# US 11,122,009 B2 · Systems and methods for identifying geographic locations of social media content collected over social networks

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,122,009 B2
- Document ID: US11122009B2
- Status: Granted
- Kind: B2
- Application number: 13/853,687
- Filed: 2013-03-29
- Published: 2014-02-06
- Granted: 2021-09-14
- Earliest claimed: 2009-12-01
- Assignees: Apple Inc.
- Applicants: Apple Inc.
- Inventors: Olga Gurevich; Rishab Aiyer Ghosh
- Web page: https://patentgrep.com/patent/US11122009B2

## CPC

- G06F 16/313: {Selection or weighting of terms for indexing}
- G06F 16/951: Indexing; Web crawling techniques
- G06F 16/953: Querying, e.g. by the use of web search engines
- G06F 16/9537: Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
- H04W 4/023: {using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds}
- H04W 4/029: Location-based management or tracking services
- H04W 4/21: for social networking applications
- H04L 2101/69: using geographic information, e.g. room number
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## 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

### Claim 1

A system, comprising:
a processing system;
a memory coupled to the processing system though a bus; and
a process executed from the memory by the processing system that causes the processing system to
continuously retrieve social media items from a social network in real time, wherein the retrieved social media items do not have IP address identifiers to identify their geographic locations;
determine a geographic location for each of the social media items retrieved in real time by analyzing n-grams of the content of that social media item for information in this content that indicates the geographic location which is authored or originated from an author, wherein the social media item lacks latitude and longitude location information, the n-grams are a contiguous sequence of words of length N in the content of that social media item,
determine a geographic location indication of the content using a feature, location probabilistic classifier that uses a training set of location-known content to predict a location for the content without geographic coordinates,
tag each of the social media items with the corresponding location information,
in response to the determination of the geographic location, confirm the identified location from the n-grams analysis for each of the social media items by comparing the identified location of this social media item to locations of prior social media items posted or authored by the same author, and
present a view of at least some of the geo-tagged social media content items with their associated geographic locations to a user.

### Claim 2 (depends on 1)

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.

### Claim 3 (depends on 1)

The system of claim 1, wherein:
the social network is one of any other web-based communities.

### Claim 4 (depends on 1)

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.

### Claim 5 (depends on 1)

The system of claim 1, wherein the process further causes the processing system to
determine geographic location of a social media item from profile information of the author/user of the social media item, wherein the user's profile contains the user's self-described geographic location.

### Claim 6 (depends on 1)

The system of claim 1, wherein the process further causes the processing system to:
determines geographic location of a social media item based on one or more of: Exif photo metadata of the social media item, check-In location data of the author of the social media item, time stamp of the social media item, and geo-located hashtags for events in the social media item.

### Claim 7 (depends on 1)

The system of claim 1, wherein the process further causes the processing system to:
utilize the geographic location information of the social media items having such information to identify geographic locations of other social media items which geographic locations are not available.

### Claim 8 (depends on 7)

The system of claim 7, wherein the process further causes the processing system to:
utilize historical archive of social media items with known geographic coordinate data as a training set to train the feature, location probabilistic classifier to predict geographic locations of the social media items which geographic locations are not available.

### Claim 9 (depends on 8)

The system of claim 8, wherein the process further causes the processing system to:
assign geographic location to a social media item in the training set in the form of city, state, or country by reverse geocoding of the latitude/longitude coordinates of the social media item.

### Claim 10 (depends on 8)

The system of claim 8, wherein:
the feature, location probabilistic 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.

### Claim 11 (depends on 8)

The system of claim 8, wherein the process further causes the processing system to:
apply the feature, location probabilistic location classifier to identify the geographic location of each of the social media items retrieved from the social media network in real time.

### Claim 12 (depends on 1)

The system of claim 1, wherein the process further causes the processing system to:
present the social media items on a map with shading indicating the relative volume of the social media items at their respective geographic locations on the map.

### Claim 13 (depends on 12)

The system of claim 12, wherein the process further causes the processing system to:
enable the map to be zoomed in focus on metrics of the social media content items at region, country, city or state level.

### Claim 14 (depends on 12)

The system of claim 12, wherein the process further causes the processing system to:
shade the map based on a polynomial function that colors the map by default based on the volume of social media items at their geographic locations.

### Claim 15

A method, comprising:
retrieving social media items from a social network in real time, wherein the retrieved social media items do not have IP address identifiers to identify their geographic locations;
determining a geographic location for each of the social media items retrieved in real time by analyzing n-grams of the content of that social media item which is authored or originated from an author for information in this content that indicates the geographic location, wherein the social media item lacks latitude, longitude location information and the n-grams are a contiguous sequence of words of length N in the content of that social media item;
determining a geographic location indication of the content using a feature, location probabilistic classifier that uses a training set of location-known content to predict a location for the content without geographic coordinates;
tagging each of the social media items with the corresponding location information;
in response to the determination of the geographic location, confirming the identified location from the n-grams analysis for each of the social media items by comparing the identified location of this social media item to locations of prior social media items posted or authored by the same author; and
presenting a view of at least some of the geo-tagged social media items with their associated geographic locations to a user.

### Claim 16 (depends on 15)

The method of claim 15, further comprising:
identifying the geographic location of a social media item using the latitude/longitude coordinates of the social media item when the user/author of the social media item opts in to share the GPS location of the device where the social media item is originated.

### Claim 17 (depends on 15)

The method of claim 15, further comprising:
identifying the geographic location of a social media item from profile information of the author/user of the social media item, wherein the user's profile contains the user's self-described geographic location.

### Claim 18 (depends on 15)

The method of claim 15, further comprising:
identifying the geographic location of a social media item based on one or more of: language used in the social media item, Exif photo metadata of the social media item, check-In location data of the author of the social media item, time stamp of the social media item, content analysis of the social media item, and geo-located hashtags for events in the social media item.

### Claim 19 (depends on 15)

The method of claim 15, further comprising:
utilizing the geographic location information of the social media items having such information to identify geographic locations of other social media items which geographic locations are not available.

### Claim 20 (depends on 19)

The method of claim 19, further comprising:
utilizing historical archive of social media items with known geographic coordinate data as a training set to train the feature, location probabilistic location classifier to predict geographic locations of the social media items which geographic locations are not available.

### Claim 21 (depends on 20)

The method of claim 20, further comprising:
assigning geographic location information to a social media item in the training set in the form of city, state, or country by reverse geocoding of the latitude/longitude coordinates of the social media item.

### Claim 22 (depends on 20)

The method of claim 20, 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.

### Claim 23 (depends on 20)

The method of claim 20, further comprising:
applying the feature, location probabilistic classifier to identify the geographic location of each of the social media items retrieved from the social media network in real time.

### Claim 24 (depends on 15)

The method of claim 15, further comprising:
presenting the social media items on a map with shading indicating the relative volume of the social media items at their respective geographic locations on the map.

### Claim 25 (depends on 24)

The method of claim 24, further comprising:
enabling the map to be zoomed in to focus on metrics of the social media items at region, country, city or state levels.

### Claim 26 (depends on 24)

The method of claim 24, further comprising:
shading the map based on a polynomial function that colors the map by default based on the volume of social media items at their geographic locations.

### Claim 27

A non-transitory machine-readable medium containing executable program instructions which when executed by a data processing device cause the device to perform a method, the method comprising:
retrieving social media items from a social network in real time, wherein the retrieved social media items do not have IP address identifiers to identify their geographic locations;
determining a geographic location for each of the social media items retrieved in real time by analyzing n-grams of content of that social media item which is authored or originated from an author for information in this content that indicates the geographic location, wherein the social media item lacks latitude and longitude location information, the n-grams are a contiguous sequence of words of length N in the content of that social media item;
determining a geographic location indication of the content using a feature, location probabilistic classifier that uses a training set of location-known content to predict a location for the content without geographic coordinates;
tagging each of the social media items with the corresponding location information;
in response to the determination of the geographic location, confirming the identified location from the n-grams analysis for each of the social media items by comparing the identified location of this social media item to locations of prior social media items posted or authored by the same author; and
presenting a view of at least some of the geo-tagged social media items with their associated geographic locations to a user.

### Claim 28 (depends on 1)

The system of claim 1, wherein:
the feature, location probabilistic classifier further determines the geographic location of the social media item using a language used in the content of the social media item.

### Claim 29 (depends on 15)

The method of claim 15, the feature, location probabilistic classifier further determines the geographic location of the social media item using on a language used in the content of the social media item.

### Claim 30 (depends on 1)

The system of claim 1, wherein the information is a hashtag.

### Claim 31 (depends on 15)

The method of claim 15, wherein the information is a hashtag.