BLENDING CONTENT POOLS INTO CONTENT FEEDS
The disclosed embodiments provide a system for processing data. During operation, the system obtains a set of content pools for a user, wherein each content pool in the set of content pools includes a set of content items associated with user activity in a member segment of a social network. Next, the system calculates a set of probabilities of clicking the content items in the content pool. The system then uses the probabilities to order the content items with other content items from other content pools into a content feed for the user. Finally, the system presents the content feed to the user.
1 . A method for processing data, comprising:
obtaining a set of content pools for a user, wherein each content pool in the set of content pools comprises a set of content items associated with user activity in a member segment of a social network;
calculating, by one or more computer systems, a set of probabilities of clicking the content items in the content pool;
using the probabilities to order, by the one or more computer systems, the content items with other content items from other content pools into a content feed for the user; and
presenting, by the one or more computer systems, the content feed to the user.
2 . The method of claim 1 , further comprising:
obtaining a set of impressions of the content items by the user; and
using the set of impressions to order the content items and the other content items into the content feed.
3 . The method of claim 2 , wherein using the set of impressions to order the content items and the other content items into the content feed comprises:
discounting a probability of clicking a content item for each impression of the content item presented to the user.
4 . The method of claim 1 , further comprising:
merging similar content items into a single content item in the content feed.
5 . The method of claim 1 , further comprising:
obtaining a set of impressions of content items within the content pools presented to the user; and
discounting a prominence of the content pool in the content feed for each impression of a content item within the content pool presented to the user.
6 . The method of claim 1 , wherein obtaining the set of content pools comprises:
obtaining one or more metrics associated with user interaction with the set of content items for the member segment;
ranking the set of content items by the one or more metrics; and
generating a content pool for the member segment based on the ranking of the content items.
7 . The method of claim 1 , wherein obtaining the set of content pools comprises:
identifying a set of member segments associated with the user in the social network; and
obtaining the set of content pools associated with the member segments.
8 . The method of claim 1 , wherein calculating the set of probabilities of clicking the content items in the content pool comprises:
obtaining a set of features associated with user activity in the social network; and
applying a statistical model to the set of features to estimate the probabilities of clicking the content items in the content pool.
9 . The method of claim 8 , wherein the set of features comprises at least one of:
profile data for the user;
a frequency of interaction with the content pool; and
a ranking of the content items in the content pool.
10 . The method of claim 8 , wherein the set of features is further associated with the content items.
11 . The method of claim 10 , wherein the set of features comprises at least one of:
a sentiment of a content item;
a topic in the content item;
a reading level of the content item;
a quality of the content item; and
a language of the content item.
12 . An apparatus, comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the apparatus to:
obtain a set of content pools for a user, wherein each content pool in the set of content pools comprises a set of content items associated with user activity in a member segment of a social network;
calculate a set of probabilities of clicking the content items in the content pool;
use the probabilities to order the content items with other content items from other content pools into a content feed for the user; and
present the content feed to the user.
13 . The apparatus of claim 12 , wherein the memory further stores instructions that, when executed by the one or more processors, cause the apparatus to:
obtain a set of impressions of the content items by the user; and
use the set of impressions to order the content items and the other content items into the content feed.
14 . The apparatus of claim 12 , wherein the memory further stores instructions that, when executed by the one or more processors, cause the apparatus to:
merge similar content items into a single content item in the content feed.
15 . The apparatus of claim 12 , wherein the memory further stores instructions that, when executed by the one or more processors, cause the apparatus to:
obtain a set of impressions of content items within the content pools presented to the user; and
discount a prominence of the content pool in the content feed for each impression of a content item within the content pool presented to the user.
16 . The apparatus of claim 12 , wherein obtaining the set of content pools comprises:
identifying a set of member segments associated with the user in the social network; and
obtaining the set of content pools associated with the member segments.
17 . The apparatus of claim 12 , wherein calculating the set of probabilities of clicking the content items in the content pool comprises:
obtaining a set of features associated with user activity in the social network; and
applying a statistical model to the set of features to estimate the probabilities of clicking the content items in the content pool.
18 . The apparatus of claim 12 , wherein the set of features comprises at least one of:
profile data for the user;
a frequency of interaction with the content pool; and
a ranking of the content items in the content pool.
19 . A system, comprising:
a content-selection non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause the system to obtain a set of content pools for a user, wherein each content pool in the set of content pools comprises a set of content items associated with user activity in a member segment of a social network; and
a blending non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause the system to:
calculate a set of probabilities of clicking the content items in the content pool;
use the probabilities to order the content items with other content items from other content pools into a content feed for the user; and
present the content feed to the user.
20 . The system of claim 19 , wherein calculating the set of probabilities of clicking the content items in the content pool comprises:
obtaining a set of features associated with user activity in the social network; and
applying a statistical model to the set of features to estimate the probabilities of clicking the content items in the content pool.