Creating customized user dictionary

1. A computer-implemented method, performed by one or more computing devices, comprising:

by one or more computer servers, collecting a plurality of words from texts submitted by a user;

by one or more computer servers, for each of a plurality of communication categories, determining a usage frequency of each of one or more of the words within the communication category; wherein each of the communication categories is characterized by at least one communication channel, wherein the at least one communication channel comprises an input device used for submitting the texts; and

by the one or more computer servers, constructing one or more customized dictionaries that each comprise a blending of selected words from the plurality of words from texts submitted by the user, a first customized dictionary being associated with a first type of input device and a second customized dictionary being associated with a second type of input device, the first customized dictionary being distinct from the second customized dictionary, the second type of input device different than the first type of input device, the construction of the one or more customized dictionaries comprising:

for each of the customized dictionaries,

by the one or more computer servers, selecting one or more frequently used words from each of one or more of the communication categories based on the usage frequency of each of one or more of the words;

by the one or more computer servers, determining a specific blending of the frequently used words selected from each of the communication categories; and

by the one or more computer servers, blending the frequently used words selected from each of the communication categories to construct the customized dictionary.

2. The method of claim 1 , further comprising:

for each of the plurality of communication categories, sorting the plurality of words based on the usage frequency of each of the words within the communication category; and

constructing a usage-frequency table that comprises the communication categories and the frequently used words from each of the communication categories.

3. The method of claim 1 , wherein constructing one of the customized dictionaries comprises:

determining a coefficient for each of the communication categories; and

blending the frequently used words from each of the communication categories based on the coefficient of each of the communication categories.

4. The method of claim 1 , further comprising:

discarding from the plurality of words one or more undesirable words; and

adding to the plurality of words one or more desirable words.

5. The method of claim 1 , wherein:

the customized dictionaries are constructed for one or more particular users respectively; and

for each of the customized dictionaries, the blending of the frequently used words from each of the communication categories is determined based on the corresponding user.

6. The method of claim 1 , wherein:

the customized dictionaries are constructed for one or more groups of users respectively; and

for each of the customized dictionaries, the blending of the frequently used words from each of the communication categories is determined based on the corresponding group of users.

7. The method of claim 1 , wherein:

the customized dictionaries are constructed for one or more communication channels respectively; and

for each of the customized dictionaries, the blending of the frequently used words from each of the communication categories is determined based on the corresponding communication channel.

8. The method of claim 1 , further comprising:

monitoring additional texts submitted by the users;

for each of the communication categories, updating the usage frequencies of the words in the communication category based on the additional texts; and

updating the customized dictionaries based on the updated usage frequencies.

9. The method of claim 1 , wherein:

the texts are received through one or more communication channels that each comprise one or more communication dimensions; and

each of the communication categories represents a unique pair of communication dimensions.

10. The method of claim 9 , wherein:

the communication channels comprise one or more of mobile input device, non-mobile input device, chat, e-mail, message, comment, status update, post, or communication object; and

the communication dimensions comprise one or more of locale, language, geography, culture, user friend list, or communication method.

11. A system comprising:

a memory comprising instructions executable by one or more processors; and

the one or more processors coupled to the memory and operable to execute the instructions, the one or more processors being operable when executing the instructions to:

collect a plurality of words from texts submitted by a user;

for each of a plurality of communication categories, determine a usage frequency of each of one or more of the words within the communication category, wherein each of the communication categories is characterized by at least one communication channel, wherein the at least one communication channel comprises an input device used for submitting the texts; and

construct one or more customized dictionaries that each comprise a blending of selected words from the plurality of words from texts submitted by the user, a first customized dictionary being associated with a first type of input device and a second customized dictionary being associated with a second type of input device, the second type of input device different than the first type of input device, the first customized dictionary being distinct from the second customized dictionary, the construction of the one or more customized dictionaries comprising:

for each of the customized dictionaries,

select one or more frequently used words from each of one or more of the communication categories based on the usage frequency of each of one or more of the words;

determine a specific blending of the frequently used words selected from each of the communication categories; and

blend the frequently used words selected from each of the communication categories to construct the customized dictionary.

12. The system of claim 11 , wherein construct one of the customized dictionaries comprises:

determine a coefficient for each of the communication categories; and

blend the frequently used words from each of the communication categories based on the coefficient of each of the communication categories.

13. The system of claim 11 , wherein:

the customized dictionaries are constructed for one or more particular users respectively; and

for each of the customized dictionaries, the blending of the frequently used words from each of the communication categories is determined based on the corresponding user.

14. The system of claim 11 , wherein:

the customized dictionaries are constructed for one or more groups of users respectively; and

for each of the customized dictionaries, the blending of the frequently used words from each of the communication categories is determined based on the corresponding group of users.

15. The system of claim 11 , wherein:

the customized dictionaries are constructed for one or more communication channels respectively; and

for each of the customized dictionaries, the blending of the frequently used words from each of the communication categories is determined based on the corresponding communication channel.

16. One or more non-transitory computer-readable storage media embodying software operable when executed by one or more computer systems to:

collect a plurality of words from texts submitted by a user;

for each of a plurality of communication categories, determine a usage frequency of each of one or more of the words within the communication category, wherein each of the communication categories is characterized by at least one communication channel, wherein the at least one communication channel comprises an input device used for submitting the texts; and

construct one or more customized dictionaries that each comprise a blending of selected words from the plurality of words from texts submitted by the user, a first customized dictionary being associated with a first type of input device and a second customized dictionary being associated with a second type of input device, the second type of input device different than the first type of input device, the first customized dictionary being distinct from the second customized dictionary, the construction of the one or more customized dictionaries comprising:

for each of the customized dictionaries,

select one or more frequently used words from each of one or more of the communication categories based on the usage frequency of each of one or more of the words;

determine a specific blending of the frequently used words selected from each of the communication categories; and

blend the frequently used words selected from each of the communication categories to construct the customized dictionary.

17. The non-transitory computer-readable storage media of claim 16 , wherein construct one of the customized dictionaries comprises:

determine a coefficient for each of the communication categories; and

blend the frequently used words from each of the communication categories based on the coefficient of each of the communication categories.

18. The non-transitory computer-readable storage media of claim 16 , wherein:

the customized dictionaries are constructed for one or more particular users respectively; and

for each of the customized dictionaries, the blending of the frequently used words from each of the communication categories is determined based on the corresponding user.

19. The non-transitory computer-readable storage media of claim 16 , wherein:

the customized dictionaries are constructed for one or more groups of users respectively; and

for each of the customized dictionaries, the blending of the frequently used words from each of the communication categories is determined based on the corresponding group of users.

20. The non-transitory computer-readable storage media of claim 16 , wherein:

the customized dictionaries are constructed for one or more communication channels respectively; and

for each of the customized dictionaries, the blending of the frequently used words from each of the communication categories is determined based on the corresponding communication channel.