Method, medium, and system for social media-based recommendations
A user may request a recommendation for an item from other users. Other users may respond to the request by recommending for or against items. Users may up-vote or down-vote the recommendations or responses of other users. The recommendations of the other users may be used to identify items and provide one or more recommendations to the requesting user. The original question and the responses may form a conversation thread. The recommendations may be inserted into the thread as responses, may be presented alongside the thread, or may be presented at the end of the thread. The recommendations may be based on one or more attributes of the user. The weight of the recommendations provided by other users may vary.
1. A method comprising:
receiving, from a user account, a request for a recommendation of an item provided by one or more other user accounts;
accessing one or more attributes associated with the user account;
accessing comments provided by the one or more other user accounts, the comments including one or more of opinions, commentary, or postings related to the item;
for each of the one or more user accounts, determining a number of previously-followed comments that are different from the accessed comments and were followed;
parsing the accessed comments to identify a set of items referred to in the accessed comments;
selecting a recommended item from the identified set of items, the recommended item being selected based on:
a weight associated with each comment of the accessed comments provided by the one or more other users;
the number of previously-followed comments for a user account of the one or more other user accounts providing a comment; and
the one or more attributes; and
determining that a size of the set of comments exceeds a threshold and a momentum of a thread of the set of comments where at least one or more processor cycles are reduced; and
generating a user interface that presents information about the recommended item to the user based on the determination.
2. The method of claim 1 , wherein the information about the recommended item is presented alongside the accessed comments.
3. The method of claim 1 , wherein the information about the recommended item is presented in-line with the accessed comments.
4. The method of claim 1 , wherein the method further comprises identifying a location of a user associated with the user account and the selecting of the recommended item is further based on the location of the user.
5. The method of claim 1 , wherein the accessing comments provided by the one or more other user accounts includes:
accessing a set of comments by the one or more other user accounts; and
for each comment in the set of comments:
determining if a product is mentioned in the comment; and
if a product is mentioned, determining if the comment is positive or negative.
6. The method of claim 1 , wherein:
accessing comments includes detecting, for each comment in the accessed comments, a degree to which the comment was agreed with by users; and
selecting the recommended item from the identified set of items is based on the degree to which one or more comments corresponding to the recommended item were agreed with.
7. The method of claim 1 , wherein the accessed comments are a batch of comments, and the method further comprises detecting an end of the batch of comments, the detection based on an elapsed time after a last comment exceeding a threshold without a further comment where the selecting of the recommended item occurs after the detecting of the end of the batch of comments.
8. The method of claim 7 , further comprising:
transmitting the user interface that presents information about the recommended item to the user;
detecting a beginning of a second batch of comments, the detection based on a first comment after the transmitting of the information about the recommended item;
detecting an end of the second batch of comments, the detection based on an elapsed time after a second comment exceeding a threshold without an additional comment;
based on the second batch of comments, selecting a second recommended item; and
generating and transmitting a second user interface that presents information about the second recommended item to the user.
9. The method of claim 1 , wherein the one or more user attributes correspond to interests of the user.
10. A system comprising:
a processor; and
a computer readable storage medium storing instructions that, when executed by the processor, cause the system to perform operations comprising:
receiving, from a user account, a request for a recommendation of an item provided by one or more other user accounts;
accessing one or more attributes associated with the user account;
accessing comments provided by the one or more other user accounts, the comments including one or more of opinions, commentary, or postings related to the item;
for each of the one or more user accounts, determining a number of previously-followed comments that are different from the accessed comments and were followed;
parsing the accessed comments to identify a set of items referred to in the accessed comments;
selecting a recommended item from the identified set of items, the recommended item being selected based on:
a weight associated with each comment of the accessed comments provided by the one or more other users;
the number of previously-followed comments for a user account of the one or more other user accounts providing a comment; and
the one or more attributes; and
determining that a size of the set of comments exceeds a threshold and a momentum of a thread of the set of comments where at least one or more processor cycles are reduced; and
generating a user interface that presents information about the recommended item to the user based on the determination.
11. The system of claim 10 , wherein the operations further comprises identifying a location of a user associated with the user account and the selecting of the recommended item is further based on the location of the user.
12. The system of claim 10 , wherein the accessing comments provided by the one or more other user accounts includes:
accessing a set of comments by the one or more other user accounts; and
for each comment in the set of comments:
determining if a product is mentioned in the comment; and
if a product is mentioned, determining if the comment is positive or negative.
13. The system of claim 10 , wherein:
accessing comments includes detecting, for each comment in the accessed comments, a degree to which the comment was agreed with by users; and
selecting the recommended item from the identified set of items is based on the degree to which one or more comments corresponding to the recommended item were agreed with.
14. The system of claim 10 , wherein the accessed comments are a batch of comments, and the method further comprises detecting an end of the batch of comments, the detection based on an elapsed time after a last comment exceeding a threshold without a further comment where the selecting of the recommended item occurs after the detecting of the end of the batch of comments and the operations further comprise:
transmit the user interface that presents information about the recommended item to the user;
detecting a beginning of a second batch of comments, the detection based on a first comment after the transmitting of the information about the recommended item;
detecting an end of the second batch of comments, the detection based on an elapsed time after a second comment exceeding a threshold without an additional comment;
based on the second batch of comments, selecting a second recommended item; and
generating and transmitting a second user interface that presents information about the second recommended item to the user.
15. The system of claim 10 , wherein the one or more user attributes correspond to interests of the user.
16. A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of an application server comprising a communication module, a recognition module, and a generation module, cause the application server to perform operations comprising:
receiving, from a user account, a request for a recommendation of an item provided by one or more other user accounts;
accessing one or more attributes associated with the user account;
accessing comments provided by the one or more other user accounts, the comments including one or more of opinions, commentary, or postings related to the item;
for each of the one or more user accounts, determining a number of previously-followed comments that are different from the accessed comments and were followed;
parsing the accessed comments to identify a set of items referred to in the accessed comments;
selecting a recommended item from the identified set of items, the recommended item being selected based on:
a weight associated with each comment of the accessed comments provided by the one or more other users;
the number of previously-followed comments for a user account of the one or more other user accounts providing a comment; and
the one or more attributes; and
determining that a size of the set of comments exceeds a threshold and a momentum of a thread of the set of comments where at least one or more processor cycles are reduced; and
generating a user interface that presents information about the recommended item to the user based on the determination.
17. The non-transitory machine-readable storage medium of claim 16 , wherein the accessing comments provided by the one or more other user accounts includes:
accessing a set of comments by the one or more other user accounts; and
for each comment in the set of comments:
determining if a product is mentioned in the comment; and
if a product is mentioned, determining if the comment is positive or negative.
18. The non-transitory machine-readable storage medium of claim 16 , wherein:
accessing comments includes detecting, for each comment in the accessed comments, a degree to which the comment was agreed with by users; and
selecting the recommended item from the identified set of items is based on the degree to which one or more comments corresponding to the recommended item were agreed with.
19. The non-transitory machine-readable storage medium of claim 16 , wherein the accessed comments are a batch of comments, and the method further comprises detecting an end of the batch of comments, the detection based on an elapsed time after a last comment exceeding a threshold without a further comment where the selecting of the recommended item occurs after the detecting of the end of the batch of comments and the operations further comprise:
transmit the user interface that presents information about the recommended item to the user;
detecting a beginning of a second batch of comments, the detection based on a first comment after the transmitting of the information about the recommended item;
detecting an end of the second batch of comments, the detection based on an elapsed time after a second comment exceeding a threshold without an additional comment;
based on the second batch of comments, selecting a second recommended item; and
generating and transmitting a second user interface that presents information about the second recommended item to the user.
20. The non-transitory machine-readable storage medium of claim 16 , wherein the one or more user attributes correspond to interests of the user.