EnterpriseSearchCenter.com Home
  News   Features   White Papers   Research Reports   Web Events   Conferences  
 
RESOURCES FOR EVALUATING ENTERPRISE SEARCH TECHNOLOGIES
February 03, 2010

Table of Contents

Customer experience and sentiment analysis
Faceted search for Contegra's Kaleido
LucidWorks ups the ante for Apache Solr
dtSearch Incorporates Faceted Search Through Contegra
Innovative Partners With EBSCO, Offers Improved Discovery
Kofax releases Express 2.0
Handcase Mobile Search Engine Hits Market
Autonomy, Precise Team Up for Media Intelligence Project
Collaborating for public safety
Analyze Anywhere from StoredIQ
Clarabridge Augments Data Mining with Kapow’s Web Technology

Customer experience and sentiment analysis

The notion that listening to your customer’s voice is important is well entrenched. Companies have long depended on data from customer surveys, call center transcripts and focus groups, captured in structured formats and handled through business intelligence applications, to help point the way to improved customer service, product enhancements and competitor vulnerabilities.

But the sheer volume of the customer choir in the Web 2.0 age often leaves companies scrambling to keep up. Publishing is now in the hands of the public, who have a vexing tendency to post with blunt honesty in unstructured formats via blogs, tweets, e-mails and forums about products and services that delight or disappoint them. And those opinions hold weight. A 2007 study by Jupiter Research (since acquired by Forrester), called “Social Networking Sites: Defining Advertising Opportunities in a Competitive Landscape,” found that 30 percent of frequent social networkers trust their peers’ opinions when making a major purchase decision, compared to the 10 percent who trust advertisements.

As Andreas Wiegend, former chief scientist of Amazon.com, predicted in a blog post for the Monitor Talent Group, “In 2009, more data will be generated by individuals than in the entire history of mankind through 2008.” Companies face a very real need not just to acknowledge the impact of unstructured social media on brand and product perception, but to understand and filter it sensibly, and to integrate it with structured customer data and get it into the hands of the right people to make it actionable.

For many companies, the burgeoning text analytics approach of sentiment analysis is becoming a critical component of their overall strategy, giving them a much-needed assist to stay responsive to customers, market opportunities and trends.

What is it?

In his white paper “Text Analytics 2009,” Seth Grimes, analytics strategist at Alta Plana, describes text analytics as “the software and the transformational steps that discover business value in ‘unstructured’ text.”

There’s special business value in discerning opinion, sentiment and subjectivity—the “voice of the customer”—in text as varied as blogs, forum postings, articles, e-mail and survey responses. That field of “customer experience analysis” applies sentiment analysis and other techniques to understand and help predict consumer behavior via text analysis coupled with analysis of customer transactions, profiles and demographics.

Vendors generally use a combination of statistical analysis of wordfrequency and co-occurrences with linguistics (involving lexicons, dictionaries and language rules) in an algorithmic approach to understanding exactly what the consumer is saying. Grimes, who will be presenting a talk in April on “Search for Sentiment” at the Search Engine Meeting 2010, which is co-sponsored by KMWorld, says, “The narrower you can frame the problem and the data you collect, the better, because you can then adjust your approach to match specific business requirements and information sources.”

The technological challenges are not for the faint-hearted or the linguistically timid. Suresh Vittal, analyst at Forrester, says, “For a long time, text analytics was a technology in search of a business need. Now, thanks to social media, the need is there; the question is whether the technology can ramp up fast enough to be commercial.” Early adoption by government agencies, which sought to apply text mining to mountains of classified documents, is giving way to more mainstream commercial demand from industries for whom customer perception is critical: hospitality, consumer brands and high-tech, among them.

Classifying the messy middle

Ours is a world in which online consumer reviews of hotels that might include the phrase “the lobby is baaaaad!” meant in a positive way, or a review of a holiday toy saying, “I would give this to all the children in my life, if I were Scrooge,” meant to disparage. Throw in slang, language evolution and socio-cultural gradations in word use, and you have a mammoth challenge for accurate computational treatment of opinion.

Larry Levy, co-founder and chief opinion gatherer at Jodange, an opinion utility that filters and aggregates thoughts, feelings and statements from traditional and social media, says accuracy remains a challenge in the industry. “The sentiment side is good at the two poles, positive and negative,” he says, estimating that Jodange’s Opinion Lens gets those sentiments right around 80 percent of the time. “But the neutrals are difficult. If you give four people in a room 100 neutral opinions and ask them to classify, even they will only agree 55 to 60 percent of the time.”

The level of granularity can also be important. If sentiment is assigned at a document level—that is, each tweet or blog post is assigned a positive, neutral or negative sentiment—how does the hypothetical tweet “I love Marriott’s bathrooms but the beds are lumpy” get classified? Marcel LeBrun, chief executive officer of Radian6, which offers clients a platform to listen, measure and engage with customers across the social web, cautions, “Ratings need to be assigned on a subject level at a minimum; a solution that assigns them at a document level is going to miss something.”

Whose opinion is it?

Even if a sentiment analysis tool were always accurate, the opinions don’t necessarily carry equal weight. LeBrun estimates that Radian6 customer Dell has 8,000 to 10,000 online conversations about its brand each day, which span the spectrum of positive to negative; the company needs to understand whose opinion actually has the power to move brand perception, and keep close tabs on those. “Sentiment analysis needs to be connected to social metrics and influence analysis to make sense,” says LeBrun.

Levy agrees, saying Jodange customers understand that listening to social media is important but now need help in filtering. “There is no longer the notion that trusted information only comes from The New York Times,” he says. “Once you get a handle on who is influencing your brand, that becomes actionable.” Influence analysis, analyzing digital breadcrumbs to see which individuals have the highest credibility and widest reach, should be a part of the overall text analytics strategy. By knowing in advance who the influencers are for your brand, you’ll be better prepared to manage crisis and opportunity effectively, reaching out to 20 key contacts instead of 10,000 questionable ones.

Taking sentiment out of the silo

There’s widespread agreement among vendors and analysts that text analysis is only as valuable as the actions it prompts. In a Forrester report from February 2009, called “Obstacles To Customer Experience Success,” a survey of 90 customer experience decision-makers from large North American firms found that 89 percent said that customer experience would be either very important or critical to their 2009 efforts, but a lack of cooperation across organizations remains a major obstacle.

When it comes to sentiment analysis, different functions are listening for different answers. A customer service manager needs insight into customer experience, a product manager wants to hear complaints or praise for features as well as product design ideas, and brand managers may be looking for competitive intelligence.

“It’s easy to turn on an application and get a feed of data,” says Sid Banerjee, CEO of Clarabridge, a provider of text mining software. “For our customers, acting on it is the hardest part of the equation. You must have an environment where people are culturally attuned to action.” Banerjee points out that where business intelligence solutions have traditionally been sold to the IT function, Clarabridge has had success selling its customer experience management solutions directly to the primary consumers of the data.

The challenge to the enterprise is to combine analysis of what is being said, by whom, with more structured customer intelligence data  in order to develop a robust customer engagement strategy. Forrester’s Vittal says that to break sentiment analysis out of the silo, “The platforms must be open and integratable. Customer intelligence data is still siloed, and there is a complexity gap that must be overcome.”

Clarabridge’s December 2009 announcement of a partnership with pollster Harris Interactive is an illustration of how it can be done. The companies plan to combine unstructured data from opinions about President Obama’s healthcare reform initiative, posted on social media and other online sites, with public opinion as measured through structured survey research, to paint a truer picture of citizens’ emotions and decision factors on that volatile issue.

Getting started

For companies that are just getting started with sentiment analysis, Radian6’s LeBrun suggests what he terms “the Yellow Brick Road” approach. “You have to pick up the social phone and listen to what’s being said, analyze and identify who the influencers are,” he says. “Step two is to start responding, not just by data mining but by building community.”

The third step is participation. By moving from metrics to diagnostics—understanding not just what is being said, but the root causes behind it—a company can truly begin to capitalize on the promise of text analytics. It’s another arrow in the quiver that can help companies understand and respond to the messages their customers are sending, loud though not always clear.  

Partial list of text analytics/sentiment analytics vendors

Attensity 

Clarabridge

Filtrbox

IBM

Jodange

Radian6

Scout Labs

SentiMetrix

SPSS

Synthesio

Temis

Teragram (a division of SAS)

To download the Alta Plana Text Analytics 2009 chart which shows the breadth of usage for text analytics tools go here: http://www.kmworld.com/downloads/60764/2085_chart-2.pdf

Back to Contents...

Faceted search for Contegra's Kaleido

Contegra Systems, which specializes in the design and development of Web sites for online information publishers and other search-centric applications, announced that it has developed faceted search for its Kaleido Search offering by integrating dtSearch APIs.

Contegra says faceted search provides users the ability to dynamically filter search results by attributes, letting users browse through results selecting criteria relevant to their search. It further claims that to date, faceted search has remained out of reach for many businesses because of design and programming costs. Contegra launched Kaleido Search to offer companies an out-of-the-box attractive user interface with an easy way to deploy faceted search, including plug-and-play operation with existing data sources.

Kaleido Search offers the ability to group search results by facet, the ability to "expand and collapse" facet selections, on-demand summaries of selected facets, and more. Kaleido Search enables these faceted search features in the context of a comprehensive solution for online data access that is fully customizable to suit any site.

The dtSearch engine can index more than a terabyte of data in a single index—as well as create and instantly search an unlimited number of indexes. The software offers more than 25 search options, including Unicode support.

Back to Contents...

LucidWorks ups the ante for Apache Solr

Lucid Imagination introduces two powerful new features for Apache Solr, which are available free of charge.

They include a comprehensive, well-organized Reference Guide documenting all of Solr’s important features and functions in a convenient e-book (pdf) format and a robust new installer. Featuring a well defined, easy-to-use setup wizard, the installer is said to make life easier for new and experienced Solr application developers alike.

For new users, the installer minimizes the complexities and reduces the time often associated with configuration and deployment of a Web service. The out-of-box experience of installing Solr becomes as simple as a few clicks of the "Next" button, also saving you any hassle of managing and installing source code. Support is built in for configuring either Tomcat and Jetty as the Solr platform, fully installed and configured just by checking a box.

Back to Contents...

dtSearch Incorporates Faceted Search Through Contegra

Contegra Systems and dtSearch announced that they had partnered to create Contegra Systems Kaleido Search, a faceted search solution that makes use of the dtSearch engine APIs. Kaleido Search gives users the ability to dynamically filter search results by various attributes and brings faceted search capabilities to companies that could not previously afford it due to programming and development costs.

Kaleido Search functions as an out-of-the-box offering, with a simple user interface and plug-and-play operation with existing data sources. With Kaleido Search, companies can search by facet, expand and collapse facet selections, acquire on-demand summaries of texts, and customize the suite for a company's particular site.

(www.contegrasystems.com, www.dtsearch.com)

Back to Contents...

Innovative Partners With EBSCO, Offers Improved Discovery

Innovative and EBSCO Publishing announced a new technology partnership between the two companies that will offer integrated access to a library's own EBSCOhost subscriptions through the Innovative Encore Discovery platform. The agreement will also allow Encore customers to add reading recommendations directly to catalog results for mutual customers using NovaList Select. Innovative will utilize the EBSCOhost Integration Toolkit to access metadata from EBSCOhost databases for which the library has an existing subscription.

In related news, Innovative announced deep article integration features for its Encore Discovery platform, designed to promote the most relevant article content alongside catalog results. The new feature is native to Encore, and streams enhanced data directly from content providers to deliver faster results.

When an initial search is made, Encore will preview top article results in the catalog results view, promoting the most current scholarly content on the first page. The abstract and, when possible, a direct link to the text will be visible. Encore will also make suggestions to clarify and continue searches on the article screen.

(www.iii.com)

Back to Contents...

Kofax releases Express 2.0

Kofax has unveiled Version 2.0 of Kofax Express, which it describes as an all-in-one scan-to-archive software package for image capture applications. The company reports V. 2.0 offers new features that enhance the application’s ease of use and expand its functionality, thereby increasing productivity and significantly reducing operating costs.

Kofax highlights the following new features and capabilities:

Automatic image file importing. The new version optimizes the FolderScan function, which allows the automatic import of image files (TIFF, PDF, JPG and BMP) from a folder directly into Kofax Express, better enabling capture from sources such as MFPs, fax servers and saved images.

Improved PDF support. Now supporting both PDF and PDF/A formats, Kofax Express 2.0’s compression is said to maintain crisp, clear color images delivered in file sizes associated with black-and-white images, leading to quicker downstream processing and improved efficiencies. The software also extends its OCR technology to expand its searchable PDF capabilities, allowing users to more easily and accurately search for data within PDF documents.

Advanced database support. Kofax Express 2.0 offers advanced database support capabilities. This includes the ability to connect to any ODBC-compliant repositories such as Microsoft Access, SQL Server or Oracle to instantly look up and then populate an index field value, thereby accelerating indexing tasks and improving accuracy. Also the software now features an export API that enables the creation of customized export connectors to virtually any repository, allowing users to increase efficiency while cost effectively leveraging existing infrastructure.

Back to Contents...

Handcase Mobile Search Engine Hits Market

Handcase has launched a new mobile search tool designed for small-screen devices such as smartphones. The search system, called Gune, is a meta-search tool that consults Google and Bing and delivers results to a single page.

(www.handycase.com)

Back to Contents...

Autonomy, Precise Team Up for Media Intelligence Project

Autonomy Corporation PLC, an infrastructure software company, and Precise, a U.K-based media intelligence company, have agreed on a strategic collaboration deal for the purpose of developing and marketing next-generation media intelligence services to the PR and communications sectors.

Precise will employ Autonomy's Meaning Based Computing technology to supplement its monitoring and analysis capabilities across the entire media spectrum, including broadcast, print, web, social media, and discussion forums.

The project will also feature the implementation of Chorus, a new media intelligence engine powered by Autonomy's Intelligent Data Operating Layer (IDOL).

(www.autonomy.com; www.precise.co.uk)

Back to Contents...

Collaborating for public safety

MuseGlobal has announced a strategic partnership with Capgemini Government Solutions to provide flexible content integration technology that has been designed to affordably connect, collaborate on, analyze, investigate and identify public safety risks. Using MuseGlobal's content connectors, law enforcement agencies will be able to extract key data from internal repositories and external sources at the federal, state, municipal, city and county levels to be accessed and integrated for analysis.

The companies say that as part of the Capgemini Intelligence Grid, MuseGlobal's customizable content connector software aims at aiding governments in rapidly setting up and easily managing new public security architectures. The Intelligence Grid is said to facilitate smooth interoperability of public security systems, enabling the active and efficient collaboration needed to identify and prevent new threats. Powered in part by MuseGlobal, the Capgemini Intelligence Grid allows the law enforcement agencies to connect to Internet and legacy systems with relative ease, harvest data from connected systems and simultaneously search connected systems to locate the content being sought. The agency requesting the data can then be provided with a consolidated view of all information found on all source systems regarding the subject search topic.

Back to Contents...

Analyze Anywhere from StoredIQ

StoredIQ has introduced Analyze Anywhere, which enables early case assessment (ECA) prior to preservation and collection, without requiring the movement of data from where it natively resides.

The company explains that prior to any collection of data, Analyze Anywhere gives legal counsel the ability to dynamically tune searches, review analytics and modify custodian lists to accurately narrow the preserved and collected set of data subject to the "duty to preserve," mitigating further legal risks and providing a legally defensible audit trail.

StoredIQ claims Analyze Anywhere can provide much deeper insight into ESI, enabling it to precisely find data beyond traditional custodian associations even in obfuscated data sources, such as file shares and SharePoint. Additionally, the offering is said to find and recommend additional, potentially relevant custodians that were not previously known to be connected to a matter.

The business context of data in its native location is not only available to the ECA user, says the company, but is also captured and pushed downstream to traditional review tools, enabling a more contextually rich review experience. StoredIQ adds that Analyze Anywhere is powered by an e-discovery workflow that includes dynamic visuals, detailed reports and intuitive dashboards to accomplish in-depth analysis of unwieldy amounts of discovered data. The user interface includes a running count of the files eliminated from consideration, and automatically calculates the potential savings from the formal review cycle.

Back to Contents...

Clarabridge Augments Data Mining with Kapow’s Web Technology

Clarabridge announced the establishment of a partnership with web data services developer Kapow Technologies that will incorporate elements of Kapow's product offerings into Clarabridge's Content Mining Platform. Under the terms of the partnership, Clarabridge will resell Kapow's Web Data Service through its Clarabridge VOC solution and will handle sales and marketing efforts for the combined offering. Clarabridge stated that the inclusion of Kapow's technology will give its customers deeper insight into their brands and tap into a wider range of content sources.

Clarabridge provides brand-oriented monitoring of numerous social media services and other forms of online discussion, allowing companies to analyze customer sentiment and impact in real time to derive useful market knowledge, improve customer care, and handle risk management and quality assurance.

(www.clarabridge.com, www.kapowtech.com)

Back to Contents...
 
[Newsletters] [Home]

Problems with this site? Please contact the webmaster. | About ITI | Privacy Policy