Suggesting targeting information for ads; such as websites and/or categories of websites for example
One or more keywords and/or information about one or more properties may be accepted, and a set of one or more taxonomy categories may be determined using at least some of the keyword(s) and/or property information and perhaps term co-occurrence clusters. The determined taxonomy categories may be presented to an advertising user as an ad targeting suggestion. Each taxonomy category may have at least one associated property (e.g., Web document), that participates in an advertising network. An advertiser selection of a suggested taxonomy category may be accepted, and the serving of an ad of the advertiser may be targeted to each property associated with the selected suggested taxonomy category. Alternatively, such properties may be presented to an advertising user as an ad targeting suggestion.
1. An apparatus comprising:
one or more processors;
at least one input device;
at least one output device; and
one or more storage devices storing processor executable instructions which, when executed by the one or more processors, cause the one or more processors perform a method of:
accessing multiple web documents;
clustering the multiple web documents into multiple different clusters based on term co-occurrence analysis of the multiple web documents;
receiving text input through a user interface;
identifying, from among the multiple different clusters, a particular cluster that has at least a threshold term co-occurrence value for the text;
outputting, through the user interface, information identifying a hierarchical vertical category of the web documents included in the particular cluster and information identifying one or more of the web documents that are included in the particular cluster;
identifying a selection of the information identifying the hierarchical vertical category in the user interface and a deselection, in the user interface, of a given web document that is included in the hierarchical vertical category; and
serving content to the web documents included in the hierarchical vertical category except for the given web document based on the selection of the hierarchical vertical category and the deselection of the given web document.
2. The apparatus of claim 1 , wherein the method comprises:
receiving data indicating a selection, through the user interface, of a request to identify additional web documents that are similar to the web documents included in the hierarchical vertical category except for the given web document;
identifying additional web documents that are similar to the web documents included in the hierarchical vertical category except for the given web document; and
serving content to the additional web documents that are similar to the web documents included in the hierarchical vertical category except for the given web document.
3. The apparatus of claim 1 , wherein the hierarchical vertical category of the web documents includes web documents that identify a particular product, web documents that identify a particular service, web documents that identify a particular industry, or web documents that identify a particular topic.
4. The apparatus of claim 1 , wherein the method comprises:
determining whether the given web document belongs in a different hierarchical vertical category; and
based on determining that the given web document belongs in a different hierarchical vertical category, removing the given web document from the hierarchical vertical category.
5. The apparatus of claim 1 , wherein identifying, from among the multiple different clusters, a particular cluster that has at least a threshold term co-occurrence value for the text comprises:
determining that the text is included, at least the threshold term co-occurrence value number of times, in search queries entered during user sessions where users accessed the web documents of the particular cluster.
6. The apparatus of claim 1 , wherein identifying, from among the multiple different clusters, a particular cluster that has at least a threshold term co-occurrence value for the text comprises:
determining that the text is included, at least the threshold term co-occurrence value number of times, in the web documents of the particular cluster.
7. The apparatus of claim 1 , wherein identifying, from among the multiple different clusters, a particular cluster that has at least a threshold term co-occurrence value for the text comprises:
determining that the text is included, at least the threshold term co-occurrence value number of times, in search queries that retrieve the web documents of the particular cluster.
8. A computer-implemented method comprising:
accessing multiple web documents;
clustering the multiple web documents into multiple different clusters based on term co-occurrence analysis of the multiple web documents;
receiving text input through a user interface;
identifying, from among the multiple different clusters, a particular cluster that has at least a threshold term co-occurrence value for the text;
outputting, through the user interface, information identifying a hierarchical vertical category of the web documents included in the particular cluster and information identifying one or more of the web documents that are included in the particular cluster;
identifying a selection of the information identifying the hierarchical vertical category in the user interface and a deselection, in the user interface, of a given web document that is included in the hierarchical vertical category; and
serving content to the web documents included in the hierarchical vertical category except for the given web document based on the selection of the hierarchical vertical category and the deselection of the given web document.
9. The method of claim 8 , comprising:
receiving data indicating a selection, through the user interface, of a request to identify additional web documents that are similar to the web documents included in the hierarchical vertical category except for the given web document;
identifying additional web documents that are similar to the web documents included in the hierarchical vertical category except for the given web document; and
serving content to the additional web documents that are similar to the web documents included in the hierarchical vertical category except for the given web document.
10. The method of claim 8 , wherein the hierarchical vertical category of the web documents includes web documents that identify a particular product, web documents that identify a particular service, web documents that identify a particular industry, or web documents that identify a particular topic.
11. The method of claim 8 , comprising:
determining whether the given web document belongs in a different hierarchical vertical category; and
based on determining that the given web document belongs in a different hierarchical vertical category, removing the given web document from the hierarchical vertical category.
12. The method of claim 8 , wherein identifying, from among the multiple different clusters, a particular cluster that has at least a threshold term co-occurrence value for the text comprises:
determining that the text is included, at least the threshold term co-occurrence value number of times, in search queries entered during user sessions where users accessed the web documents of the particular cluster.
13. The method of claim 8 , wherein identifying, from among the multiple different clusters, a particular cluster that has at least a threshold term co-occurrence value for the text comprises:
determining that the text is included, at least the threshold term co-occurrence value number of times, in the web documents of the particular cluster.
14. The method of claim 8 , wherein identifying, from among the multiple different clusters, a particular cluster that has at least a threshold term co-occurrence value for the text comprises:
determining that the text is included, at least the threshold term co-occurrence value number of times, in search queries that retrieve the web documents of the particular cluster.
15. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:
accessing multiple web documents;
clustering the multiple web documents into multiple different clusters based on term co-occurrence analysis of the multiple web documents;
receiving text input through a user interface;
identifying, from among the multiple different clusters, a particular cluster that has at least a threshold term co-occurrence value for the text;
outputting, through the user interface, information identifying a hierarchical vertical category of the web documents included in the particular cluster and information identifying one or more of the web documents that are included in the particular cluster;
identifying a selection of the information identifying the hierarchical vertical category in the user interface and a deselection, in the user interface, of a given web document that is included in the hierarchical vertical category; and
serving content to the web documents included in the hierarchical vertical category except for the given web document based on the selection of the hierarchical vertical category and the deselection of the given web document.
16. The medium of claim 15 , wherein the operations comprise:
receiving data indicating a selection, through the user interface, of a request to identify additional web documents that are similar to the web documents included in the hierarchical vertical category except for the given web document;
identifying additional web documents that are similar to the web documents included in the hierarchical vertical category except for the given web document; and
serving content to the additional web documents that are similar to the web documents included in the hierarchical vertical category except for the given web document.
17. The medium of claim 15 , wherein the hierarchical vertical category of the web documents includes web documents that identify a particular product, web documents that identify a particular service, web documents that identify a particular industry, or web documents that identify a particular topic.
18. The medium of claim 15 , wherein the operations comprise:
determining whether the given web document belongs in a different hierarchical vertical category; and
based on determining that the given web document belongs in a different hierarchical vertical category, removing the given web document from the hierarchical vertical category.
19. The medium of claim 15 , wherein identifying, from among the multiple different clusters, a particular cluster that has at least a threshold term co-occurrence value for the text comprises:
determining that the text is included, at least the threshold term co-occurrence value number of times, in search queries entered during user sessions where users accessed the web documents of the particular cluster.
20. The medium of claim 15 , wherein identifying, from among the multiple different clusters, a particular cluster that has at least a threshold term co-occurrence value for the text comprises:
determining that the text is included, at least the threshold term co-occurrence value number of times, in the web documents of the particular cluster.