by clicking on the page. A slider will appear, allowing you to adjust your zoom level. Return to the original size by clicking on the page again.
the page around when zoomed in by dragging it.
the zoom using the slider on the top right.
by clicking on the zoomed-in page.
by entering text in the search field and click on "In This Issue" or "All Issues" to search the current issue or the archive of back issues respectively.
by clicking on thumbnails to select pages, and then press the print button.
this publication and page.
displays a table of sections with thumbnails and descriptions.
displays thumbnails of every page in the issue. Click on a page to jump.
allows you to browse through every available issue.
GCN : November 2012
FEATURE BIG DATA health and safety -- don't want to talk about their text analytics projects. According to McNeill, that reluctance arises from a number of different con- cerns. Agencies that are using text ana- lytics to look for fraud or to detect other questionable activity don't want to tip their hands to those doing the activity. "Smart organizations are doing purpose- ful activity to get around government," said McNeill, "so government talking about how they are actually finding them only provides them with ammunition." Jamie Popkin, a managing vice presi- dent at the Gartner Group, agrees. "When you look at the history of where this started it came out of the military and intelligence-gathering wings of gov- ernment so I'm not surprised many peo- ple don't want to talk about it," he said. Whether it's being used for rule-mak- ing efforts, litigation discovery, detect- ing compliance and fraud, or monitoring activity for trade negotiations, the spe- cific data being monitored and the tools and techniques being used, "may not be something that you want so clearly pub- licized," he said. And monitoring and analysis of social media is even more sensitive. "I would separate social media as something of a special case," said Popkin. "If the gov- ernment is trolling social media, having GCN NOVEMBER 2012 • GCN.COM 21 CASE STUDY: HOW NASA IS USING TEXT ANALYTICS TO IMPROVE AVIATION SAFETY NASA's Aviation Safety Program has been applying text analytics to the generally non-controversial goal of scanning hun- dreds of thousands of unstructured text reports made by pilots, mechanics and other staff to find patterns that may help improve airline safety. "We've been developing and imple- menting different text mining algorithms for analyzing aviation safety reports as well as other safety-related reports are several years," Ashok Srivastava, project manager for the System-wide Safety and Assurance Technologies project for the Aviation Safety Program, told GCN. "By doing these kinds of analyses we hope to get a better understanding of what is go- ing on in the aviation system with respect to different safety concerns." Specifically, Srivastava says, the focus is on the reports submitted to the Aviation Safety Reporting System, a NASA pro- gram that collects incident reports from pilots, air traffic controllers and others. "It's a remarkable database," said Sriv- astava. "If you look at these reports you can find discussions from pilots about certain incidents, you can also see issues that are coming up that are mechanical, or passenger safety concerns. One of the key issues that we are interested in ad- dressing is why do aviation safety inci- dents occur? What are the precursors? What are the drivers to different safety incidents? The technologies are giving us new ways of developing that insight." Before Srivastava's team started apply- ing text analytics to the data it was only reviewed by human analysts. And while humans haven't been taken entirely out of the loop, they can't catch patterns that oc- cur across and between disparate reports as effectively as text analytic programs. The team's initial efforts used natural language processing techniques to ana- lyze the data. "That got us to a certain point," said Srivastava, "but we started to make a shift toward using more statistical methods for analyzing the data based on machine learning." With NLP methods, explains Srivas- tava, there was a lot of tagging of words and phrases using human-built rules that were encoded into the computer system. And then that information is used to ana- lyze the text and determine what type of anomaly it was describing -- a runway incursion, a bird strike, etc. The problem is, writing all those rules is very human labor intensive. "The machine-learning approach is very different," said Srivastava. "It takes all of the data and a few examples of the way different reports are categorized and then we developed statistical techniques to take documents and predict which cat- egory they fell into. It didn't require the same degree of rule building as in natural language processing. It also reduced the amount of cost involved in analyzing the data because it didn't require handcrafted rules." As benevolent as NASA's project is, Srivastava says that it is not entirely with- out controversy. "One of the things that we are really interested in doing in the fu- ture is analyzing in tandem the text docu- ments with the numerical data that come from the flight data recorder," he said. "But the carriers don't let text reports get linked with the flight data recorders. I think there are number of issues. There are privacy concerns." Already, says Srivastava, the team's work is making a mark. "Our technology has been transferred to major carriers in the United States and to a number of agencies, including the Federal Aviation Agency. " • --- Patrick Marshall