GeoSpark Analytics: Real Time Analytics
April 6, 2020
In late 2017, OGSystems chopped out some of the firm’s analytics capabilities. The new company was Geospark Analytics. The service provided enabled customers like the US Department of Defense and FEMA to obtain information about important new events. “Events” is jargon for an alert plus data about something that is important.
“FEMA Contractor Tracing Coronavirus Deaths Uses Web Scraping, Social Media Monitoring” explains one use of the system. The write up says:
Geospark Analytics combines machine learning and big data to analyze events in real-time and warn of potential disruptions to the businesses of high-dollar private and public clientele…
Like Bluedot in Canada, Geospark was one of the monitoring companies analyzing open source and some specialized data to find interesting events. The write up continues:
Geospark Analytics’ product, called Hyperion, the namesake of the Titan son of Uranus (meaning, “watcher from above”), fingered Wuhan as a “hotspot,” in the company’s parlance, within hours after news of the virus first broke. “Hotspots tracks normal patterns of activity across the globe and provides a visual cue to flag disruptive events that could impact your employees, operations, and investments and result in billions of dollars in economic losses,” the company’s website says.
Engadget points out that there are a couple of companies with the name “Geospark.” DarkCyber finds this interesting. This statement provides more color about the Geospark approach:
Geospark Analytics claims to have processed “6.8 million” sources of information; everything from tweets to economic reports. “We geo-position it, we use natural language processing, and we have deep learning models that categorize the data into event and health models,” Goolgasian [Geospark’s CEO] said. It’s through these many millions of data points that the company creates what it calls a “baseline level of activity” for specific regions, such as Wuhan. A spike of activity around any number of security-, military-, or health-related topics and the system flags it as a potential disruption.
How does Geospark avoid the social media noise, bias, and disinformation that finds its way into open source content? The article states:
“We rely more on traditional data sources and we don’t do anything that isn’t publicly available,” Goolgasian said, echoing a common refrain among data firms that fuel surveillance products by mining the internet itself.
Providing specialized services to government agencies is not much of a surprise in DarkCyber’s opinion. Financial firms can also be avid consumers of real-time data. The idea is to get the jump on the competition which probably has its own source of digital insights.
Other observations:
- The apparent “surprise” threading through the Engadget article is a bit off putting. DarkCyber is aware of a number of social media and specialized content monitoring services. In fact, there is a surplus of these operations and not all will survive in the present business climate.
- Detecting and alerting are helpful but the messengers failed to achieve impact. How does DarkCyber know? Well, there is the lockdown.
- Publicizing what companies like Geospark and others do to generate income can have interesting consequences.
Net net: Some types of specialized services are difficult to explain in a way that reduces blowback. Some of the blowback have significant impact on social media analytics companies. The Geofeedia case is a reminder. I know. I know. “What’s a Geofeedia some may ask?”
Good question and DarkCyber thinks few know the answer. Plucking insights from information many people believe to be privileged can be fraught with business shock waves.
Stephen E Arnold, April 6, 2020
Comments
-
- Subscribe to Beyond Search
Feature archive
News archive
-
