Sending safety-check prompts based on user interaction
View Patent ↗In one embodiment, a method includes identifying an emergency event; determining that a threshold percentage of users who are associated with the emergency event have posted content related to the emergency event to an online social network; sending, in response to the determination, a safety-check prompt to each of a first set of users; determining a current-prompting probability based on one or more engagement metrics of the safety-check prompt by the first set of users; and sending, in response to determining that the current-prompting probability is above a first threshold probability, the safety-check prompt to each of a second set of users, wherein the second set of users comprises more users than the first set of users.
1. A method comprising:
by a computing device, identifying an emergency event;
by the computing device, determining that a threshold percentage of users who are associated with the emergency event have posted content related to the emergency event to an online social network;
by the computing device, sending, in response to the determination, a safety-check prompt to each of a first set of users;
by the computing device, determining a current-prompting probability based on one or more engagement metrics of the safety-check prompt by the first set of users; and
by the computing device, sending, in response to determining that the current-prompting probability is above a first threshold probability, the safety-check prompt to each of a second set of users, wherein the second set of users comprises more users than the first set of users.
2. The method of claim 1 , further comprising sending, in response to determining that the current-prompting probability is above a second threshold probability, the safety-check prompt to each of a third set of users, wherein the third set of users comprises more users than the second set of users and the second threshold probability is higher than the first threshold probability.
3. The method of claim 1 , wherein the safety-check prompt comprises one or more selectable icons that enable a user to indicate a safety status associated with the user.
4. The method of claim 1 , wherein identifying an emergency event comprises classifying, based on one or more emergency metrics, a plurality of items on an alert feed as either a qualifying emergency or as a non-qualifying emergency.
5. The method of claim 1 , wherein the current-prompting probability is determined at regular intervals.
6. The method of claim 1 , wherein the one or more engagement metrics comprise:
a number of users in the first set of users who have interacted with the safety-check prompt;
a number of users in the first set of users who have ignored or hid the safety-check prompt; or
a number of impressions of the safety-check prompt.
7. The method of claim 1 , wherein determining that a threshold percentage of users associated with the emergency event have posted content related to the emergency event comprises, for each user who has posted content to the online social network within a threshold timeframe:
determining that the user is associated with the emergency event;
extracting one or more text strings from the posted content; and
applying a natural language analysis to determine that the text strings comprise one or more n-grams that are related to the emergency event.
8. The method of claim 1 , wherein the emergency event is associated with a particular geographic location, and each user in the first set of users and each user in the second set of users is also associated with the particular geographic location.
9. The method of claim 1 , wherein the first set of users are randomly selected from the users who have posted content related to the emergency event to the online social network.
10. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
identify an emergency event;
determine that a threshold percentage of users who are associated with the emergency event have posted content related to the emergency event to an online social network;
send, in response to the determination, a safety-check prompt to each of a first set of users;
determine a current-prompting probability based on one or more engagement metrics of the safety-check prompt by the first set of users; and
send, in response to determining that the current-prompting probability is above a first threshold probability, the safety-check prompt to each of a second set of users, wherein the second set of users comprises more users than the first set of users.
11. The media of claim 10 , wherein the software is further operable when executed to send, in response to determining that the current-prompting probability is above a second threshold probability, the safety-check prompt to each of a third set of users, wherein the third set of users comprises more users than the second set of users and the second threshold probability is higher than the first threshold probability.
12. The media of claim 10 , wherein the safety-check prompt comprises one or more selectable icons that enable a user to indicate a safety status associated with the user.
13. The media of claim 10 , wherein identifying an emergency event comprises classifying, based on one or more emergency metrics, a plurality of items on an alert feed as either a qualifying emergency or as a non-qualifying emergency.
14. The media of claim 10 , wherein the current-prompting probability is determined at regular intervals.
15. The media of claim 10 , wherein the one or more engagement metrics comprise:
a number of users in the first set of users who have interacted with the safety-check prompt;
a number of users in the first set of users who have ignored or hid the safety-check prompt; or
a number of impressions of the safety-check prompt.
16. The media of claim 10 , wherein the emergency event is associated with a particular geographic location, and each user in the first set of users and each user in the second set of users is also associated with the particular geographic location.
17. A system comprising: one or more processors; and a memory coupled to the processors comprising instructions executable by the processors, the processors being operable when executing the instructions to:
identify an emergency event;
determine that a threshold percentage of users who are associated with the emergency event have posted content related to the emergency event to an online social network;
send, in response to the determination, a safety-check prompt to each of a first set of users;
determine a current-prompting probability based on one or more engagement metrics of the safety-check prompt by the first set of users; and
send, in response to determining that the current-prompting probability is above a first threshold probability, the safety-check prompt to each of a second set of users, wherein the second set of users comprises more users than the first set of users.
18. The system of claim 17 , wherein the processors are further operable when executing the instructions to send in response to determining that the current-prompting probability is above a second threshold probability, the safety-check prompt to each of a third set of users, wherein the third set of users comprises more users than the second set of users and the second threshold probability is higher than the first threshold probability.
19. The system of claim 17 , wherein the safety-check prompt comprises one or more selectable icons that enable a user to indicate a safety status associated with the user.
20. The system of claim 17 , wherein the current-prompting probability is determined at regular intervals.