solutions out there or any of the capable analysis workbenches or social-media analytics tools. Instead, there’s a whole spectrum of sentiment sources and analysis possibilities.

What are some of the most exciting break throughs that you are seeing in the technology or methodologies related to sentiment analysis?

Wow. First off, there are beyond-polarity solutions, which look at emotional categories — for instance, angry, happy, sad, frustrated, satisfied — that offer much greater business insight and usability than positive/negative/neutral scoring systems. And leading edge solutions are going beyond text, to detect sentiment in speech and even in images and video. On the methodological front, some of the best systems are linking sentiment with transactional records (sales, inquiries, payments, Web clickstreams), including with location correlation, to move us toward a world of integrated analytics.

Can you share an interesting example of a brand or organization has successfully used sentiment?

Let me point you to an article I wrote in February, 2008, where I profiled the use of sentiment analysis (by my friend Tom Anderson of Anderson Analytics) as one analytical component of “triangulation” strategy around the Unilever Dove-brand pro.age campaign. I quote Catherine Cardoso of Unilever in the article: “We were very pleased with the results and the depth of insight. The results were helpful beyond understanding reactions to our campaign. We also gained an understanding of what motivates people on discussion boards, which issues are most important to women in our target group, and how to create better products and messaging for them.”

In your opinion, what is the biggest obstacle keeping sentiment analysis from reaching its true potential?

Misperceptions, also inflated expectations, fostered by low-grade tools that are keyword based and lack any mechanism to link sentiment to actual business outcomes. On the one hand you get low accuracy, and further there’s a “decision gap.” You get a colorful dashboards, but because the tools are working in isolation, treating social and survey sources as information silos, you can’t reliably know what sentiment is important, and what sentiment really means to your business in the sense of driving transactions, boosting satifaction, and so on.

Companies like Radian6, (recently bought by Salesforce), SM2 and others have included sentiment as part of their social media analytics/monitoring tools for some time now. How will the future of the technology and method to using the data be different than what is available now?

Let’s name names. I was incredibly disappointed when I get an SM2 briefing from Alterian. I saw, earlier this year, primitive sentiment capabilities and analysis interfaces that resembled those of BI tools circa 2000. Check out what I wrote last March in an article, “What I Look For In A Social Analysis Tool.” There are other tools with similar, serious deficiencies.

Radian6, as an example, illustrates two routes forward. First, Radian6 provides a framework for plug-in of dozens of disparate extensions, including text and sentiment analysis from at least four different providers, AlchemyAPI, Clarabridge, Lexalytics, and OpenAmplify. This sort of openness and inter-operation is a benefits the solution providers and their customers alike. Second, the acquisition of Radian6 by Salesforce.com should further users’ ability to link customer-relationship data captured in Salesforce — profiles, transactions, interactions — with customer attitudes, emotions, and opinions, posted on-social and online and analyzed via Radian6, related to products and services offered by Salesforce customers and their competitors. This would mark the end of social as a silo.

What impact will mobile technology and the context that it provides (IE: location specific data) have on collecting and analyzing consumer sentiment?

Mobile creates the opportunity to solicit and collect feedback on the spot, at the point-of-service, and to understand peoples’ choices as they do whatever they’re doing. (Of course you have to consider privacy regulations and expectations.) And by collecting location and time data along with sentiment, linked to activities, you get additional analysis variables that can feed more capable, more accurate predictive models. Mobile is huge, in many, many ways.

You are one of the organizers of the upcoming Sentiment Analysis Symposium. Why do you feel an event like this is needed now? What are you hoping to accomplish?

The up-coming symposium, November 9 in San Francisco, is actually the third, following on April 2010 and 2011 New York events. The events are designed as a meeting ground for technologists and business users. They’re designed for education, for new and experienced folks alike, and to create networking and deal-making opportunities.

Folks should check out the Web site, sentimentsymposium.com, also the optional, pre-symposium tutorial (for people just getting started) and research session (for advanced users and developers).

How can people find out more information about how sentiment analysis is being used for business?

I’ve written quite a bit on the topic myself, and you can also learn from solution providers. Ask them for case studies and customer references. But I also recommend just taking a shot yourself. There are two factors that support this approach –

1) You’re working with natural language, with material you can understand directly, and it’ll be pretty clear whether the tools you’re trialing are doing a good job.

2) You have a variety of choices available including hosted, as-a-service solutions that can be used without a large up-front investment, also social-analytics and survey-analysis solutions that embed sentiment analysis without imposing a heavy technical burden on users.

I’m happy to field questions. Folks should contact me via Twitter at @sethgrimes at 301-270-0795 or grimes(at)altaplana.com.

—————

Use the code FOAF for a $100 discount your registration to attend the Sentiment Analysis Symposium on November 9th.

 

Enhanced by Zemanta

Did you enjoy this blog post? If so, then why not:Leave Comment Below | Subscribe To This Blog | Sign Up For Our Newsletter |

About Adam Helweh

Adam Helweh

Adam is CEO of Secret Sushi Creative Inc, a strategic design, digital and social media marketing agency. He specializes in the convergence of design and technology to provide businesses with more intelligent and interactive ways to connect with customers and grow. His clients have included Edelman, Broadcom, Stanford Federal Credit Union, the Thomas Keller Restaurant Group, Bunchball and others. He's also the co-host of the "SoLoMo Show", a weekly digital marketing podcast, and he has shared the stage with professionals from companies including Facebook, Virgin Airlines, Paypal, Dell and 24 Hour Fitness.

Other posts by

Comments & Reactions

Comments Policy

Comments on Social Media Explorer are open to anyone. However, I will remove any comment that is disrespectful and not in the spirit of intelligent discourse. You are welcome to leave links to content relevant to the conversation, but I reserve the right to remove it if I don't see the relevancy. Be nice, have fun. Fair?

  • Davis G H Phillips

    Excellent round-up.
    I think that the application of latent semantic indexing as a component of sentiment analysis has made the process much better. 

    I have been ‘loading’ semantic concepts in order to offer enhanced perspectives (the view of the client is an example) and to get a closer match to human coding have found that a Bayesian parse makes each of the processes more realistic.

    I think those of us in this business are getting close to being able to offer automated analysis close to 85% which is as good as I think we will get for a number of years.

  • Davis G H Phillips

    Excellent round-up.
    I think that the application of latent semantic indexing as a component of sentiment analysis has made the process much better. 

    I have been ‘loading’ semantic concepts in order to offer enhanced perspectives (the view of the client is an example) and to get a closer match to human coding have found that a Bayesian parse makes each of the processes more realistic.

    I think those of us in this business are getting close to being able to offer automated analysis close to 85% which is as good as I think we will get for a number of years.

  • http://www.online-business-virtual-assistant.com/ Virtual Business Assistant

    Hi loved this “How can people find out more information about how sentiment analysis is being used for business?” sentiment for business would be a new field to digg.

    • Kellybagley

      The quote that you put into your frame made the sentence too long to be easily understood. Tell your programmer to make other frames available to you in this situation.

  • http://www.online-business-virtual-assistant.com/ Virtual Business Assistant

    Hi loved this “How can people find out more information about how sentiment analysis is being used for business?” sentiment for business would be a new field to digg.

    • Kellybagley

      The quote that you put into your frame made the sentence too long to be easily understood. Tell your programmer to make other frames available to you in this situation.

  • http://www.evoapp.com/blog Sergei Dolukhanov

    “I saw, earlier this year, primitive sentiment capabilities and analysis interfaces that resembled those of BI tools circa 2000.”
    Somehow companies are still stuck with their sentiment technology, but I’m sure this will improve as more feedback is processed and acknowledged, and more methods are tested. 

    When it comes to business use cases for sentiment, there are many. However, none are more important or beneficial than correlating the sentiment data you pull from the social web, or any data set really, (surrounding any topic of relevance to your company) to key business performance metrics. For example, when taking a sampling of online sentiment of “Bank of America” and comparing it to their stock prices over the last 3 months, the patterns, dips, valleys, and peaks are shockingly close in resemblance. Without even taking numbers in to account, the sheer visual resemblance is remarkable. Tying sentiment, especially cumulative, to core business metrics and identifying trends, themes, and other predictive analytic patterns from doing this is one of the best use case scenarios in business for this technology. Keep an eye out for an infographic we are doing on this; we’ll be releasing it at the end of this week / early next. You’ll be able to find it on our blog at http://www.evoapp.com/blog

    Either way, great job on the interview Adam. I thought you asked all the right questions and Seth Grimes did a great job in covering the important aspects of this technology. 
    Cheers, 

    – Sergei Dolukhanov
    @sdolukhanov:twitter 
    http://www.evoapp.com 

    • http://www.secretsushi.com/ Adam Helweh

      Thank you Sergei. For the praise and for the thoughtful comment. You got me thinking a bit. It seems the problem businesses have in doing what you mention is the forethought of which business metric correlate the sentiment data with and also the still lacking accuracy in sentiment tracking tools, yes?

      • http://www.evoapp.com/blog Sergei Dolukhanov

        Yes, the accuracy of sentiment tools is generally in the 80-90% range, it’s tough to say if anyone will ever get it perfect because of the naturally fluidity of the human language and the millions of variations people use to say the same things. However, you can still get a great overall perspective even with a sentiment tool that hits 90% accuracy.

        I would think the best metrics to correlate sentiment with are anything having to do with financial figures or stock prices maintaining a consistent time frame throughout. I.e. you take the sentiment of your brand for the last quarter, and take all the financial numbers and see where they fit together in the grand scheme of things. For the Bank of America experiment, the correlations between negative sentiment and falling stock price are very real and clear to see when you overlay the visuals on top of one another. Obviously this was just one example, and “just a dip” in to the real pond, but it opens up some interesting paths to wander down. 

  • http://www.evoapp.com/blog Sergei Dolukhanov

    “I saw, earlier this year, primitive sentiment capabilities and analysis interfaces that resembled those of BI tools circa 2000.”
    Somehow companies are still stuck with their sentiment technology, but I’m sure this will improve as more feedback is processed and acknowledged, and more methods are tested. 

    When it comes to business use cases for sentiment, there are many. However, none are more important or beneficial than correlating the sentiment data you pull from the social web, or any data set really, (surrounding any topic of relevance to your company) to key business performance metrics. For example, when taking a sampling of online sentiment of “Bank of America” and comparing it to their stock prices over the last 3 months, the patterns, dips, valleys, and peaks are shockingly close in resemblance. Without even taking numbers in to account, the sheer visual resemblance is remarkable. Tying sentiment, especially cumulative, to core business metrics and identifying trends, themes, and other predictive analytic patterns from doing this is one of the best use case scenarios in business for this technology. Keep an eye out for an infographic we are doing on this; we’ll be releasing it at the end of this week / early next. You’ll be able to find it on our blog at http://www.evoapp.com/blog

    Either way, great job on the interview Adam. I thought you asked all the right questions and Seth Grimes did a great job in covering the important aspects of this technology. 
    Cheers, 

    – Sergei Dolukhanov
    @sdolukhanov:twitter 
    http://www.evoapp.com 

    • http://www.secretsushi.com/ Adam Helweh

      Thank you Sergei. For the praise and for the thoughtful comment. You got me thinking a bit. It seems the problem businesses have in doing what you mention is the forethought of which business metric correlate the sentiment data with and also the still lacking accuracy in sentiment tracking tools, yes?

      • http://www.evoapp.com/blog Sergei Dolukhanov

        Yes, the accuracy of sentiment tools is generally in the 80-90% range, it’s tough to say if anyone will ever get it perfect because of the naturally fluidity of the human language and the millions of variations people use to say the same things. However, you can still get a great overall perspective even with a sentiment tool that hits 90% accuracy.

        I would think the best metrics to correlate sentiment with are anything having to do with financial figures or stock prices maintaining a consistent time frame throughout. I.e. you take the sentiment of your brand for the last quarter, and take all the financial numbers and see where they fit together in the grand scheme of things. For the Bank of America experiment, the correlations between negative sentiment and falling stock price are very real and clear to see when you overlay the visuals on top of one another. Obviously this was just one example, and “just a dip” in to the real pond, but it opens up some interesting paths to wander down. 

  • http://www.facebook.com/bryanjennewein Bryan D Jennewein

    What an intriguing and engaging post! At Radian6, we receive many inquiries about “Sentiment Analysis” and communicate to our clients many of the points Seth makes above – in particular, managing expectations regarding accuracy and methods. 

    I was glad to see Seth describe our Radian6 Insights Platform as a framework; he really hit the nail on the head: what we have built is a platform where many providers of analysis, extraction, and other social insights can plug-in to enhance social post data.

    One item I wanted to clarify was which providers are currently available. Seth listed “AlchemyAPI, Clarabridge, Lexalytics, and OpenAmplify,” when in fact only Lexalytics and OpenAmplify are available and accessible today. In addition to these, also available today are Klout, OpenCalais, and some Basic Demographic data. We have many more prospective providers of Sentiment Analysis and other social insights coming soon. Stay tuned! 

    Cheers,
    Bryan JenneweinProduct Manager – Radian6 Insights & Radian6 Analysis Dashboard  | Radian6, a salesforce.com company | C: 506.238.5962 | E: bryan.jennewein@radian6.com | @bryanjennewein:twitter 

  • http://www.facebook.com/bryanjennewein Bryan D Jennewein

    What an intriguing and engaging post! At Radian6, we receive many inquiries about “Sentiment Analysis” and communicate to our clients many of the points Seth makes above – in particular, managing expectations regarding accuracy and methods. 

    I was glad to see Seth describe our Radian6 Insights Platform as a framework; he really hit the nail on the head: what we have built is a platform where many providers of analysis, extraction, and other social insights can plug-in to enhance social post data.

    One item I wanted to clarify was which providers are currently available. Seth listed “AlchemyAPI, Clarabridge, Lexalytics, and OpenAmplify,” when in fact only Lexalytics and OpenAmplify are available and accessible today. In addition to these, also available today are Klout, OpenCalais, and some Basic Demographic data. We have many more prospective providers of Sentiment Analysis and other social insights coming soon. Stay tuned! 

    Cheers,
    Bryan JenneweinProduct Manager – Radian6 Insights & Radian6 Analysis Dashboard  | Radian6, a salesforce.com company | C: 506.238.5962 | E: bryan.jennewein@radian6.com | @bryanjennewein:twitter 

  • http://www.facebook.com/matykiewicz Pawel Matykiewicz

    Let’s not forget the applicability of sentiment analysis in healthcare. It can be used for patient outcome measurements (does the patient feel well after intervention A compared to B), diagnosis (psychiatric diseases), intervention (mood monitoring for patients with special needs). These are all business opportunities.

  • http://www.facebook.com/matykiewicz Pawel Matykiewicz

    Let’s not forget the applicability of sentiment analysis in healthcare. It can be used for patient outcome measurements (does the patient feel well after intervention A compared to B), diagnosis (psychiatric diseases), intervention (mood monitoring for patients with special needs). These are all business opportunities.

  • http://bestessay4u.com/ Custom essay

    Blogs are so interactive where we get
    lots of informative on any topics…… nice job keep it up !!custom essay

  • http://bestessay4u.com/ Custom essay

    Blogs are so interactive where we get
    lots of informative on any topics…… nice job keep it up !!custom essay

  • http://twitter.com/rpaulsingh R. Paul Singh

    Great article and great sets of comments. In order to get accurate sentiment analysis, a generalized horizontal solution is unlikely to result in high accuracy unless an industry expert continues to tune the software over a period of time. Most companies don’t have either the resources or the patience to get this data and so only look at broad brush and give up.

    Looking at this problem some companies like http://www.socialnuggets.net have taken a vertical industry approach to this problem. SocialNuggets focuses on consumer electronics industry while there are others who focus on hospitality while others are focusing on automobile or healthcare. Just an enterprise software companies ended up segregating their customers into various verticals we think sentiment analysis will become more and more verticalized.

    Listening to social media’s textual data and creating meaningful analytics and correlating it with quantitative business data is in its infancy. Social media data when mined correctly will become like an independent consumer report and predictive analysis for companies where they can know many things including the following:
    How is our product feature set being perceived compared to our competition?
    What effect does our ad campaign have in helping the brand?
    Looking at intent to purchase of various products how does a retailer stock different products?
    Is our product likely to perform better in one region vs others based on social geo data?

  • http://twitter.com/rpaulsingh R. Paul Singh

    Great article and great sets of comments. In order to get accurate sentiment analysis, a generalized horizontal solution is unlikely to result in high accuracy unless an industry expert continues to tune the software over a period of time. Most companies don’t have either the resources or the patience to get this data and so only look at broad brush and give up.

    Looking at this problem some companies like http://www.socialnuggets.net have taken a vertical industry approach to this problem. SocialNuggets focuses on consumer electronics industry while there are others who focus on hospitality while others are focusing on automobile or healthcare. Just an enterprise software companies ended up segregating their customers into various verticals we think sentiment analysis will become more and more verticalized.

    Listening to social media’s textual data and creating meaningful analytics and correlating it with quantitative business data is in its infancy. Social media data when mined correctly will become like an independent consumer report and predictive analysis for companies where they can know many things including the following:
    How is our product feature set being perceived compared to our competition?
    What effect does our ad campaign have in helping the brand?
    Looking at intent to purchase of various products how does a retailer stock different products?
    Is our product likely to perform better in one region vs others based on social geo data?

  • http://twitter.com/TomHCAnderson Tom H C Anderson

    Thanks for the mention Seth! 

  • http://twitter.com/TomHCAnderson Tom H C Anderson

    Thanks for the mention Seth! 

  • http://twitter.com/VineBuzz Rich Reader

    Thanks for the concise overview of sentiment analysis, and whetting our appetites for #SAS11

  • http://twitter.com/VineBuzz Rich Reader

    Thanks for the concise overview of sentiment analysis, and whetting our appetites for #SAS11

  • http://ctrl.pragma-tech.com Ramy Ghaly

    Great interview with Seth Grimes on sentiment analysis and what it means to marketers. 

  • http://ctrl.pragma-tech.com Ramy Ghaly

    Great interview with Seth Grimes on sentiment analysis and what it means to marketers. 

  • http://www.socialmarketingdynamics.com/ Sydney @ Social Dynamics

    That is quite an interesting concept. Though, I’m slightly curious if they can detect sarcasm? lools. Because for the life of me, I can never distiguish it if it was said out of context, every single time.ha

  • http://www.socialmarketingdynamics.com/ Sydney @ Social Dynamics

    That is quite an interesting concept. Though, I’m slightly curious if they can detect sarcasm? lools. Because for the life of me, I can never distiguish it if it was said out of context, every single time.ha

  • Pingback: Online Brand Sentiment: Which Brands Win & Lose Online | Appenheimer

  • Pingback: SEO content marketing roundup, week ending November 9th | SEO Copywriting

  • http://twitter.com/Collectual Collective Intellect

    When working with sentiment we often advise our clients to create the context first, then apply sentiment. Sentiment on its own provides very little value and as Seth noted it’s not entirely reliable. By isolating consumer conversations around pricing, intentions (intent to view, intent to purchase), loyalty, etc. then filtering by sentiment that a better understanding of consumer preferences and opinions is possible. 

    Great interview with Seth. Thanks for sharing!

    • Mahabecs

      hello madam,i am from india,i am dng research in sentimental analysis.pls give your valuable suggestions to carry out my research

  • http://twitter.com/Collectual Collective Intellect

    When working with sentiment we often advise our clients to create the context first, then apply sentiment. Sentiment on its own provides very little value and as Seth noted it’s not entirely reliable. By isolating consumer conversations around pricing, intentions (intent to view, intent to purchase), loyalty, etc. then filtering by sentiment that a better understanding of consumer preferences and opinions is possible. 

    Great interview with Seth. Thanks for sharing!

  • Pingback: The Top Challenges with Sentiment Analysis

  • Pingback: Jeffrey Henning’s Top 20 #MRX Stories of the Year | GreenBook

  • Pingback: Social media reputation monitoring | Useful Social Media Blog

  • Pingback: Social Media & Sentiment: 5 Takeaways from the Sentiment Analysis Symposium | Social Media Explorer

  • Pingback: top 20 stories discussed on the Twitter #MRX community in 2011 « Mundo da Pesquisa

  • Pingback: The Big Data Impact on Social Media Marketing | Tech Chatter

  • Pingback: The Big Data Impact on Social Media Marketing

  • Pingback: SoLoMo Show Ep 28: Deep Dive into Social Media Monitoring and Measurement with ViralHeat's Erin Robbins O'Brien | Social Media Explorer

  • Pingback: OPINION POLLS OR OPINION TROLL-LA-LOLS? | JOUR2722

  • Pingback: OPINION POLLS OR OPINION TROLL-LA-LOLS | JOUR2722

  • Pingback: Seven tips for marketing with Twitter, Pinterest and social media | Creativity_Unbound

  • Pingback: Sentiment Analysis and the Power of Positive | PeerIndexPeerIndex

  • Pingback: abs

  • Pingback: garnicia cambogia

  • Pingback: This Web-site

  • Pingback: The Big Data Impact on Social Media Marketing

  • Pingback: Online Brand Sentiment: Which Brands Win & Lose Online « MindCorp | Newsfeed