Systems and methods for identifying geographic locations of social media content collected over social networks

• US 20140040371A1
• Filed: 03/29/2013
• Published: 02/06/2014
• Est. Priority Date: 12/01/2009
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Topsy Labs, Inc (Apple Inc.)
• Inventors: Ghosh, Rishab Aiyer, Gurevich, Olga
• Granted Patent: US 11,122,009 B2
• Time in Patent Office: Days
• US Class Current: 709/204
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: H04L 2101/69 using geographic information, e.g. room number
• CPC Class Codes: H04W 4/023 using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/21 for social networking applications

Abstract

A new approach is proposed that contemplates systems and methods to identify geographic locations of all social media content items retrieved form a social network in real time, wherein the geographic locations are physical locations from which the social media content items are originated or authored. If the latitude/longitude (geographic) coordinates of the content item are available, the geographic location of the social media content item can be identified using such geographic coordinates. For content items which geographic coordinates are not available, historical archive of content items with high-confidence of geographic locations are utilized to train a location classifier to predict geographic locations of such content items with high accuracy. Finally, the identified locations of the content items are confirmed to be accurate and are presented to a user together with the content items.

Claims

1. A system, comprising:

a social media content collection engine, which in operation, continuously retrieves all social media content items from a social network in real time, wherein the retrieved social media content items do not have IP address identifiers to identify their geographic locations;

a social media geo tagging engine, which in operation,

continuously identifies and marks each of the social media content items retrieved in real time with its proper geographic location from which such content item is authored or originated;

confirms the identified location of a content item by comparing the identified location to locations of prior content items posted or authored by the same author;

a social media content analysis engine, which in operation, presents a view of at least some of the geo-tagged social media content items with their associated geographic locations to a user.

2. The system of claim 1, wherein:

the social network is a publicly accessible web-based platform or community that enables its users/members to post, share, communicate, and interact with each other.

3. The system of claim 1, wherein:

the social network is one of any other web-based communities.

4. The system of claim 1, wherein:

the content items on the social media network include one or more of citations, tweets, replies and/or re-tweets to the tweets, posts, comments to other users'"'"' posts, opinions, feeds, connections, references, links to other websites or applications, or any other activities on the social network.

5. The system of claim 1, wherein:

the social media geo tagging engine identifies the geographic location of a social media content item using the latitude/longitude coordinates of the content item when the user/author of the content item opts in to share the GPS location of the device where the content item is originated.

6. The system of claim 1, wherein:

the social media geo tagging engine identifies geographic location of a content item from profile information of the author/user of the content item, wherein the user'"'"'s profile contains the user'"'"'s self-described geographic location.

7. The system of claim 1, wherein:

the social media geo tagging engine identifies geographic location of a content item based on one or more of;

language used in the content item, Exif photo metadata of the content item, check-In location data of the author of the content item, time stamp of the content item, content analysis of the content item, and geo-located hashtags for events in the content item.

8. The system of claim 1, wherein:

the social media geo tagging engine utilizes the geographic location information of the content items having such information to identify geographic locations of other content items which geographic locations are not available.

9. The system of claim 8, wherein:

the social media geo tagging engine utilizes historical archive of content items with high-confidence geographic coordinate data as a training set to train a customized probabilistic location classifier to predict geographic locations of the content items which geographic locations are not available.

10. The system of claim 9, wherein:

the social media geo tagging engine assigns geographic location to a content item in the training set in the form of city, state, or country by reverse geocoding of the latitude/longitude coordinates of the content item.

11. The system of claim 9, wherein:

the location classifier recognizes and extracts a set of features related to geographical location from each of the posts in the training set and calculates an observation set of the extracted features as the cross-product of the location vector and feature set, yielding <

feature, location>

pairs.

12. The system of claim 9, wherein:

the social media geo tagging engine applies the location classifier to identify the geographic location of each of the social media content items retrieved from the social media network in real time.

13. The system of claim 1, wherein:

the social media content analysis engine presents the social media content items on a map with shading indicating the relative volume of the social media content items at their respective geographic locations on the map.

14. The system of claim 13, wherein:

the social media content analysis engine enables the map to be zoomed in focus on metrics of the social media content items at region, country, city or state level.

15. The system of claim 13, wherein:

the social media content analysis engine shades the map based on a polynomial function that colors the map by default based on the volume of social media content items at their geographic locations.

16. A method, comprising:

retrieving all social media content items from a social network in real time, wherein the retrieved social media content items do not have IP address identifiers to identify their geographic locations;

identifying and marking continuously each of the social media content items retrieved in real time with its proper geographic location from which such content item is authored or originated;

confirming the identified location of a content item by comparing the identified location to locations of prior content items posted or authored by the same author;

presenting a view of at least some of the geo-tagged social media content items with their associated geographic locations to a user.

17. The method of claim 16, further comprising:

identifying the geographic location of a social media content item using the latitude/longitude coordinates of the content item when the user/author of the content item opts in to share the GPS location of the device where the content item is originated.

18. The method of claim 16, further comprising:

identifying geographic location of a content item from profile information of the author/user of the content item, wherein the user'"'"'s profile contains the user'"'"'s self-described geographic location.

19. The method of claim 16, further comprising:

identifying geographic location of a content item based on one or more of;

language used in the content item, Exif photo metadata of the content item, check-In location data of the author of the content item, time stamp of the content item, content analysis of the content item, and geo-located hashtags for events in the content item.

20. The method of claim 16, further comprising:

utilizing the geographic location information of the content items having such information to identify geographic locations of other content items which geographic locations are not available.

21. The method of claim 20, further comprising:

utilizing historical archive of content items with high-confidence geographic coordinate data as a training set to train a customized probabilistic location classifier to predict geographic locations of the content items which geographic locations are not available.

22. The method of claim 21, further comprising:

assigning geographic location to a content item in the training set in the form of city, state, or country by reverse geocoding of the latitude/longitude coordinates of the content item.

23. The method of claim 21, further comprising:

recognizing and extracting a set of features related to geographical location from each of the posts in the training set and calculates an observation set of the extracted features as the cross-product of the location vector and feature set, yielding <

feature, location>

pairs.

24. The method of claim 21, further comprising:

applying the location classifier to identify the geographic location of each of the social media content items retrieved from the social media network in real time.

25. The method of claim 16, further comprising:

presenting the social media content items on a map with shading indicating the relative volume of the social media content items at their respective geographic locations on the map.

26. The method of claim 25, further comprising:

enabling the map to be zoomed in to focus on metrics of the social media content items at region, country, city or state levels.

27. The method of claim 25, further comprising:

shading the map based on a polynomial function that colors the map by default based on the volume of social media content items at their geographic locations.