[Editor's Note: This guest post is by Tom Reamy, Chief Knowledge Architect and founder of KAPS Group, a group of knowledge architecture, taxonomy, and eLearning consultants. Tom has 20 years of experience in information architecture, intranet management and consulting, and education and training software.  Tom will be presenting a tutorial, Text Analytics for Semantic Applications and moderating a panel, Emotional Semantics - Beyond Sentiment at the upcoming SemTechBiz Conference in San Francisco.]

While sentiment analysis continues to generate a lot of press, it is not clear how much real value organizations are deriving from it.  One reason for that is that the standard approach to sentiment has been mostly statistical and/or long lists of sentiment terms.  However, if you add in other, advanced text analytics capabilities such as auto-categorization using advanced operators, you can not only develop more sophisticated sentiment analysis, you can also develop a whole new class of applications that either enhance and/or go beyond simple sentiment analysis.

These advanced operators include such commands as DEST_6 (count two words as a positive indicator only if they are with 6 words of each other) or SENT (only count words in the same sentence).

Read more

SemTechBiz is Less Than 2 Weeks Away

The Semantic Tech & Business Conference (SemTechBiz) is coming to San Francisco on June 3-7! Join us for case studies, innovative panels, tutorials, and keynotes that will provide you with practical advice, hands-on guidance, and breakthrough approaches to solving business problems with semantic technology. Passes go up $200 at the door. Sign up now and save !

Market Strategies International recently released the first edition of what it says will be an annual Social Media Brand Index, a measure for brands both of consumer-generated social media about them and of their own sponsored content. The Index takes into account four components. Volume, or the amount of buzz about a brand online, is one of them — and its most highly weighted component, too. The others take their cue from what we might call more meaning-related measures, sentiment analytics and semantic markup among them.

For example, there’s net Sentiment, which Market Strategies says represents the ratio of positive to negative sentiments expressed about a brand based on automated natural language processing of the content of posts, comments and mentions. Another component, Positive Emotions, seems to flow from that measure, representing the number of content items that are identified as having the warm fuzzies about them, again based on automated coding of content.

Read more

Last month Magistrate Judge Andrew Peck, of the U.S. District Court for the Southern District of New York, issued an opinion in a gender discrimination case that had this to say about computer-assisted review: “Computer-assisted review is an available tool and should be seriously considered for use in large-data-volume cases where it may save the producing party (or both parties) significant amounts of legal fees in document review.”

In doing so, he just also may have made a case for the legal profession to do some more investigation of semantic technology in order to cope with its own Big Data challenges. In the mid-2000s, the Federal Rules of Civil Procedure were amended to take into account electronic discovery, so that both sides in a legal challenge would have to confer within sixty days of filing to disclose how they handled digital data. The beauty of the American legal system is that it requires each party to pony up information that is meaningful and responsive to the facts of the case. The dark side is that the proliferation of data inside businesses means employees are creating more and more data in lots of different ways, which means legal staff has to spend a lot more time sifting through digital realms of structured and unstructured information to discover what may have to do with a lawsuit or government investigation, what is responsive to the other party’s document request, and what is privileged information, too.

“It’s created a cottage industry in temp staffing – now there are temp lawyers, contract attorneys who work from $30 to $75 an hour,” says Jay Leib, Chief Strategy Officer at kCura, which makes the Relativity Assisted Review e-discovery text analytics software based on latent semantic indexing technology. “Just like we outsource factory workers, there are outsourced attorneys overseas doing document review to combat the amount of data that’s sprung up.” There is so much data out there that it’s entirely possible that a $3 million lawsuit could cost $6 million to litigate, he says.

Read more

Seth Grimes recently set the record straight regarding the terms “text analytics” and “semantic content enrichment.” Grimes starts with a few definitions of text analytics: “Text analytics is a set of software and transformational steps that discover business value in ‘unstructured’ text. (Analytics in general is a process, not just algorithms and software.) The aim is to improve automated text processing, whether for search, classification, data and opinion extraction, business intelligence or other purposes.” He adds, “Text analytics draws on data mining and visualization and also on natural-language processing (NLP). Supplement NLP with technologies that recognize patterns and extract information from images, audio, video and composites and you have content analytics.” Read more

Lexis Nexis has announced a new release of Lexis Advance which includes “content enriched using SRA’s industry-leading NetOwl® text and entity analytics technology, delivering a more sophisticated semantic search capability to enable legal professionals to conduct better, faster and more relevant research. As one key part of the Lexis Advance application, NetOwl’s entity and relationship extraction capabilities semantically enrich the vast amounts of text-based content offered to legal professional customers.” Read more

We often discuss text analysis and natural language processing (NLP) here at SemanticWeb.com, so we were pleased to see this nice, if incomplete, survey of tools and services for NLP. The article begins, “Although Natural Language Processing (NLP) has been around since the 1950s in the computer science world, more and more uses for this powerful technology are being uncovered every day. Search engines like Google use NLP as one of the ways they extract meaning from web pages, Microsoft has a whole team of people working on NLP projects, and a number of universities have dedicated major resources working on the advancement of NLP, but what about everyone else? NLP has many uses going beyond behemoth websites including uses for the enterprise, small business, and end users.” Read more

A recent article reminds businesses that the semantic web is here and asks what they’re going to do about it. The article states, “Web 3.0 has enabled people and machines to connect, evolve, share and use knowledge. Looking even further ahead, with Web 4.0 wherein we have a self-learning intelligence, the distinctive advantage will come from the combination of semantic technologies, like text analytics, along with other analytical models that extend semantic interoperability. In other words, having feedback loops for improving models – utilizing both semantic representations along with those from areas such as data mining, forecasting, optimization, simulations, and alike. Using these technologies, organizations will create that higher-order learning that did not exist using any one of those methods in isolation.” Read more

On the way from Saplo – that’s the company whose tradeshow trademark is the wearing of shocking green suits by CEO Mattias Tyrberg and his co-founders – is a Prediction API for its text analytics platform. The vendor already provides through its API access to services for entity and topic tagging, related and similar articles, sentiment analysis and contextual recognition upon which developers can build applications.

The Prediction API, due around summer’s end, seeks to predict outcomes from text, as Tyrberg describes it. That is, it assesses how a company name or any other word has been described in text and  finds a correlation between that and expected outcomes, such as sales volumes.

It works by having the user submit historic text and historic data points, from which the technology analyzes the relationship between the meaning of the text and the data that the user wants to have predicted (it also will return data of how good it believes it can predict the outcome, Tyrberg says). After that, the user submits new text data to Saplo for a new time period, and based on that text Saplo returns a prediction of the next outcome.

“Think of it like BI,” says Tyrberg. “You might be able to predict new numbers based on previous numbers, but a lot of information that is available is in written text, and we can find the correlations between the meaning of that text and numerical data.”

Read more

Photo Courtesy: Flickr/Vironevaeh

As we get ready to celebrate the July 4 holiday here in the States, there’s a lot to cheer for about how the Semantic Web can be a force for good when it comes to creating an informed and empowered populace upon which democracy depends. Examples of this include the work being done by the Tetherless World Constellation at Rensselaer Polytechnic Institute to translate open government datasets into RDF and create applications using linked government data (read more here); and work by the Sunlight Foundation, which does things such as make semantic information in its OpenCongress wiki available via an API with the help of the Semantic MediaWiki extension.

The departure of Vivek Kundra as federal CIO that takes effect in August  – together with the planned funding cuts to e-government initiatives, such as the Data.gov open data effort –  may take its toll on the data that’s available to Semantic Web initiatives at the federal level. On the other hand, states themselves are plowing ahead, most recently with the launch of the State of Illinois Open Data site that’s built on Socrata’s platform. Socrata supports a number of different formats for developers, RDF among them, with its Open API. Cities won’t be left out of the mix, either, with New York, San Francisco, and Chicago, to name a few, pursuing this agenda.

But let’s take a moment to look beyond government data.

Read more

At SemTech, OpenAmplify’s founder and CEO Mark Redgrave and co-founder and CIO Mike Petit talked to The Semantic Web Blog about the company’s cloud-based technology for extracting meaning from text and what’s next on the horizon.

Most recently, Radian6 incorporated OpenAmplify’s technology as part of its Insights social media monitoring service. OpenAmplify includes a CRM Insight that automatically filters and tags individual comments into to-do categories, such as comment, engage or support.

OpenAmplify expects shortly to have something to show the market about its ability to deal with one of the vexing problems around pronoun ambiguity in text analytics. Watch the video for some details: