DETERMINATION OF GENERAL AND TOPICAL NEWS AND GEOGRAPHICAL SCOPE OF NEWS CONTENT

• US 20150026255A1
• Filed: 07/17/2013
• Published: 01/22/2015
• Est. Priority Date: 07/17/2013
• Status: Active Grant

• Current Assignee: Yahoo Assets LLC
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Wexler, Mike
• Granted Patent: US 9,807,181 B2
• Time in Patent Office: Days
• US Class Current: 709/204
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: H04L 51/222 using geographical location information, e.g. messages transmitted or received in proximity of a certain spot or area
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04W 4/185 by embedding added-value information into content, e.g. geo-tagging

Abstract

Methods for categorizing news are presented. One method groups articles into clusters that share a common topic. A first category is identified for each article that indicates if the article is news or not. Further, the method includes an operation for determining use data for each article that has information about people that have accessed or referenced the article. Additionally, the method includes an operation for combining the use data and the first category for all the articles in each cluster to determine the geographical scope of interest for the cluster. The use data and the first category are combined for all the articles in each cluster to determine a second category for each article that indicates if the article is general news, topical news, or not news. The articles are presented to the user based on the geographical scope of interest, the second category, and the attributes of the user.

Claims

1. A method for categorizing news articles, the method comprising:

grouping articles into clusters, each cluster being associated with a topic that is common to articles in the cluster;

identifying a first category for each article, the first category indicating if the article is news or not-news;

determining use data for each article, the use data including information about people that have accessed the each article;

combining the use data and the first category for all the articles in each cluster to determine a geographical scope of interest for the cluster;

combining the use data and the first category for all the articles in each cluster to determine a second category for each article, the second category indicating if the article is general news, topical news, or not-news; and

presenting the articles to a user based on the geographical scope of interest, the second category, and attributes of the user, wherein operations of the method are executed by a processor.

2. The method as recited in claim 1, wherein determining use data further includes:

identifying users of a social network that have referenced each article; and

determining a geographical location of the users that have accessed each article.

3. The method as recited in claim 1, wherein determining use data further includes:

identifying emails that refer to each article; and

determining a geographical location of users associated with the respective emails.

4. The method as recited in claim 1, wherein determining use data further includes:

identifying text messages that refer to each article; and

determining a geopgraphic location of users associated with the respective text messages

5. The method as recited in claim 1, wherein determining use data further includes:

identifying users that have performed web searches related to each article; and

determining a geographical location of users that have performed the web searches.

6. The method as recited in claim 1, wherein determining use data further includes:

identifying news publishers that have published each article; and

determining a geographical location of the news publishers.

7. The method as recited in claim 1, wherein determining use data further includes:

identifying users that have performed an operation indicating an approval for each article; and

determining a geographical location of the users.

8. The method as recited in claim 1, wherein identifying the first category further includes:

extracting topic information from each article based on an analysis of text in each article;

identifying categorizations given by article providers for each article; and

utilizing machine categorization based on machine learning of sample articles categorized by judges.

9. The method as recited in claim 8, wherein utilizing machine categorization further includes:

analyzing the sample articles to provide an automated classifier; and

utilizing the classifier with each of the articles.

10. The method as recited in claim 1, wherein determining the second category further includes:

identifying signals associated with each article; and

combining the signals to determine the second category for each article.

11. The method as recited in claim 1, wherein determining the geographical scope of interest further includes:

mapping locations of users that have access each article; and

determining regions of interest for each article based on the mapped locations.

12. The method as recited in claim 1, wherein the attributes of the user includes one or more of user geographical location, user residence location, user birth location, news parameters configured by the user, user social activity, or user search history.

13. A computer program embedded in a non-transitory computer-readable storage medium, when executed by one or more processors, for categorizing news articles, the computer program comprising:

program instructions for grouping articles into clusters, each cluster being associated with a topic that is common to articles in the cluster;

program instructions for identifying a first category for each article, the first category indicating if the article is news or not-news;

program instructions for determining use data for each article, the use data including information about people that have referenced the each article;

program instructions for combining the use data and the first category for all the articles in each cluster to determine a geographical scope of interest for the cluster;

program instructions for combining the use data and the first category for all the articles in each cluster to determine a second category for each article, the second category indicating if the article is general news, topical news, or not-news; and

program instructions for presenting the articles to a user based on the geographical scope of interest, the second category, and attributes of the user.

14. The computer program as recited in claim 13, wherein determining use data further includes:

identifying instant messages that refer to each article; and

determining a geographical location of users associated with the respective instant messages.

15. The computer program as recited in claim 13, wherein determining use data further includes:

identifying emails that refer to each article; and

determining a geographical location of users associated with the respective emails.

16. The computer program as recited in claim 13, wherein determining use data further includes:

identifying users that have performed web searches related to each article; and

determining a geographical location of users that have performed the web searches.

17. The computer program as recited in claim 13, wherein determining use data further includes:

identifying news publishers that have published each article; and

determining a geographical location of the news publishers.

18. The computer program as recited in claim 13, wherein determining use data further includes:

identifying users that have performed an operation indicating an approval for each article; and

determining a geographical location of the users.

19. A system for categorizing news articles, the system comprising:

a processor; and

a memory having a computer program, wherein program instructions from the computer program when executed by the processor cause the processor to;

group articles into clusters, each cluster being associated with a topic that is common to articles in the cluster;

identify a first category for each article, the first category indicating if the article is news or not-news;

determine use data for each article, the use data including information about people that have accessed the each article;

combine the use data and the first category for all the articles in each cluster to determine a geographical scope of interest for the cluster;

combine the use data and the first category for all the articles in each cluster to determine a second category for each article, the second category indicating if the article is general news, topical news, or not-news; and

present the articles to a user based on the geographical scope of interest, the second category, and attributes of the user.

20. The system of claim 19, wherein determining the use data further includes:

identifying users of a social network that have accessed each article; and

determining a geographical location of the users that have accessed each article.