News Column

Researchers Submit Patent Application, "Geolocating Social Media", for Approval

September 9, 2014



By a News Reporter-Staff News Editor at Information Technology Newsweekly -- From Washington, D.C., VerticalNews journalists report that a patent application by the inventor RISHE, NAPHTALI DAVID (Miami Beach, FL), filed on February 19, 2014, was made available online on August 28, 2014.

The patent's assignee is The Florida International University Board Of Trustees.

News editors obtained the following quote from the background information supplied by the inventors: "Data mining refers to the analysis of large data sets to discover interesting patterns and gain information. The information obtained from data mining can provide insight into dimensional relationships between fields such as transactions, sales, date/time, health, environment, biology, and products. Applications of data mining include, but are not limited to, discovering buying patterns/sales trends, discovering biomarkers and performing gene mapping, detecting fraud, performing forensics, as well as predicting behaviors.

"One emerging area of interest for data mining includes social media. Patterns of behavior and content available from the pervasive use of social media have widespread applications for improving business, providing humanitarian relief, and assisting users as a few examples.

"Social media refers to Internet-based applications that propagate user-generated content. Social media include social networking applications, blogs, wikis, and other content (e.g., image, video, text) sharing applications. A massive amount of content (and associated data) is generated and posted to social media sites. Unlike traditional 'structured' attribute-value data, social media data is often noisy (i.e., contain issues with trustworthiness) and unstructured (e.g., do not necessarily contain cohesive or consistent attributes).

"One attribute that can be useful for uncovering patterns in social media content is source location. However, currently, only a minority of social media content include this attribute."

As a supplement to the background information on this patent application, VerticalNews correspondents also obtained the inventor's summary information for this patent application: "This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

"Techniques for providing estimated geographic coordinates indicating location source for social media posts are disclosed. By assigning geographic coordinates indicating a location source for social media data, the social media data can be analyzed for emerging patterns and relationships to location attributes.

"According to one embodiment, a knowledge base can be created that includes one or more representative keywords (with corresponding weights or probabilities) for each cluster of geolocated social media data, where each cluster corresponds to a spatio-temporal region.

"According to another embodiment, the knowledge base can be created by grouping geolocated social media data according to geographical area and extracting representative tags. The representative tag extraction can be accomplished by ranking tags for the data within a cluster. The rankings for the tags may be used to provide a weight for a keyword and/or to select the keywords representing a particular location (or region) during a particular time frame.

"According to yet another embodiment, non-geolocated social media data can be assigned an approximate geolocation using the knowledge base prepared from geolocated data. Keywords and other metadata can be extracted from the non-geolocated social media data and used to search for a highest probability matching cluster from the knowledge base.

BRIEF DESCRIPTION OF THE DRAWINGS

"FIG. 1 shows a process flow for creating a knowledge base according to an embodiment of the invention.

"FIG. 2 shows a representation of a cluster according to an embodiment of the invention.

"FIG. 3 shows a data structure of a knowledge base according to an embodiment of the invention.

"FIG. 4 shows a process flow for assigning an approximate geolocation to social media data that does not contain location coordinates in its metadata according to an embodiment of the invention.

"FIG. 5 shows a process flow diagram according to an embodiment of the invention.

"FIG. 6 shows a representative data structure of an example knowledge base.

"FIG. 7 shows computer architecture diagram illustrating a computing system capable of implementing aspects of embodiments presented herein."

For additional information on this patent application, see: RISHE, NAPHTALI DAVID. Geolocating Social Media. Filed February 19, 2014 and posted August 28, 2014. Patent URL: http://appft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&u=%2Fnetahtml%2FPTO%2Fsearch-adv.html&r=813&p=17&f=G&l=50&d=PG01&S1=20140821.PD.&OS=PD/20140821&RS=PD/20140821

Keywords for this news article include: Information Technology, Information and Data Architecture, Information and Data Mining, Legal Issues, The Florida International University Board Of Trustees.

Our reports deliver fact-based news of research and discoveries from around the world. Copyright 2014, NewsRx LLC


For more stories covering the world of technology, please see HispanicBusiness' Tech Channel



Source: Information Technology Newsweekly


Story Tools






HispanicBusiness.com Facebook Linkedin Twitter RSS Feed Email Alerts & Newsletters