Social analytics system and method for analyzing conversations in social media

• US 8,682,723 B2
• Filed: 09/14/2009
• Issued: 03/25/2014
• Est. Priority Date: 02/28/2006
• Status: Expired due to Fees

• Current Assignee: Twelvefold Media Inc.
• Original Assignee: Twelvefold Media Inc.
• Inventors: Parsons, Todd, Ratcliffe, Mitch, Crumpler, Rob, Kessler, Will, Freytag, Kurt
• Primary Examiner(s): KINSAUL, DANIEL W
• Application Number:
  US12/558,788
• Publication Number:
  US 20100070485A1
• Time in Patent Office: 1,653 Days
• Field of Search: None
• US Class Current: 705/14.52
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0264 based upon schedule
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

Conversations in an online content universe are monitored. A social analysis module analyzes individual conversations between publishers in the online content universe. Publishers that influence a conversation are identified.

Claims

1. A method of targeting online advertising, comprising:

repeatedly crawling the web to maintain a database of historical online content in a computer system;

applying search engine queries via the computer system to the database to produce search results, wherein said queries include keywords, Boolean operators and universal resource indicators (URIs) defining a topic of conversation to be explored;

optimizing said search result sets for relevance to said topic by applying multiple queries to produce a search result set over time including multiple instances of online content related to said topic of conversation and publishers of said multiple instance of topic related online content;

determining influence of said publishers on said online content on the topic of conversation by scoring, in said search result sets,

a) attributes of both a particular instance of said topic related online contents, as well as

b) attributes of online content that link to that particular instance, and

c) a conversational correlation between two or more of said publishers related to said topic of conversation;

and thereafter

targeting online advertising to one or more of said publishers determined to then have the highest level, or rate of change, of influence.

2. The method of claim 1, wherein said topic is a conversation between said online content publishers.

3. The method of claims 1 or 2, wherein said attributes of said topic related online content include one or more of page popularity, site popularity, relevance, recency, inlink recency, inlink page popularity and inlink popularity.

4. The method of claims 1 or 2, wherein targeting online advertising further comprises:

predictively analyzing changes of influence of some of said topic related online content and/or said publishers over time.

5. The method of claim 4, further comprising:

extrapolating future roles of said influential publishers in commercial brand perception.

6. The method of claims 1 or 2, wherein targeting online advertising further comprises:

retrospectively analyzing changes of influence on said topic by extracting date and time information in said database of historical online content related to selected said publishers.

7. The method of claims 1 or 2, wherein targeting online advertising further comprises:

providing data identifying selected said publishers to an ad server for online ad placement.

8. The method of claims 1 or 2, wherein targeting online advertising further comprises:

identifying a selected publisher and a key time to insert an advertisement related to the topic.

9. The method of 1 or 2, wherein each of the queries may include a large plurality of different search indices and the method further comprises:

eliminating redundant URIs in the search queries, and

normalizing ranking of the different search indices before crawling.

10. The method of 1 or 2, wherein the method further comprises:

accepting input keywords and URIs from a user to define the topic;

monitoring conversations related to the topic to determine a list of influential publishers; and

directly engaging one or more of said publishers by the user for targeted ad placement.