Our Sentiment about Text Analytics and Social Media

Submitted by Jeff Catlin on Mon, 2010-03-22 04:00

At Lexalytics, we try to follow the news in all of the industries that affect and are affected by text analytics, chief among them is social media monitoring. An interesting bit of news came out last week from Radian6; they reported that last year was their first profitable year. This is bigger news than one might think because there are soooooo many players in the social media monitoring space that I have always worried that none of them could garner enough market share to become viable money-making companies. It says something about how they run their business in that they've reached this milestone, but it also says something about the space in general. Social Media and all the things it's used for: - Brand Awareness - Disaster discovery - Advertising & customer engagement have quickly jumped the fence from novelties to mainstream features that almost all large companies worry about (and some mid-sized ones as well). Not only are companies like Radian6 prospering, but established players like Facebook are growing their traffic numbers to the point that they are seeing more page views than Google. The users are forcing companies to listen to them, and the smart companies are engaging monitoring companies like Radian6, ScoutLabs and others to listen to the customers. Some may wonder why this transformation has happened so quickly (I'd say in less than 2 years), and the answer is that pretty much everybody wins, so why wouldn't Social Media become a defacto part of life for consumers and businesses? The consumers get more of a say, so they're happy, and the companies that choose to listen have a direct connection to their customers thereby a means to interact and hopefully increase sales and revenue.

Submitted by Jeff Catlin on Mon, 2010-03-15 04:00

Now for something a bit out of the norm for me...a post about the enterprise search market. I don't know if everyone has noticed, but the enterprise search market has changed dramatically in the last 18 months or so. For example, when Microsoft bought FAST a couple of years ago I expected that they would pull FAST into Microsoft and adjust their business model, and so they have. FAST is much more focused on Sharepoint these days and will over time cease their support of Linux as an operating system. If you're Microsoft this is a pretty reasonable move, as Sharepoint has a massive user base and has historically been weak at search. Unfortunately, this isn't a good thing for FAST's biggest clients who can't realistically migrate to Sharepoint. So, what are these users to do? Well, Autonomy and Endeca are the obvious choices, but Autonomy has been moving away from the enterprise search space for the last few years. Endeca has historically focused on eCommerce applications, but now appears to be moving toward enterprise search, though they aren't there yet. So, where does this leave all the companies with massive content search problems? At the moment there doesn't seem to be a clear answer to this one, but as near as I can tell there are 2 candidates vying for the crown; as I alluded to above, one is Endeca. They seem to realize that FAST's acquisition has opened up the high end market, and the other is Lucene/SOLR which is making noticeable inroads in the enterprise search world. It's too early to tell how all this will play out, but my hope is Endeca makes a full-on play for the high-end enterprise market by continuing to upgrade their core search offering [DISCLOSURE: Endeca is a reseller of Lexalytics software, so we have a vested interest in their success]. In the other corner is Lucene/SOLR, which is a great engine, and is a perfect solution for the companies that are willing to spend the time and money to get a fully customized solution, however until it reaches critical mass there will be those companies that are uncomfortable with it because it's open source. Lucene/SOLR may well overcome this stigma and become the enterprise engine that takes over the high end market, but it'll be a while before we know for sure. I'll keep an eye on it, and post on this topic again in 4 or 5 months and see if the landscape has changed, but for now keep your eyes on Endeca and Lucene.

Submitted by Jeff Catlin on Tue, 2010-03-09 05:00

You know you've hit the right spot when Microsoft starts telling your story. I just watched an interesting TED webcast by Gary Flake of Microsoft explaining Microsoft's Pivot application that the labs group has developed: http://blogs.msdn.com/searchblog/archive/2010/03/05/microsoft-pivot-future-of-browsing-searching.aspx The basic premise is that we shouldn't fear the explosion of information that's occurring, we should embrace it as an opportunity to look at the big picture. The key to this demonstration is that by looking at the aggregate of information and what that content has in common we can spot patterns and trends that would otherwise be invisible. The only thing missing in the presentation is the recognition that figuring out the right ways to sort this sea of information is the tricky piece; how do I know that I'll see interesting things if I sort by "Tour de France" after I see a cover story on Lance Armstrong? They may have ignored it because they haven't got that piece figured out yet, but the truth is that Text Analytics is a perfect tool for exactly that purpose. The best way to swim around in a big sea of content is to give the users a high level idea of what's in the content and then adjust the sort columns dynamically based on the content you're looking at. For example if I search for "car recalls" I should be presented with the best ways to sift into the data from all of the recall stories, so I'd expect sort options like: "Toyota", "acceleration" or "Congress". Everyone realizes that content volumes aren't going down, so it stands to reason that this sort of application will have to become mainstream because simple search just won't narrow down the choices enough. It's great to see Microsoft pitching this story, and hopefully the Pivot application will become a bit more generic over time because it's a really nice looking application with a lot of potential.

Submitted by Christine Sierra on Tue, 2010-02-23 05:00

I am fascinated by the nay-sayers that repeatedly claim automated sentiment software, web sites and services are garbage. According to them, the software almost always get it wrong; it doesn't interpret sarcasm; it's not 100% accurate. The rule of thought is that you can't extract true sentiment unless you have a staff of humans reading and tagging every potential story about your company as negative, neutral or positive. Really? I mean can you honestly say that automated sentiment is useless and wrong ALL of the time? There are certainly some examples out there of solutions that are far from useful, but is that a reflection of the entire industry? I started to think of some other automated things that I rely on in my daily life and wondered if they are always perfect. If they always intepret things the way I do. Or, perhaps, they make my job easier so as a human I can focus on other tasks that matter and can filter out items that would otherwise take up time and distract me. Here's what I came up with:

Spam filter software: Wow. Wouldn't I love this to be 100% accurate and catch every spam email that hits my desktop. But while it doesn't always filter out every offensive message, it is much more efficient than opening and reading every email to determine for myself if it's legit or not.

Search engines: How come when I type "best pizza in Boston" into Google Search I get a list of 7 establishments scattered around the city? Can't there only be one "best"? Doesn't it understand that? But luckily I agree with all the yummy choices it returns so I'd say it did a pretty good job.

Spell checker: I make typos. All the time. Every day. Luckily, there are these little squiggly lines that show up under my mis-spelled words to let me know there may be something wrong. But sometimes the suggestion the software makes is wrong or the word I wanted isn't even listed as a suggestion. However, most of the time, when I type "teh" and mean "the", it gets caught. Obviously I'm having fun with this post and I certainly don't mean to imply that any of the above need to be perfect, I'm happy they work most of the time. But the bigger picture is that these examples all have to do with words - and how we express them and how we input them or receive them. If you are being vocal with your expectations that sentiment software based on text needs to be accurate and right 100% of the time, you are bound to be disappointed more times than not. If you are processing a lot of information and need to streamline the process by concentrating on the extremes, then explore what automated systems can do for you. It seems easier at times to focus on what it can't do instead of what it can. And don't believe claims of absolute accuracy, especially with sentiment and text analytics. Computers can only process so much from text, as text is comprised of typed words, and like the spell checker example above, typed words are by no means perfect. At least mine aren't.

Submitted by Seth Redmore on Fri, 2010-02-12 05:00
Continuing the analysis of tech related sites, I decided to check to see if Apple really was that important across another consumer-focused tech site. I originally envisioned comparing Engadget and Gizmodo; but only got really good, clean content from Gizmodo. The Engadget content was too noisy with ads and headlines to make for a useful comparison. So, the short answer is that Apple is also number one in Gizmodo’s heart, but not by such a staggering amount. Here’s the content map for Gizmodo.  And you can see that Apple is number one. However, a quick look at the numbers shows a different perspective:  The difference is in the proportion of articles devoted to Apple and how the “tail” treated other companies. Across the Gizmodo universe, there were 4406 articles processed. 272 articles out of the 4406 mention Apple. That’s only 6%. Microsoft rates a 4.2%, with Google not far behind. What’s interesting is that the top companies are roughly the same in terms of the discussion…. Apple, Microsoft, Google in that order are #1, #2, and #3 for Mossberg, Pogue, and Gizmodo. Are they the top 3 personal tech companies? Seems like there is a bit of agreement here. Where they start to diverge is in the rest of the list. Facebook doesn’t make the top 10 for either Mossberg or Pogue – and I’d say that Facebook has become increasingly important. Amazon doesn’t make Mossberg’s list, but makes the list for Pogue and Gizmodo. (you can check out the earlier blog post to see their lists of top 10 companies). Yahoo! only makes Mossberg’s list (neither of the other’s), and AT&T figures way more prominently in Gizmodo’s list than either of the others. Sony makes all 3 lists. Canon only makes it onto Pogue’s list of top companies.  What I find most interesting about this chart is the fact that with the exception of the concept of “video”, everybody has some negative – and it’s roughly the same proportion for each. I’d be curious as to whether this is an editorial decision, or something that just sorta worked out. The themes seem to have less negative, but the companies each have a significant chunk of negativity associated with them – which is why everybody appears as neutral when it’s all mushed together.  So, again, comparing to Mossberg and Pogue, a few things stand out. First off is the face that Blu-ray players come out so high in the themes. Battery-life is the top theme, where with Mossberg&Pogue, it’s down the list at #8. The concept of “software” doesn’t even make the list for Gizmodo. Oh, to call it “hard drive” or “hard disk”? Gizmodo calls it a “hard drive”, M&P call it “hard disk”. I bet that’s a function of age, personally. Smile I find the theme “personal portable” to be rather intriguing, so, here are the companies and themes that are co-mentioned with this theme: So, you can see that it probably has to do with gaming and video players. Last, but not least, let’s see where gizmodo stands on their primary themes (in terms of sentiment for each): I find it interesting that the concept of “screen” is overall neutral, but once a particular size is mentioned (”inch screen”) then the conversation seems to get more polarized. The most positive discussions are around battery life (which I find strange, given that it’s the thing that is increasing most slowly). So, in summary, I find it interesting that the top 3 tech companies are exactly the same across Mossberg, Pogue, and Gizmodo (Apple, Microsoft, Google). They even have the same order. The big difference is in the proportion of their coverage (25% for Mossberg/Pogue, and 6% for Gizmodo).
Submitted by Seth Redmore on Thu, 2010-02-11 05:00
We get 2 papers here at my house, courtesy of my news-hound wife: the New York Times and the Wall Street Journal. (Of course, neither has a comics section, which basically ruins the newspaper experience for me, but that’s neither here nor there.) After glancing through the NYT Personal Technology section, I decided that I wanted to see how David Pogue (NYT tech columnist) compared to Walt Mossberg (WSJ tech columnist). And by “compare”, I wasn’t really looking for anything in particular, more just curious… So, I used Mozenda’s (www.mozenda.com) excellent screen scraping solution and snagged all of the URLs for as many posts as they had in their archives, (This took about 20 minutes total, because I’m not terribly familiar with the screenscraper.) I then fed the URLs to PRScope as a list of URL in the “add text” section (and checking the “URLs only” checkbox). A section that could probably use a different name, because, yes while you can add text to it, you can (very importantly) add a block of text that’s just a list of URLs. But, again, I digress. So, for Mossberg, that ended up being 242 articles, and for Pogue it was 660 articles. Both stretched back somewhere into 2005 or 6. I wasn’t really concerned about time-series analysis for this, more just the “big-picture” what are they writing about… Here’s the connection map for the project:  Granted, this is a mismash of blog posts and real columns, but I figured it would give a good sense of what they saw to be important. Apple, apparently. (Even with all the obvious crap in there — “previous post”, etc, Apple stands out). Let’s take a look at the map with just the two main people (Walt and David Pogue) without the themes.  226 articles out of 902 (25%) mention Apple at least once. 162 (18%) mention Apple at least twice. Is it just one of them with the Apple fascination? Nope. Mossberg has 75 out of 242 (31%) and Pogue has 151/660 (23%). Microsoft only has 130 articles between the two of them. It’s in the same basic “bucket” of size as Apple (relative to Dell, and Intel) – which is why the icons are the same size. When I turn off people (the large “David Pogue” block is somewhat compressing things), I see this:  Which gives a better feel for the scope. It’s also interesting to note the fact that Apple has an overall positive view in their minds, as opposed to the basically neutral view of the other companies. Showing the companies sentiment as pie charts gives me a connection map as so:  So, the difference isn’t huge, but enough to tilt Apple towards the positive. I suppose that this isn’t surprising, given the overall perception of the two companies. Perhaps it’s more surprising that Microsoft has so much green, eh? The top 10 companies, with their sentiment scores, from Mossberg:
  Negative Neutral Positive Articles
Apple 7 24 44 75
Microsoft Corporation 3 21 30 54
Dell Inc. 6 13 12 31
Google Inc. 1 9 13 23
Intel Corporation 1 10 11 22
Sony Corporation 3 5 13 21
Yahoo! Inc. 1 5 7 13
Sprint 2 4 5 11
Lenovo 5 2 3 10
Samsung 1 5 4 10

The top 10 companies, with the sentiment scores, from Pogue:

  Negative Neutral Positive Articles
Apple 19 65 67 151
Microsoft Corporation 14 35 27 76
Google Inc. 3 37 17 57
Verizon 15 21 14 50
Canon Inc. 2 14 8 24
Amazon Com Inc 2 10 9 21
Sprint 4 14 3 21
Dell Inc. 4 7 7 18
Sony Corporation 4 9 3 16
Cingular 2 8 5 15

Somebody doesn’t like Verizon, eh? This begs the question of what are the companies that they tend to talk about the most… Here it is, the top 20: None of these come as a surprise, in fact none of the top 50 really come as a surprise. Verizon has by far the highest percentage of negative commentary out of all of the companies mentioned. Enough of that. Just what sorts of things are they discussing in the blogs? By turning off companies and looking at a list of top themes, we get the following… The top 10 themes (aggregated) are:  Let’s see how they differ by journalist: Mossberg’s themes (stacked sentiment): Clearly, he’s happy about the direction that storage is taking. Pogue’s themes (stacked sentiment): No strong sentiment with any of his themes, but the man believes in the power of the phone. In the last bit of this analysis, let’s take a look at the themes that are associated with Apple (for both journalists). You can see that the connections are strongest between the concepts of “phone”, “software”, and “screen” (and, oh boy doesn’t Apple always have nice screens on their stuff?) For Mossberg, the picture changes slightly: There’s still a tight connection to software, but, the connection to phone is less (not surprising). But what’s interesting is the fact that he seems to be writing a lot about the connection between Apple and music (hence the tight connection to the theme of “music”). And there’s that storage thing again (”hard disk”). And here’s Pogue’s: In Pogue’s connection map with Apple, you can see the prevalence of phone and phone-related themes (cellphone, phone call, cell), and an almost complete absence of things related to music. One interesting thing to note is that the theme “music play” – probably “music player” – has a lot of negative in both maps, indicating some issues there. So, why are they Fanboiz of Apple’s? I don’t know. I do know that I’m sitting here writing this on an 8-core Mac Pro & 30? studio monitor, with a 17? MacBook Pro open next to me, so I don’t have a lot of room to make fun of anybody. I do wonder if Apple is really such an important force in personal technology that they deserved mention in 25% of their articles, tho. I will probably look at some geekier (and I mean that with all the love in my heart) tech sites like Engadget and Gizmodo next, and we’ll see if a similar proportion occurs there.

Submitted by Seth Redmore on Tue, 2010-02-09 05:00

The Super Bowl brings inevitable re-running and armchair quarterbacking at all the advertising agencies about how they could have done better. There's statistics and measurements galore, from Nielsen to USAToday about popularity and viewing. I was curious about what people were saying about the ads, so, I pointed Lexascope at the blogosphere and news feeds, and below is what it told me. We didn't do a big scientific-sounding study with lots of important seeming partners, we just snagged a bunch of blog and news content and let Lexascope read it and tell us what's up. Surprisingly enough, given the huffing and puffing around Tim Tebow's "pro-life" ad, Google's ad turned out the most pundits in the blogosphere and got the most news coverage. The top 3 were: Google's "Parisian Romance" Focus on the Family's "Tim Tebow" Audi's "Green Police" I'm not saying these were the best, just that they generated the most conversation. Google's ad has generated a number of pariodies - perhaps this is the real genius of the spot, in that it is going viral in a very different way than normal - viral with parodies, not necessarily with the original spot. Here's one of them. Here's the connection map:  

A few very interesting things come up.

  1. There are 3 disjoint clusters - the discussion around Google, the discussion around Tim Tebow/Focus on the Family, and the "Betty White" Snickers ad.
  2. Audi's ad gets connected to Tim Tebow, as the ads were co-mentioned in a number of articles, but the discussion about Google was completely disjoint from that discussion.
  3. The conversation around Google was largely positive (except for the normal hating around Google being big and bad), the Snickers commercial offended nobody, and the Tim Tebow commercial basically reflected our views (as a country) about organizations like Focus on the Family - it's probably reasonable to think that 1/3 think they're great, 1/3 don't care, and 1/3 don't like them.
  4. CBS has the only soundly negative sentiment through this discussion, with the controversy around the Focus on the Family ad, and it's seemingly contradictory handling of a pro-gay dating site's ad leading to some thrashing in the blogosphere and the news.

The USA Today "Super Bowl Ad Meter" showed that the favorite ad by viewers was the Snickers ad. My question is this: What's better - to be rated as "viewer's favorite ad" or to generate the most discussion? This, of course, is where the art and science of PR mix together - it probably depends on the tone of the conversation and the folks you were trying to reach.

Submitted by Christine Sierra on Mon, 2010-02-08 05:00

Jeff recently shared his thoughts on Text Analytics Market Growth with Seth Grimes for his report on B-Eye Network: Text Analytics Opportunities and Challenges for 2010 (free registration required). It's a well written report, outlining the thoughts and expectations for 2010 from industry leaders and innovators in the Text Analytics industry. Here is Jeff's excerpt, providing some insight on how Text Analytics and Sentiment will play out in 2010: Market Growth Lexalytics CEO Jeff Catlin affirms other respondents' themes. He sees search as a particular growth area and makes other points regarding text-analytics market growth:

Text analytics [TA] will become a mainstream feature set in enterprise search applications (though not by name). We've seen a steady march toward this in 2009, and it's most notable in how accepted TA features are by the general public. When I'm at a party now and tell someone what we do, they say "Oh yeah, I read something about that sort of stuff last month" as opposed to the "Huh???" that I used to get. The effect of this is that there are a lot more opportunities for TA in enterprise applications, and I suspect it will mean that one or two of the players may get picked up by a big company.

Sentiment will complete its transition to a "checklist" feature that everyone who works in this space will have to provide. All of the vendors (big and small) will claim to have sentiment. The consumers of this technology will also get a bit more educated - we're seeing this in RFP requests for particular capabilities of sentiment - which will help separate the wheat from the chaff. Unfortunately for us, sentiment won't be a totally differentiating feature that you can hang a business on anymore, as there will be lots of competition on the sentiment front.

The [differentiation between] larger TA players and the niche players will become even more obvious. The bigger players will integrate a number of useful and useable semantic features into their engines which will help with things like ad hoc classification, concept roll-up, and relationship [extraction].

On the business side, we expect 2010 to be a "Home Run" year for all the TA vendors with growth rates of 75% to 200% not out of the norm. This is partly due to the mainstreaming of the technology, which is opening up a lot of additional verticals.

Submitted by Christine Sierra on Fri, 2010-01-22 05:00

About a year ago, our CTO Mike Marshall did some accuracy testing on sentiment using our software. This wasn't so much to showcase Lexalytics capabilities as it was to show that accuracy using automated sentiment can be helpful in the business process if done correctly.

One thing we do know for sure is that computers don't change their minds about the sentiment for a certain piece of text. If you run the same piece of text through the software 100 times, it will come back with the same results every time. Humans, on the other hand, have the capacity to change their minds - and disagree with each other - on the same piece of text. But that's okay. At Lexalytics we've never suggested you take human analysis out of the equation when it comes to analyzing unstructured content. In fact, our hope has always been to help the humans be more productive. Removing the neutral content is the goal, so the focus can be on the extremes within the content - the really positive or the really negative. I was recently surprised by a statement recently from Forrester Principal Analyst Suresh Vital that "in talking to clients who have deployed some form of sentiment analysis, accuracy rests at about 50 percent." If this were to be true in our client base, we'd sadly be out of business. I hope as more and more companies enter into the sentiment analysis arena that they continue to test and retest their models. Below is Mike's analysis from earlier in 2009:

Experience has also shown us that human analysts tend to agree about 80% of the time, which means that you are always going to find documents that you disagree with the machine on. However, having said all that, customers still like to be told a base line number, it's human nature after all to want to know how something will perform, so I thought I would do a little test using the new model based system on a known set of data. As recommended on the Text Analytics mailing list I used the Movie Review Data put together by Pang and Lee for their various sentiment papers. This data consists of 2000 documents (1000 positive, 1000 negative) and I sliced it into a training set consisting of 1800 documents (900 positive and 900 negative) and a test set consisting of the remaining 200. It took about 45 seconds to train the model and then I ran the test set against it (using a quick PHP script). Now bearing in mind this is still experimental and that we plan to make more tweaks to the model, I was pleasantly surprised (ok I was more than pleasantly surprised) at the results. Our overall accuracy was 81.5% with 81 of the positive documents being correctly identified and 82 of the negative ones. This is right in the magic space for human agreement. For fun, I then ran the same 200 test set documents against our phrase based sentiment system, expecting a far lower score, but again we performed better than I thought scoring 70.5% accuracy. With a domain specific dictionary I'm sure that that score could be pushed up towards 80% as well. So what does all that tell us? Well, it tells us that for specific domain sets you can get very high accuracy levels, though if you ran say, financial content against the movie trained database the results would be far different. It also tells us that the phrase based sentiment technique produces good results even in its base state against a wide range of content sources (we normally are processing news-related data after all).

So, would you agree?

Submitted by Christine Sierra on Wed, 2009-12-16 05:00

Wow, it has been a while since we blogged. That's bad. Sorry about that, but we've had some new developments coming out of the company, literally. First, we helped launch a new subscription-based product called Lexascope - www.lexascope.com - and it is powered by Lexalytics' Salience technology. We previewed this in October at the Inbound Marketing Summit and are pleased to have it avaiable for download. It's still in beta, but we are encouraging everyone to take a look and sign up for the 15 day FREE trial. Let us know what you think. The first desktop application is geared towards PR professionals who want to discover entities, themes and sentiment from RSS feeds or online content. In addition, we're working on a new product called Lexalytics Cascade. Cascade attacks a class of problems not addressed by our Salience product, namely stateful content processing. It provides users the ability to look across a collection of content and perform tasks like content filtering, document similarity and collection level theme rollup. In the initial release, we focused on providing a high performance filtering engine to bucket content via user-defined queries, and to provide a scalable document similarity engine capable of measuring the similarity of terabytes of documents. If you're thinking, "exactly what is a filtering engine?" The easiest way to imagine it is to think about it as a search engine standing on its head. In a filtering engine, the queries are indexed and the documents flow across the engine and act more like queries, where the documents are "filtered" into buckets represented by the indexed queries. Filtering engines are designed to operate against live flows of content like newsfeeds or twitter streams. The advantage of a filtering engine over a search engine to bucket content is simple, PERFORMANCE. A filtering engine can filter hundreds of thousands of documents per hour. This capability combined with the engines similarity capabilities means that you can process large flows of content with Cascade, and identify duplicates and/or syndicated documents in your document stream. Throughout 2010 Lexalytics will further enhance Cascade with a series of new releases focusing on the aggregation and rollup of concepts across whole collections of content. We hope you forgive us for being gone for so long. As we approach the holidays we want to wish you and your families all the best for a healthy and happy holiday, and look forward to more (frequent) posts in 2010. ~The team at Lexalytics