CONTENT CHANNEL CURATION
One or more content examples associated with a content channel are received. One or more entities are determined based on the one or more content examples. One or more web documents are provided in a content feed based on the one or more determined entities.
1 . A method of, comprising:
receiving one or more content examples associated with a content channel;
determining one or more entities based on the one or more content examples; and
providing one or more web documents in a content feed based on the one or more determined entities.
2 . The method of claim 1 , further comprising receiving an indication to create a content channel.
3 . The method of claim 1 , wherein determining one or more entities based on the one or more examples includes learning a corresponding meaning for the one or more examples.
4 . The method of claim 3 , wherein learning a corresponding meaning for the one or more content examples is based on a term frequency-inverse document frequency value.
5 . The method of claim 3 , wherein determining one or more entities based on the one or more examples further includes mapping the corresponding learned meaning for the one or more is content examples to a corresponding entity.
6 . The method of claim 5 , wherein a mapped entity has a corresponding vector.
7 . The method of claim 6 , further comprising determining one or more other entities that are similar to the mapped entity.
8 . The method of claim 7 , wherein the one or more other entities are determined to be similar to the mapped entity based at least in part on a distance.
9 . The method of claim 1 , further comprising determining the one or more web documents to include in the content feed.
10 . The method of claim 9 , further comprising determining the one or more web documents to include in the content feed based at least in part on a distance between a vector associated with one of the one or more determined entities and a vector associated with one of the one or more web documents.
11 . The method of claim 10 , wherein the vector associated with the one of the one or more determined entities is determined based at least in part on collaborative filtering.
12 . The method of claim 1 , further comprising receiving at least one indication indicating whether one of the one or more determined web documents should be included in the content channel.
13 . The method of claim 12 , further comprising in response to receiving an indication that indicates the one of the one or more determined web documents should not be included in the content feed, adjusting a ranking of a web document for which the indication is received.
14 . The method of claim 1 , wherein the one or more content examples includes at least one of one or more words, a uniform resource locator associated with a website, a longform explanation of an example, a link included in the website, and/or a social media post.
15 . The method of claim 1 , wherein at least one of the one or more content examples has a corresponding weight value.
16 . The method of claim 1 , wherein the corresponding weight value indicates a degree to is which the content channel should include web documents that are similar to the at least one of the one or more content examples.
17 . The method of claim 1 , further comprising:
receiving a request for content associated with a topic; and
determining the content channel includes the content associated with the topic.
18 . A system, comprising:
a processor configured to:
receive one or more content examples associated with a content channel;
determine one or more entities based on the one or more content examples; and
provide one or more web documents in a content feed based on the one or more determined entities; and
a memory coupled to the processor and configured to provide the processor with instructions.
19 . The system of claim 1 , wherein the one or more examples includes at least one of one or more words, a uniform resource locator associated with a website, a longform explanation of an example, a link included in the website, and/or a social media post.
20 . A computer program product, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:
receiving one or more content examples associated with a content channel;
determining one or more entities based on the one or more content examples; and
providing one or more web documents in a content feed based on the one or more determined entities.