SOCIAL MEDIA DRIVEN ADVERTISEMENT TARGETING

• US 20100030648A1
• Filed: 08/01/2008
• Published: 02/04/2010
• Est. Priority Date: 08/01/2008
• Status: Abandoned Application

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Laghaeian, Raymond, Manolescu, Dragos
• Application Number:
  US12/184,254
• Publication Number:
  US 20100030648A1
• Time in Patent Office: Days
• US Class Current: 705/14.660
• CPC Class Codes: G06Q 10/0637 Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute

Abstract

Techniques and systems for selecting one or more advertisements to target (e.g., send to, display to, etc.) a user are disclosed wherein the interests of the user are inferred based on current behaviors of social media. Social media is collected and categorized according to some predetermined criteria, such as keywords or outlinks in a post. As a function of the social media collected, current topics in the social media are identified and an advertisement, or advertisements, relating to the current topics is selected. Current topics may be those topics that are more popular, for example, in the social media at the instant a user enters an ad-enabled site.

Claims

1. A method for selecting an online advertisement to target a user, comprising:

identifying current topics in social media according to a first snapshot of the social media; and

selecting the online advertisement to target the user as a function of the current topics identified.

2. The method of claim 1, comprising acquiring a post from the online social media content using syndicated feed crawlers.

3. The method of claim 2, comprising categorizing the post acquired using some predetermined criteria.

4. The method of claim 3, wherein the predetermined criteria used to categorize the post is at least one of the following:

main topic of the post;

links in the post that point to another website;

keywords;

persons, places, or brands mentioned in the post;

sentiment of the author; and

demographics of the author.

5. The method of claim 3, wherein the post is categorized using inference algorithms.

6. The method of claim 5, wherein the inference algorithms are trained to infer the topic of a post and categorize it as a function of the inferred topic.

7. The method of claim 1, wherein an online advertisement is selected to reflect current, popular conversational topics.

8. The method of claim 1, wherein the online advertisement is selected in real-time to reflect current behavior.

9. The method of claim 1, comprising selecting an advertisement as a function of the user'"'"'s known interest;

wherein, the user'"'"'s known interest are used to filter current topics that are more likely to be relevant to the user.

10. The method of claim 9, comprising determining the user'"'"'s interests as a function of a site the user was referred from.

11. The method of claim 1, comprising:

tagging the online advertisement based on some predetermined criteria;

storing the online advertisement;

selecting the online advertisement when the advertisement'"'"'s tag relates to current topics; and

displaying the selected online advertisement on an ad-enabled site.

12. The method of claim 1, comprising identifying current topics of online social media according to a second snapshot of the social media some predetermined time after the first snapshot or upon the occurrence of some predetermined event.

13. A method for selecting an online advertisement to target a user, comprising:

monitoring social media,

wherein inferences are made about the social media using some predetermined criteria,

wherein the predetermined criteria includes at least one of the following;

main topic of the post;

links in a post that point to another website;

keywords;

persons, places, or brands mentioned in the post;

sentiment of an author; and

demographics of the author;

taking a snapshot of social media,

wherein the snapshot acquires the data about the inferences made at an instant the snapshot is taken;

predicting the user'"'"'s interests as a function of the data acquired by the snapshot,

wherein the data is used to find the current popular conversational topics; and

selecting the online advertisement as a function of the prediction,

wherein the selection is presented to a user on an ad-enabled site.

14. The method of claim 13, comprising enhancing the prediction as a function of the user'"'"'s known characteristics.

15. The method of claim 13, wherein the advertisement is selected in real-time to reflect current behaviors.

16. The method of claim 13, wherein inferences are made using trained algorithms and rules.

17. A system for selecting an online advertisement to target a user, comprising:

an inference component configured to make inferences about social media

an acquisition component configured to take a snapshot of the inferences made by the inference component;

a prediction component configured to predict the user'"'"'s interest as a function of the snapshot taken by the acquisition component; and

a selection component configured to select the online advertisement that relates to the user'"'"'s predicted interests.

18. The system of claim 17, wherein the prediction component uses currently, popular conversational topics as determined by the snapshot to predict the user'"'"'s interests.

19. The system of claim 17, wherein the prediction component is configured to enhance the prediction if characteristics of a user are known.

20. The system of claim 17, wherein the selection component is configured to automatically select an advertisement from a storage component and display the advertisement on an ad-enabled site.