Semantria Goes Pentalingual
January 1, 2013
Semantria is a text analytics and sentiment analysis solutions company. In order to reach a new clientele as well as work with companies with an international base, “Semantria Announces Content Classification and Categorization Functionality in 5 Languages.” Semantria now speaks English, Spanish, French, German, and Portuguese.
To power its categorization functionality, Semantria uses the Concept Matrix. It is a large thesaurus that used Wikipedia in its beta phase. After digesting Wikipedia, the Concept Matrix created lexical connections between every concept within it. Semantria developed the technology with Lexalytics and the Lexalytics Salience 5 engine powers the Concept Matrix. The Concept Matrix is a one of a kind tool that organizes and classifies information:
“Seth Redmore, VP Product Management and Marketing at Lexalytics, explains; ‘Text categorization requires an understanding of how things are alike. Before the Concept Matrix, you’d have to use a massive amount of training data to “teach” your engine, i.e. ‘documents about food’.’ And, he continues, ‘With the Concept Matrix, the training’s already done, and by providing Semantria a few keywords, it drops your content into the correct categories.’ ”
A piece of software that does all the organizing for you, how amazing is that? If it “ate” Wikipedia and made lexical connections, what could it do with Google, Bing, the entire Internet?
Whitney Grace, January 01, 2013
Sponsored by ArnoldIT.com, developer of Augmentext
Lexalytics Rolls out Native Phrase Based Sentiment in Spanish
October 28, 2012
I wanted to call attention to Lexalytics push into the Spanish language. In a couple of weeks you will learn about a remarkable technology which does not require “language packs.” I already wrote about the language innovations of Bitext in Madrid, Spain.
The Lexalytics’ approach, according to “Lexalytics Announces Availability of Native Phrase-Based Sentiment in Spanish,” is:
the only company to provide phrase-based sentiment in any language, providing unparalleled opportunities for tuning and customization for any application involving text. All of Lexalytics’ language packs are native to the language, with no translation step, so that all nuances of sentiment are captured directly without confusion from a machine translation step. Lexalytics’ Salience Engine is a market leading text analytics engine, used by industries as varied as social media monitoring, manufacturing, and pharmaceuticals to determine the “who,” “what,” “where,” and “tone” that’s implicit in any piece of text. Salience supports a number of different text analytics functions, including Named Entity Recognition, Sentiment Analysis, Categorization/Classification, Summarization, Theme Extraction and more. In other words, if you have text, Salience can tell you what it means.
For more information about Lexalytics, navigate to www.lexalytics.com.
Stephen E Arnold, October 28, 2012
Measuring Emotion in the Enterprise
August 24, 2012
We thought SharePoint incorporated social functions. We also thought Fast Search offered sentiment analysis via Lexalytics‘ technology. More must be needed, since CIO now declares, “Yammer Lets Organizations Measure Emotions in Enterprise Social Networks.” The write up informs us:
“Yammer is adding functionality to its cloud-based enterprise social networking (ESN) software that lets organizations gauge the types of emotions expressed in employee posts.
“The new capability will be provided via an integration with Kanjoya, whose Crane software is designed to identify and analyze ‘sentiment’ in text, Yammer said on Thursday.
“Yammer customers who sign up for this feature will have a new Crane dashboard in their Yammer admin console that will describe the prevalent mood in reactions from employees in the ESN about specific topics.”
The example given—use the software to analyze emails and other communications to determine how employees feel about a recent benefits change.Crane tracks about 80 different emotions; it allows administrators to search by keywords, narrow reactions by office or department, and create graphical representations of their workers’ feelings.
I know such a tool can be more efficient than simply asking employees for their opinions, especially in large organizations. Still, I just can’t ignore the Orwellian aftertaste left by such innovations. Maybe it’s just me.
Cynthia Murrell, August 24, 2012
Sponsored by ArnoldIT.com, developer of Augmentext
Lexalytics and FutureEverything Join Forces to Analyze London Olympics Sentiment
August 23, 2012
To further add to the hype of the London Olympics, text analysis firm Lexalytics has announced that it has partnered with FutureEverything with the goal of analyzing the overall sentiment during the said event. “Lexalytics tracks mood of London Olympics” describes how they’re set on accomplishing this:
“The Amherst-based software business has provided Salience, a multi-lingual text analysis engine that is integrated into systems for media monitoring, analysis and business intelligence, to Emoto, a project by FutureEverything.
… Launched this week, Emoto provides the worldwide mood in response to events that are taking place in London 2012. The project tracks micro-blogging sites such as Twitter for themes that are related to the Olympic Games and then analyzes the messages for content and tone, according to the company.”
The public can then access this information via the Emoto website and through the Android mobile app aptly named Emoto in London.
While we all used to think that emotions and computers just don’t mix, Lexalytics has done a good job of getting a lifeless, emotionless machine quantify some sentiment and draw out meaning from text. Of course, the company is far from perfecting this technology and is currently refining it. But once it does, I’m really excited what sort of big applications will emerge, particularly in the area of mobile tech. I can imagine our phones summarizing our emails for us complete with the action items. What do you think?
Lauren Llamanzares, August 23, 2012
Sponsored by ArnoldIT.com, developer of Augmentext
IBM Combines and Expands Decision Management Tools
June 29, 2012
IBM has been working hard to build its technology treasure trove; it has acquired over 30 companies, captured hundreds of analytics patents, and made deals with over 27,000 business partners. Now Yahoo Finance reveals, “IBM Launches New Class of Analytics Software to Improve Decision Making.” So, it appears that after many acquisitions, we now have a new “class” of analytics. How can this be?
The recent release of IBM’s Operational Decision Management software combines the company’s Analytical and Operational Decision Management tools. The combination, the press release asserts, empowers the software to accurately suggest the next best action to its users and their employees. The write up emphasizes:
“In a single platform, IBM has combined the power of business rules, predictive analytics and optimization techniques through intuitive interfaces that allow users to focus on specific business problems. The resulting decision can be consumed by existing pre-packaged or custom-built applications, including many applications on the mainframe. The platform also takes advantage of IBM InfoSphere Streams technology where big data can be analyzed and shared in motion, providing real-time decision making in environments where thousands of decisions can be made every second.”
IBM also added a new social network analytics feature which expands sentiment analysis capabilities. See the write up and other links above for more information on the software. We agree that these developments may be a welcome evolution. A whole new class of analytics, though? That may be a bit much.
Cynthia Murrell, June 29, 2012
Sponsored by PolySpot
Social Media Analytics Finds 98.6 Percent Positive Sentiment Towards Rock of Ages
June 27, 2012
Have you ever wondered if it was possible to accurately predict a successful motion picture?
If so, wouldn’t the owner of this technology invest in winning films? MarketWatch recently discussed this very topic in the article “Social Media Sentiment Strongly Positive Toward ‘Rock of Ages’ Despite Film’s Disappointing Box Office.”
According to the article, Attensity, a social analytics and engagement provider, has released a report analyzing public reaction in social media to the movie, Rock of Ages by using the company’s social analytics application Attensity Analyze.
After looking at sites like Twitter, Facebook, news sites, forums, videos and other social sources before and after the release, the report found:
“Attensity’s data reveals that the already positive sentiment toward Rock of Ages, in fact, grew over 10 percent after the film’s premiere. Positive sentiment for Tom Cruise in the movie also increased, moving from 47.87 percent to 52 percent. On the other hand, critics of Tom Cruise jumped on the opportunity to post their negative comments about the actor and his participation in Rock of Ages, adding to the small amount of negative sentiment and arguably playing a role in the film’s lackluster opening weekend numbers.”
While researchers discovered an overwhelming 96.8 percent positive sentiment toward Rock of Ages, can this technology be applied to all movies and actually predict a film’s success? or does it merely pick up on the excitement surrounding it?
Jasmine Ashton, June 27, 2012
Sponsored by PolySpot
Wand Taxonomy Asserts Sentiment Analysis on Structured and Unstructured Content
June 5, 2012
We are continuing to see sentiment analysis play an integral role in business intelligence and enterprise search. The news release, ”Information Builders Adds Sophisticated Sentiment Analysis Capabilities to Its Strategic Business Intelligence Platform” explains the addition to Information Builders’ WebFOCUS Magnify platform.
While much attention has been placed on sentiment analysis of unstructured content from Facebook and Twitter, this solution offers these same capabilities on structured data. As Magnify indexes content, the Wand Taxonomy server analyzes and determines the content’s overall mood as positive, negative, or neutral, and returns a score to Magnify.
Gerald Cohen, president and CEO of Information Builders was quoted stating the following:
“The information hidden within the nuances of human speech has historically been very difficult to extract in an automated fashion. By integrating the Wand Taxonomy server into WebFOCUS Magnify, we’ve created an incredibly powerful tool, which enables our customers to uncover the tone of their enterprise content. With WebFOCUS Magnify, the financial impact of emotion is now measurable.”
This top-notch tool from the taxonomy company Wand is the next-generation technology behind what Information Builders now offers. Without it, sentiment analysis on both structured unstructured data would not be possible—or more importantly, searchable.
Megan Feil, June 5, 2012
Sponsored by PolySpot
The Invisibility of Open Source Search
March 27, 2012
I was grinding through my files and I noticed something interesting. After I abandoned the Enterprise Search Report, I shifted my research from search and retrieval to text processing. With this blog, I tried to cover the main events in the post-search world. The coverage was more difficult than I anticipated, so we started Inteltrax, which focuses on systems, companies, and products which “find” meaning using numerical recipes. But that does not do enough, so we are contemplating two additional free information services about “findability.” I am not prepared to announce either of these at this time. We have set up a content production system with some talented professionals working on our particular approach to content. We are also producing some test articles.
Until we make the announcement, I want to reiterate a point I made in my talks in London in 2011 about open source search and content processing:
Most reports about enterprise search ignore open source search solution vendors. A quiet revolution is underway, and for many executives, the shift is all but invisible.
We think that the “invisible” nature of the open source search and content processing options is due to four factors:
Most of the poobahs, self appointed experts and former home economics majors have never installed, set up, or optimized an open source search system. Here at ArnoldIT we have that hands on experience. And we can say that open source search and content processing solutions are moving from the desks of Linux wizards to more mainstream business professionals.
Next, we see more companies embracing open source, contributing to the overall community with bug fixes and new features and functions. At the same time, the commercial enterprises are “wrapping” open source with proprietary, value-added features and functions. The leader in this movement is IBM. Yep, good old Big Blue is an adherent of open source software. Why? We will try to answer this in our new information services.
Third, we think the financial pressure on organizations is greater than ever. CNBC and the Murdoch outfitted Wall Street Journal are cheering for the new economic recovery. We think that most organizations are struggling to make sales, maintain margins, and generate new opportunities. Open source search and content solutions promise some operating efficiencies. We want to cover some of the business angles of the open source search and content processing shift. Yep, open source means money.
Finally, the big solutions vendors are under a unique type of pressure. Some of it comes from licensees who are not happy with the cost of “traditional” solutions. Other comes from the data environment itself. Let’s face it. Certain search systems such as your old and dusty version of IBM STAIRS or Fulcrum won’t do the job in today’s data and information rich environment. New tools are needed. Why not solve a new information problem without dragging the costs, methods, and license restrictions of traditional enterprise software along for the ride? We think change is in the wind just like the smell of sweating horses a couple of months before the Kentucky Derby.
Our approach to information in our new services will be similar to that taken in Beyond Search. We want to provide pointers to useful write ups and offer some comments which put certain actions and events in a slightly different light. Will you agree with the information in our new services? We hope not.
Stephen E Arnold, March 27, 2012
Sponsored by Pandia.com
Attensity: Friday Night Spam Fest
December 10, 2011
Short honk: Here’s an opinion for my one or two readers. I am confused about email marketing from search and content processing companies. Is spam a best practice? Is spam a signal of marketing need or sales desperation? Is spam better than relying on satisfied customers to generate referrals?
ArnoldIT does not do “spam” via email. Whenever I give a talk, I am a veritable Iowa-inspired food production factory of low grade calories. But at age 67, what do you want from a semi retired goose in rural Kentucky?
Here’s the story:
I was at dinner on December 9, 2011, and my wretched mobile device buzzed. I thought I had the gizmo on silent.
Wrong.
A quick look and what do I see, fork paused with a chunk of fried spam half way to my goosely bill. In my opinion, spamming me in Harrod’s Creek during dinner time is the email equivalent of an 800 call from a telemarketer pitching a roof repair deal.
Digital spam. Friday night. Dinner time. Brilliant I suppose.
Here what I received, ruining my appetite for the “real” stuff I was nibbling at the time: “Attensity to Deliver Real Time Audience Analytics on Republican Debate.” Who mailed this missive? sender@attensity.com. Okay, spam mavens, get that email address: sender@attensity.com.
What does Attensity promise me as my real spam cools?
Well, the goose is energized. Here’s the low calorie pitch:
The reports will be driven by Attensity’s real-time social analytics solution, which gives organizations the ability to monitor and analyze over 75 million online and social media sources, as well as internal sources such as emails, surveys and communities, and extract business insights from those conversations. The solution is part of Attensity’s award-winning suite of multi-channel customer analytics and response applications.
Believe it or not, Attensity, one of the “leaders” in understanding the “voice of the customer” or sentiment analysis found to evoke sentiment from me. I don’t think about Attensity as a customer support outfit. Nope. Nope. Nope. I think about Attensity’s roots and its more fascinating line of business. Navigate to LinkedIn and learn this:
Welcome to Attensity Government Systems — the broadest suite of semantic applications and engines to help you realize your agency objectives through the power of text. Attensity’s products and solutions, our dedicated government field engineering team, along with our network of defense, consulting, and solutions integrators are delivering results every day to key government agencies in intelligence, law enforcement, civilian service, and defense. By selecting and implementing Attensity’s solutions, these organizations are better understanding and responding to citizen needs, and connecting the dots to prevent terror and crime. Source: http://www.linkedin.com/company/attensity-government-systems
To put this snippet in context, you may find these links helpful.
- Reading conversations with some “color” at this link
- AGS launch. You can request more information here
- Triple search
- “Attensity offers to listen for governments, law enforcement”
- Attensity Analyze 5.5 Release Provides Large-Scale Data Grid Offering for Voice of the Customer Analytics.
Who funded Attensity? Lots of folks, including an important government agency? Here’s a link which may be of interest.
Now what’s fascinating is that Attensity is into the voice of the customer thing.
In my own algorithmic method, the Attensity marketing effort gets an “unsatisfactory” for email marketing effectiveness. I assume an azure chip consultant, a former middle school teacher, or a failed search engine optimization expert cooked up this campaign.
Here’s a thought.
Check out the non spamming alternatives to Attensity. You can get sentiment methods from folkslike ExpertSystem, ClearCI.com, the French outfit PolySpot, and Infonic Lexalytics operation, among others.
One nagging question for me: Why is Attensity spamming me on Friday night. 8:33 pm?
Brilliance, desperation, a Hail Mary from a football university in Utah?
Stephen E Arnold, December 10, 2011
Freebie, gentle reader, freebie. The goose’s feathers are ruffled.
Lexalytics Trains Your Computer!
September 27, 2011
Lexalytics competes in the realm of text analysis. Its Salience engine helps companies track what people are saying about their products on the internet. Seth Redmore, VP of Product Management at Lexalytics, talks sentiment analysis with David Cox in, “Train Your Computer, Monitor Your Brand Online Using Sentiment Analysis.”
Sentiment analysis is quite a task for a computer. Language is shaded with tone and intonation and the same line of written text can often mean two very different things. Redmore’s cites how internet buzz surrounding the BP oil spill was incorrectly interpreted as positive by computer systems. We learned:
When you looked at the content, the way it was being described was that it was the “biggest,” “largest” spill–not “worst.” That’s a hard thing to wrap your head around. I as a human know an oil spill is bad, but when a machine is interpreting it, from the perspective of the oil spill, things are good.
The field is not perfect yet, but Redmore sees exciting advances on the horizon. Wikipedia could be harnessed as a natural language tutorial for computer systems. In-person communicates will continue to be shaped by the technologies that make online or virtual communications possible. Keep an eye on Lexalytics for the newest advances in NLP and artificial intelligence. Oh, and as for training my computer, I am waiting. A combination of Watson and Salience might be an interesting combination for a TV game show demo too.
Emily Rae Aldridge, September 27, 2011
Sponsored by Pandia.com
-
- Subscribe to Beyond Search
Feature archive
News archive
-
