Prioritizing messages within a message network
A system and a method are disclosed for recommending electronic messages in a message sharing system. Users can post messages to the message sharing system. These messages from posting users are received by the system and sent to receiving users that have subscribed to the posting users. The receiving users interact with the messages in various ways, such as by sharing the messages with other users. Interaction information is received for each of the electronic messages. The interaction information includes an indication of the number of interactions with the electronic message by receiving users. A score is determined for each electronic message based on the interaction information. Electronic messages are selected for being recommended to a user or a group of users based on the scores. The recommendations are then sent to the users, enabling users to better focus their attention on messages that are likely to be interesting.
1. A computer-implemented method for selecting messages, comprising:
receiving a selection specifying a particular consumer in a social networking system;
retrieving, from a message stream of the consumer, electronic messages broadcasted by a plurality of posting users of the social networking system;
for two or more of the retrieved electronic messages:
estimating a number of detected interactions between users of the social networking system and the electronic message under consideration,
normalizing the number of detected interactions based on a number of expected interactions computed for the electronic message,
computing a level of connectedness between the particular consumer and a posting user who broadcasted the electronic message under consideration, and
computing, by a computer processor, a probability that the particular consumer will interact with the electronic message based on the normalized number of detected interactions and the level of connectedness;
ranking the retrieved electronic messages based on the computed probabilities; and
rearranging an order of appearance of the retrieved electronic messages in the message stream based on the ranking.
2. The computer-implemented method of claim 1 , further comprising transmitting a notification message to a user device to trigger a notification corresponding to the retrieved electronic messages in the message stream.
3. The computer-implemented method of claim 2 , wherein the notification message comprises a visual highlight indicating that the retrieved electronic messages are in the message stream.
4. The computer-implemented method of claim 1 , wherein an interaction corresponding to the detected interactions comprises at least one selected from a group consisting of forwarding the electronic message and streaming the electronic message.
5. The computer-implemented method of claim 1 , wherein the number of expected interactions for the electronic message is based on a number of users of the social networking system who have previously received the electronic message under consideration.
6. The computer-implemented method of claim 1 , further comprising classifying each of the electronic messages based on a characteristic of at least one selected from a group consisting of the electronic message and a posting user of the electronic message, wherein the probability that the particular consumer will interact with each electronic message is further based on the characteristic.
7. The computer-implemented method of claim 6 , wherein a characteristic of the electronic message includes at least one selected from a group consisting of length of the electronic message, contents of the electronic message, language of the electronic message, and elapsed time since the electronic message was posted.
8. The computer-implemented method of claim 1 , wherein the number of expected interactions for the electronic message is determined by identifying an average number of interactions previously observed for other electronic messages having the number of receiving users.
9. The computer-implemented method of claim 1 , wherein the number of expected interactions for the electronic message is determined based on demographic information associated with the posting user who broadcasted the electronic message.
10. The method of claim 1 , wherein the probability that the particular consumer will interact with the electronic message indicates a likelihood of the particular consumer selecting a link included in the message.
11. The method of claim 1 , wherein the probability that the particular consumer will interact with the electronic message indicates a likelihood of the particular consumer sharing the message with other users of the social networking system.
12. The method of claim 1 , wherein the probability that the particular consumer will interact with the electronic message indicates a likelihood of the particular consumer tagging the electronic message as a favorite message.
13. A non-transitory computer readable medium configured to store instructions for selecting messages, the instructions configured to execute on at least one computer processor to enable the computer processor to:
receiving a selection specifying a particular consumer in a social networking system;
retrieve, from a message stream of the consumer, electronic messages broadcasted by a plurality of posting users of the social networking system;
for two or more of the retrieved electronic messages:
estimate a number of detected interactions between users of the social networking system and the electronic message under consideration,
normalize the number of detected interactions based on a number of expected interactions computed for the electronic message,
compute a level of connectedness between the particular consumer and a posting user who broadcasted the electronic message under consideration, and
compute, by a computer processor, a probability that the particular consumer will interact with the electronic message based on the normalized number of detected interactions and the level of connectedness;
rank the retrieved electronic messages based on the computed probabilities; and
rearrange an order of appearance of the retrieved electronic messages in the message stream based on the ranking.
14. The non-transitory computer readable medium of claim 13 , wherein the instructions are further configured to enable the computer processor to transmit a notification message to a user device to trigger a notification corresponding to retrieved messages in the message stream.
15. The non-transitory computer readable medium of claim 14 , wherein the notification message comprises an instruction to highlight the retrieved messages on a display of the user device.
16. The non-transitory computer readable medium of claim 13 , wherein the number of expected interactions for the electronic message is based on a number of users of the social networking system who have previously received the electronic message under consideration.
17. The non-transitory computer readable medium of claim 13 , wherein the instructions are further configured to enable the computer processor to classify each of the electronic messages based on a characteristic of at least one selected from a group consisting of the electronic message and a posting user of the electronic message, the probability that the particular consumer will interact with each electronic message is further based on the characteristic.
18. The non-transitory computer readable medium of claim 17 , wherein a characteristic of the electronic message includes at least one selected from a group consisting of length of the electronic message, contents of the electronic message, language of the electronic message, and elapsed time since the electronic message was posted.
19. The non-transitory computer readable medium of claim 13 , wherein the number of expected interactions for the electronic message is determined by identifying an average number of interactions previously observed for other electronic messages having the number of receiving users.
20. The non-transitory computer readable medium of claim 13 , wherein the number of expected interactions for the electronic message is determined based on demographic information associated with the posting user who broadcasted the electronic message.
21. The non-transitory computer readable medium of claim 13 , wherein the probability that the particular consumer will interact with the electronic message indicates a likelihood of the particular consumer selecting a link included in the message.
22. The non-transitory computer readable medium of claim 13 , wherein the probability that the particular consumer will interact with the electronic message indicates a likelihood of the particular consumer sharing the message with other users of the social networking system.
23. The non-transitory computer readable medium of claim 13 , wherein the probability that the particular consumer will interact with the electronic message indicates a likelihood of the particular consumer tagging the electronic message as a favorite message.
24. A system for selecting messages, comprising:
a memory for storing instructions; and
a processor configured execute the instructions to perform the steps of:
receiving a selection specifying a particular consumer in a social networking system;
retrieving, from a message stream of the consumer, electronic messages broadcasted by a plurality of posting users of the social networking system;
for two or more of the retrieved electronic messages:
estimating a number of detected interactions between users of the social networking system and the electronic message under consideration,
normalizing the number of detected interactions based on a number of expected interactions computed for the electronic message,
computing a level of connectedness between the particular consumer and a posting user who broadcasted the electronic message under consideration, and
computing, by a computer processor, a probability that the particular consumer will interact with the electronic message based on the normalized number of detected interactions and the level of connectedness;
ranking the retrieved electronic messages based on the computed probabilities; and
rearranging an order of appearance of the retrieved electronic messages in the message stream based on the ranking.
25. The system of claim 24 , further comprising transmitting a notification message to a user device to trigger a notification corresponding to the retrieved electronic messages in the message stream.
26. The system of claim 25 , wherein the notification message comprises a visual highlight indicating that the retrieved electronic messages are in the message stream.
27. The system of claim 24 , wherein an interaction corresponding to the detected interactions comprises at least one selected from a group consisting of forwarding the electronic message and streaming the electronic message.
28. The system of claim 24 , wherein number of expected interactions for the electronic message is based on a number of users of the social networking system who have previously received the electronic message under consideration.
29. The system of claim 24 , further comprising classifying each of the electronic messages based on a characteristic of at least one selected from a group consisting of the electronic message and a posting user of the electronic message, wherein the probability that the particular consumer will interact with each electronic message is further based on the characteristic.
30. The system of claim 29 , wherein a characteristic of the electronic message includes at least one selected from a group consisting of length of the electronic message, contents of the electronic message, language of the electronic message, and elapsed time since the electronic message was posted.
31. The system of claim 24 , wherein the number of expected interactions for the electronic message is determined by identifying an average number of interactions previously observed for other electronic messages having the number of receiving users.
32. The system of claim 24 , wherein the number of expected interactions for the electronic message is determined based on demographic information associated with the posting user who broadcasted the electronic message.
33. The system of claim 24 , wherein the probability that the particular consumer will interact with the electronic message indicates a likelihood of the particular consumer selecting a link included in the message.
34. The system of claim 24 , wherein the probability that the particular consumer will interact with the electronic message indicates a likelihood of the particular consumer sharing the message with other users of the social networking system.
35. The system of claim 24 , wherein the probability that the particular consumer will interact with the electronic message indicates a likelihood of the particular consumer tagging the electronic message as a favorite message.