TECHNIQUES FOR RANKING OF SELECTED BOTS
Techniques for ranking of selected bots are described. In one embodiment, for example, an apparatus may comprise a client front-end component operative to receive a bot contact display prompt from a client device; and send an ordered bot contact list to the client device; a bot contact list component operative to retrieve a bot contact list from a selection component, the bot contact list comprising a plurality of bot contacts; and a contact ranking component operative to determine a ranking weight for each of the plurality of bot contacts; and generate the ordered bot contact list by ordering the bot contact list based on the ranking weight. Other embodiments are described and claimed.
1 . A computer-implemented method, comprising:
receiving a bot contact display prompt from a client device;
retrieving a bot contact list from a selection component, the bot contact list comprising a plurality of bot contacts;
determining a ranking weight for each of the plurality of bot contacts;
generating an ordered bot contact list by ordering the bot contact list based on the ranking weight; and
sending the ordered bot contact list to the client device.
2 . The method of claim 1 , the bot contact display prompt comprising a null-state search prompt, further comprising:
determining the ranking weight for each of the plurality of bot contacts based on bot-specific information and social-context information.
3 . The method of claim 1 , further comprising:
modifying the ranking weight for one or more of the plurality of bot contacts based on a compensated-promotion indicator for the one or more of the plurality of bot contacts.
4 . The method of claim 1 , further comprising:
modifying the ranking weight for one or more of the plurality of bot contacts based on an existing-bot-thread indicator for the one or more of the plurality of bot contacts.
5 . The method of claim 1 , the bot contact display prompt comprising a user search prompt, further comprising:
determining the ranking weight for each of the plurality of bot contacts based on bot-specific information, social-context information, and bot-specific search-result performance information.
6 . The method of claim 5 , the bot-specific information comprising one or more of a page-bot relationship indicator, a bot category, a bot active-thread count, a bot user-retention rate, and a bot block rate; the social-context information comprising one or more of a bot-friend interaction count, a bot-history-similarity measure, a user-bot-block measure, and a messaging-context intent determination.
7 . The method of claim 5 , the ranking weight for each of the plurality of bot contacts based on a linear function combining the bot-specific information, the social-context information, and the bot-specific search-result performance information, the linear function determined based on a linear regression of a historical data set for bot interactions, the linear regression optimizing for one or more of bot click-through rate and top-used-bot summed-rankings.
8 . The method of claim 1 , further comprising:
determining the ranking weight for each of the plurality of bot contacts based on a linear function of a bot growth measure, a bot responsiveness measure, a bot quality measure, and a bot volume measure.
9 . An apparatus, comprising:
a client front-end component operative to receive a bot contact display prompt from a client device; and send an ordered bot contact list to the client device;
a bot contact list component operative to retrieve a bot contact list from a selection component, the bot contact list comprising a plurality of bot contacts; and
a contact ranking component operative to determine a ranking weight for each of the plurality of bot contacts; and generate the ordered bot contact list by ordering the bot contact list based on the ranking weight.
10 . The apparatus of claim 9 , further comprising:
the contact ranking weight operative to determine the ranking weight for each of the plurality of bot contacts based on a linear function of a bot growth measure, a bot responsiveness measure, a bot quality measure, and a bot volume measure.
11 . The apparatus of claim 9 , the bot contact display prompt comprising a user search prompt, further comprising:
the contact ranking component operative to determine the ranking weight for each of the plurality of bot contacts based on bot-specific information, social-context information, and bot-specific search-result performance information.
12 . The apparatus of claim 11 , the bot-specific information comprising one or more of a page-bot relationship indicator, a bot category, a bot active-thread count, a bot user-retention rate, and a bot block rate; the social-context information comprising one or more of a bot-friend interaction count, a bot-history-similarity measure, a user-bot-block measure, and a messaging-context intent determination.
13 . The apparatus of claim 11 , the ranking weight for each of the plurality of bot contacts based on a linear function combining the bot-specific information, the social-context information, and the bot-specific search-result performance information, the linear function determined based on a linear regression of a historical data set for bot interactions, the linear regression optimizing for one or more of bot click-through rate and top-used-bot summed-rankings.
14 . At least one computer-readable storage medium comprising instructions that, when executed, cause a system to:
receive a bot contact display prompt from a client device;
retrieve a bot contact list from a selection component, the bot contact list comprising a plurality of bot contacts;
determine a ranking weight for each of the plurality of bot contacts;
generate an ordered bot contact list by ordering the bot contact list based on the ranking weight; and
send the ordered bot contact list to the client device.
15 . The computer-readable storage medium of claim 14 , comprising further instructions that, when executed, cause a system to:
determine the ranking weight for each of the plurality of bot contacts based on a linear function of a bot growth measure, a bot responsiveness measure, a bot quality measure, and a bot volume measure.
16 . The computer-readable storage medium of claim 14 , comprising further instructions that, when executed, cause a system to:
modify the ranking weight for one or more of the plurality of bot contacts based on a compensated-promotion indicator for the one or more of the plurality of bot contacts.
17 . The computer-readable storage medium of claim 14 , comprising further instructions that, when executed, cause a system to:
modify the ranking weight for one or more of the plurality of bot contacts based on an existing-bot-thread indicator for the one or more of the plurality of bot contacts.
18 . The computer-readable storage medium of claim 14 , the bot contact display prompt comprising a user search prompt, comprising further instructions that, when executed, cause a system to:
determine the ranking weight for each of the plurality of bot contacts based on bot-specific information, social-context information, and bot-specific search-result performance information.
19 . The computer-readable storage medium of claim 18 , the bot-specific information comprising one or more of a page-bot relationship indicator, a bot category, a bot active-thread count, a bot user-retention rate, and a bot block rate; the social-context information comprising one or more of a bot-friend interaction count, a bot-history-similarity measure, a user-bot-block measure, and a messaging-context intent determination.
20 . The computer-readable storage medium of claim 18 , the ranking weight for each of the plurality of bot contacts based on a linear function combining the bot-specific information, the social-context information, and the bot-specific search-result performance information, the linear function determined based on a linear regression of a historical data set for bot interactions, the linear regression optimizing for one or more of bot click-through rate and top-used-bot summed-rankings.