Page 14 - GCN, Oct/Nov 2016
P. 14

ADVANCED ANALYTICS
S
S
P
PO
ON
N
S
S
O
OR
RE
ED
DC
C
O
ON
NT
T
E
EN
N
T
T
NEW FRONTIERS IN ADVANCED ANALYTICS
INTELLIGENT SEARCH CREATES CONNECTIONS
New applicaH
JOHN FRANK
CEO, DIFFEO
OW DO I KNOW what I missed? Traditionally, a research
analyst could only know she’d covered those sources that she had queried directly. A new
frontier in text analytics is expanding the
user’s reach by automatically analyzing in-progress notes, such as an email in Outlook or a page in OneNote. These new
This new application of text analytics accelerates both junior and senior analysts. It learns from the user’s triage of new content, and provides a quick picture of the knowledge graph surrounding a user’s notes. By keeping track of which recommendations a user accepts or rejects, the tool “hangs in there” as the researcher’s thoughts evolve. For example, with traditional search tools, a researcher tracking an organization’s activities might miss a document indicating that one of its partners or suppliers built a new facility next door – a classic unknown that this new approach can detect.
All organizations that process information will benefit from this new kind of intelligent search. From analyzing advanced threats to solving a backlog of information requests, putting machine intelligence into your in-progress documents allows you to uncover the whole story, so you can ask the big questions immediately.
Read more from John Frank at carahsoft.com/innovation/Frank.
Location dataS
tion applies existing text analytics to take a predictive approach.
systems recommend documents that fill in knowledge gaps by automatically comparing the user’s text to data in vast enterprise repositories and also the Deep Web.
Instead of only applying text analytics to source documents, this new approach uses extractions from the user’s in-progress document to query for new data and to predict how much new knowledge each document can reveal to the user. This allows machines to operate at human-level accuracy, and humans to operate at machine scale.
HARNESSING THE POWER OF LOCATION DATA
attached to social media posts can provide valuable intelligence.
OCIAL MEDIA DATA—the information gathered from posts on Instagram, Facebook, Twitter, Vine, Periscope, and more—is the richest set of high-volume, location-tagged
actionable data. With this data, agencies have what they need to improve real-time operations and deliveries, as well as stay on top of the latest security threats, natural disasters, and other important events.
Agencies can use location data in social media posts to monitor certain areas. If the word “flood” frequently occurs in one part of Louisiana, for example, emergency management can immediately dispatch first responders.
As sensors become a bigger part of the picture, they also can be a valuable source of intelligence. If there is a natural disaster, bombing, or other important event, agencies can use this location information, embedded in everything from vehicles to inventory, to understand where every asset is at any given time.
Agencies are drowning in data. What they really need is actionable data that is relevant to them. Social media and location data will only become more important over time, so deploying the right technology to help agencies leverage that data is key.
Read more from Phil Harris at carahsoft.com/innovation/Harris.
data in human history. And it continues to grow richer and more valuable with every minute.
While federal agencies have been mining social data for intelligence for some time, traditional
search mechanisms miss rich, actionable location data, the key component to generating immediate response and awareness. That was the “big idea” back in 2010. We asked ourselves, “What if you could add the ‘where’ element to the ‘who’ and ‘what’ element of social media?”
That’s a powerful question. The combination of real-time social media data from multiple sources and location data, combined with more static data like locations of roads, utilities, physical assets, and maps, gives you highly relevant and
PHIL HARRIS
CEO, GEOFEEDIA
S-14


































































































   12   13   14   15   16