Methods and apparatus for inserting content into conversations in on-line and digital environments
Content is inserted into conversations hosted on a takeoff site using creatives that provide lures and links to other material that users engaged in the conversation might find helpful and relevant. Such insertions are made in a contextually meaningful fashion through the use of a matching and decision process that determines best candidate creatives and an appropriate time and place for their insertion into the conversation.
1. A system for inserting content, the system comprising:
a processor; and
a memory, wherein the memory stores instructions that, when executed by the processor, cause the processor to:
analyze elements of a conversation taking place at a first destination to detect elements relating to expression of need for information in the conversation;
identify a pool of one or more candidate second destinations based on relevance of the second destinations to the expression of need for information in the conversation;
identify a pool of one or more candidate templates relevant to the pool of one or more candidate second destinations;
construct a set of candidate creatives by combining one or more of the pool of candidate templates with one or more of the candidate second destinations;
score the set of candidate creatives for relevance to the expression of need for information;
select at least one of the set of candidate creatives based on the scoring for presentation at the first destination; and
insert the selected one of the set of candidate creatives at the first destination.
2. The system of claim 1 , wherein the detected elements comprise at least one of speech acts, entities or other special words, or contributor properties of the conversation at the first destination.
3. The system of claim 1 , wherein the selected one of the set of candidate creatives is selected based on similarity of textual data of the first destination to the template and second destination of each of the set of candidate creatives.
4. The system of claim 1 , wherein each template includes at least one of an introduction and a call to action, and the second destination comprises a landing page.
5. The system of claim 4 , wherein the instructions, when executed, further cause the processor to construct the set of candidate creatives by combining each one of the pool of candidate second destinations with each one of the pool of candidate templates, where the second destinations further comprise landing pages.
6. The system of claim 5 , wherein the each of the set of candidate creatives is scored based on textual similarity between the first destination and the template and the landing page of the second destination of the candidate creative and at least one of the set of candidate creatives is selected based on the textual similarity score.
7. The system of claim 5 , wherein the landing page is selected based on at least one of mouseovers, click throughs, page visits to the landing page, and product purchases within the landing page.
8. The system of claim 5 , wherein the at least one of the set of candidate creatives is selected based on at least one of conversational statistics, campaign management requirements, and information about a device on which the selected one of the set of candidate creatives will be displayed.
9. The system of claim 5 , wherein the pool of templates comprises templates having a common thematic element.
10. The system of claim 1 , wherein the detected elements of the first destination correspond to a message at the first destination, and the instructions comprise instructions for display of the selected one of the set of candidate creatives at a location near to the message.
11. The system of claim 1 , wherein the first and second destinations are online sites hosting conversational content.
12. A method of inserting content, the method comprising:
analyzing, by one or more processors, elements of a conversation taking place at a first destination to detect elements relating to expression of need for information in the conversation;
identifying a pool of one or more candidate second destinations based on relevance of the second destinations to the expression of need for information in the conversation;
identifying a pool of one or more candidate templates relevant to the pool of one or more candidate second destinations;
constructing a set of candidate creatives by combining one or more of the pool of candidate templates with one or more of the candidate second destinations;
scoring the set of candidate creatives for relevance to the expression of need for information;
selecting, by the one or more processors, at least one of the set of candidate creatives based on the scoring for presentation at the first destination; and
inserting, by the one or more processors, the selected one of the candidate creatives at the first destination.
13. The method of claim 12 , wherein the detected elements comprise at least one of speech acts, entities or other special words, or contributor properties of the conversation at the first destination.
14. The method of claim 12 , wherein the selected one of the set of candidate creatives is selected based on similarity of textual data of the first destination to the template and second destination of each of the set of candidate creatives.
15. The method of claim 12 , each template includes at least one of an introduction and a call to action, and the second destination comprises a landing page.
16. The method of claim 15 , further comprising constructing, by the one or more processors, the set of candidate creatives by combining each one of the pool of candidate second destinations with each one of the pool of candidate templates, where the second destinations further comprise landing pages.
17. The method of claim 16 , wherein the each of the set of candidate creatives is scored based on textual similarity between the first destination and the template and the landing page of the second destination of the candidate creative and at least one of the set of candidate creatives is selected based on the textual similarity score.
18. The method of claim 16 , wherein the landing page is selected based on at least one of mouseovers, click throughs, page visits to the landing page, and product purchases within the landing page.
19. The method of claim 16 , wherein the at least one of the set of candidate creatives is selected based on at least one of conversational statistics, campaign management requirements, and information about a device on which the selected one of the set of candidate creatives will be displayed.
20. The method of claim 16 , wherein the pool of templates comprises templates having a common thematic element.
21. The method of claim 12 , wherein the detected elements of the first destination correspond to a message at the first destination, and the instructions comprise instructions for display of the selected one of the set of candidate creatives at a location near to the message.
22. The method of claim 12 , wherein the first and second destinations are online sites hosting conversational content.