Campaigns responsive to keyword trends
Online advertising campaigns are operated responsive to keyword trends. The keywords used by a group of browsers is analyzed periodically over time. A list of the most frequently used keywords is separated into those that have previously appeared on the list, referred to herein as the stable keywords, and those that are newly emerging, referred to herein as the trending keywords. The advertiser selects at least one advertising creative that the advertiser associates with the stable keywords, referred to herein as the stable creative, and at least one advertising creative that the advertiser associates with the trending keywords, referred to herein as the trendy creative. The advertising system then operates the online advertising campaign to deliver the respective stable and trendy creatives in proportion to the frequency of use of the trending versus the stable keywords.
1. A computer-implemented method, comprising:
determining, by an advertising system, a relative proportion of stable keywords to trending keywords corresponding to a previous time period, the determining comprising:
analyzing, by the advertising system, keywords present in consumption history data, received from a consumption history server, of a group of browsers;
based on the analyzing, identifying a list of keywords and frequencies of each of the keywords in the list of keywords present in the consumption history data during the previous time period;
identifying a group of stable keywords and a group of trending keywords from the list of keywords; and
comparing a total number of instances of the stable keywords to a total number of instances of the trending keywords in the consumption history data corresponding to the previous time period; and
sending, by the advertising system to an ad exchange, in response to a first plurality of bid requests received from the ad exchange, a first plurality of ad redirects, a first subset of the first plurality of ad redirects corresponding to a stable creative according to the relative proportion and a second subset of the first plurality of ad redirects corresponding to a trendy creative according to the relative proportion.
2. The method of claim 1 , wherein identifying the list of keywords present in the consumption history data further comprises:
identifying a list of keywords present in the consumption history data each having a respective frequency of use, by the group of browsers, above a threshold.
3. The method of claim 2 , wherein:
identifying the list of keywords present in the consumption history data further comprises:
ranking the keywords present in the consumption history data of the group of browsers based on their respective frequencies; and
identifying a list of keywords having a respective frequency ranking above a threshold.
4. The method of claim 1 , wherein:
identifying the group of stable keyword comprises identifying keywords that have appeared on each of a first number of lists of keywords corresponding to a first number of previous time periods; and
identifying the group of trending keywords comprises identifying keywords that have appeared on each of a second number of lists of keywords taken from a second number of previous time periods, where the second number is less that the first number.
5. A non-transitory computer-readable storage medium storing processor-executable computer program instructions that, when executed, cause a computer processor to perform a method, the method comprising:
determining, by an advertising system, a relative proportion of stable keywords to trending keywords corresponding to a previous time period, the determining comprising:
analyzing, by the advertising system, keywords present in consumption history data, received from a consumption history server, of a group of browsers;
based on the analyzing, identifying a list of keywords and frequencies of each of the keywords in the list of keywords present in the consumption history data during the previous time period;
identifying a group of stable keywords and a group of trending keywords from the list of keywords; and
comparing a total number of instances of the stable keywords to a total number of instances of the trending keywords in the consumption history data corresponding to the previous time period; and
sending, by the advertising system to an ad exchange, in response to a first plurality of bid requests received from the ad exchange, a first plurality of ad redirects, a first subset of the first plurality of ad redirects corresponding to a stable creative according to the relative proportion and a second subset of the first plurality of ad redirects corresponding to a trendy creative according to the relative proportion.
6. The medium of claim 5 , wherein identifying the list of keywords present in the consumption history data further comprises:
identifying a list of keywords present in the consumption history data each having a respective frequency of use, by the group of browsers, above a threshold.
7. The medium of claim 5 , wherein identifying the list of keywords present in the consumption history data further comprises:
ranking the keywords present in the consumption history data of the group of browsers based on their respective frequencies; and
identifying a list of keywords having a respective frequency ranking above a threshold.
8. The medium of claim 5 , wherein:
identifying the group of stable keyword comprises identifying keywords that have appeared on each of a first number of lists of keywords corresponding to a first number of previous time periods; and
identifying the group of trending keywords comprises identifying keywords that have appeared on each of a second number of lists of keywords taken from a second number of previous time periods, where the second number is less that the first number.
9. A system, comprising:
a processor; and
a non-transitory computer-readable storage medium storing processor-executable computer program instructions that, when executed, cause a computer processor to perform a method, the method comprising:
determining, by an advertising system, a relative proportion of stable keywords to trending keywords corresponding to a previous time period, the determining comprising:
analyzing, by the advertising system, keywords present in consumption history data, received from a consumption history server, of a group of browsers;
based on the analyzing, identifying a list of keywords and frequencies of each of the keywords in the list of keywords present in the consumption history data during the previous time period;
identifying a group of stable keywords and a group of trending keywords from the list of keywords; and
comparing a total number of instances of the stable keywords to a total number of instances of the trending keywords in the consumption history data corresponding to the previous time period; and
sending, by the advertising system to an ad exchange, in response to a first plurality of bid requests received from the ad exchange, a first plurality of ad redirects, a first subset of the first plurality of ad redirects corresponding to a stable creative according to the relative proportion and a second subset of the first plurality of ad redirects corresponding to a trendy creative according to the relative proportion.
10. The system of claim 9 , wherein identifying the list of keywords present in the consumption history data further comprises:
identifying a list of keywords present in the consumption history data each having a respective frequency of use, by the group of browsers, above a threshold.
11. The system of claim 9 , wherein identifying the list of keywords present in the consumption history data further comprises:
ranking the keywords present in the consumption history data of the group of browsers based on their respective frequencies; and
identifying a list of keywords having a respective frequency ranking above a threshold.
12. The system of claim 9 , wherein:
identifying the group of stable keyword comprises identifying keywords that have appeared on each of a first number of lists of keywords corresponding to a first number of previous time periods; and
identifying the group of trending keywords comprises identifying keywords that have appeared on each of a second number of lists of keywords taken from a second number of previous time periods, where the second number is less that the first number.