System and method for predicting a geographic origin of content and accuracy of geotags related to content obtained from social media and other content providers

Abstract

A system and method for managing geotag data associated with content within a geofeed is provided. The content may be tagged with metadata such as geotag data that may specify a location where the content was created. The generated content may be geotagged by one or more geotag sources including a GPS-enabled device, a user input, a content provider, a user profile, or other sources. The system may determine the geotag data for the content that is not already associated with geotag data. The system may determine a confidence level of the geotag data, whether already geotagged or not. The confidence level may be indicative of a likelihood that the geotag data accurately describes a location where the content was actually created.

What is claimed is: 
     
         1 . A computer implemented method of determining a location where a social media content item was created when the content item lacks geotag data, wherein the content item is associated with a user and posted to a social media content provider, the method being implemented on a computer having one or more physical processors programmed with one or more computer program instructions that, when executed by the one or more physical processors, program the computer to perform the method, the method comprising:
 obtaining, by the computer, the content item from the social media content provider;   obtaining, by the computer, metadata associated with the content item;   determining, by the computer, that geotag data is missing from the metadata; and   responsive to the determination that the geotag data is missing from the metadata, identifying, by a computer-implemented recognition technique performed on the content item by a location prediction component of the computer, the location at which the content item was created.   
     
     
         2 . The method of  claim 1 , wherein identifying the location comprises:
 recognizing, by the location prediction component, text in the content item; and   associating, by the location prediction component, the recognized text with a recognized location, wherein the location is identified based on the recognized location.   
     
     
         3 . The method of  claim 1 , wherein the content item comprises audio information and identifying the location comprises:
 performing, by the location prediction component, speech recognition on the audio information to identify a recognized location associated with the content item, wherein the location is identified based on the recognized location.   
     
     
         4 . The method of  claim 1 , wherein identifying the location comprises:
 identifying, by the location prediction component, a hyperlink in the content item, wherein the hyperlink links to geotagged content whose metadata includes second location information that indicates where the geotagged content was created, wherein the location is based on the second location information.   
     
     
         5 . The method of  claim 4 , the method further comprising:
 identifying, by the location prediction component, a correlation between the content item and the geotagged content, wherein the location is based on the correlation.   
     
     
         6 . The method of  claim 1 , wherein identifying the location comprises:
 recognizing, by the location prediction component, an image in the content item; and   associating, by the location prediction component, the recognized image with a recognized location, wherein the location is determined based on the recognized location.   
     
     
         7 . The method of  claim 6 , the method further comprising:
 identifying, by the location prediction component, a geographical feature in the recognized image from the content item;   electronically accessing, by the location prediction component, a database configured to store geographic information indicating recognized locations associated with one or more geographical features; and   obtaining, by the location prediction component, the recognized location from the database based on the identified geographical feature.   
     
     
         8 . The method of  claim 7 , wherein the geographical feature comprises one or more recognized buildings, signage, landmarks, and/or places. 
     
     
         9 . The method of  claim 1 , wherein identifying the location comprises:
 obtaining, by the location prediction component, a second content item associated with the user;   obtaining, by the location prediction component, second metadata associated with the second content item;   obtaining, by the location prediction component, second geotag data from the second metadata, the second geotag data comprising location information that indicates a location at which the second content item was created;   obtaining, by the location prediction component, a difference between a first time at which the content item was posted and a second time at which the second content item was posted; and   determining, by the location prediction component, whether the difference is less than or equal to a predetermined time, wherein the location is determined based on the location in which the second content item was created responsive to a determination that the difference is less than or equal to the predetermined time.   
     
     
         10 . The method of  claim 1 , wherein the location is automatically identified responsive to the determination that the geotag data is missing from the metadata. 
     
     
         11 . The method of  claim 1 , wherein identifying the location comprises:
 identifying, by the location prediction component, an indication of the location in the metadata associated with the content item that is missing geotag data.   
     
     
         12 . The method of  claim 1 , the method further comprising:
 determining, by the computer, a confidence level associated with the location, wherein the confidence level is indicative of a likelihood that the location accurately describes the location where the content was created.   
     
     
         13 . A system configured to determine a location where a social media content item was created when the content item lacks geotag data, wherein the content item is associated with a user and posted to a social media content provider, the system comprising:
 a computer having one or more physical processors programmed by one or more computer program instructions that, when executed by the one or more physical processors, program the computer to:
 obtain the content item from the social media content provider; 
 obtain metadata associated with the content item; 
 determine that geotag data is missing from the metadata; and 
 responsive to the determination that the geotag data is missing from the metadata, identify, by a computer-implemented recognition technique performed on the content item by a location prediction component of the computer, the location at which the content item was created. 
   
     
     
         14 . The system of  claim 13 , wherein to identify the location, the location prediction component is configured to:
 recognize text in the content item; and   associate the recognized text with a recognized location, wherein the location is identified based on the recognized location.   
     
     
         15 . The system of  claim 13 , wherein the content item comprises audio information, and to identify the location, the location prediction component is configured to:
 perform speech recognition on the audio information to identify a recognized location associated with the content item, wherein the location is identified based on the recognized location.   
     
     
         16 . The system of  claim 13 , wherein to identify the location, the location prediction component is configured to:
 identify a hyperlink in the content item, wherein the hyperlink links to geotagged content whose metadata includes second location information that indicates where the geotagged content was created, wherein the location is based on the second location information.   
     
     
         17 . The system of  claim 16 , wherein the location prediction component is configured to:
 identify a correlation between the content item and the geotagged content, wherein the location is based on the correlation.   
     
     
         18 . The system of  claim 13 , wherein to identify the location, the location prediction component is configured to:
 recognize an image in the content item; and   associate the recognized image with a recognized location, wherein the location is determined based on the recognized location.   
     
     
         19 . The system of  claim 18 , wherein the location prediction component is configured to:
 identify a geographical feature in the recognized image from the content item;   electronically access a database configured to store geographic information indicating recognized locations associated with one or more geographical features; and   obtain the recognized location from the database based on the identified geographical feature.   
     
     
         20 . The system of  claim 19 , wherein the geographical feature comprises one or more recognized buildings, signage, landmarks, and/or places. 
     
     
         21 . The system of  claim 13 , wherein to identify the location, the location prediction component is configured to:
 obtain a second content item associated with the user;   obtain second metadata associated with the second content item;   obtain second geotag data from the second metadata, the second geotag data comprising location information that indicates a location at which the second content item was created;   obtain a difference between a first time at which the content item was posted and a second time at which the second content item was posted; and   determine whether the difference is less than or equal to a predetermined time, wherein the location is determined based on the location in which the second content item was created responsive to a determination that the difference is less than or equal to the predetermined time.   
     
     
         22 . The system of  claim 13 , wherein the location is automatically identified responsive to the determination that the geotag data is missing from the metadata. 
     
     
         23 . The system of  claim 13 , wherein to identify the location, the location prediction component is configured to:
 identify an indication of the location in the metadata associated with the content item that is missing geotag data.   
     
     
         24 . The system of  claim 13 , wherein the computer is further programmed to:
 determine a confidence level associated with the location, wherein the confidence level is indicative of a likelihood that the location accurately describes the location where the content was created.