TECHNICAL FIELD
The present invention generally relates to the field of mobile applications, and more particularly, to a method and a system for analysing social network application data to predict gender of a user.
BACKGROUND 5
This section is intended to provide information relating to the field of the invention and thus any approach/functionality described below should not be assumed to be qualified as prior art merely by its inclusion in this section.
Procuring gender information of people may be quite useful in social and commercial fields of marketing. The gender information may be used in several 10 tasks such as conducting a plurality of surveys, identifying usage and/or purchasing trends of various products and/or services by a particular gender type, creating targeted advertisements, etc.
The advent and subsequent popularity of Internet-based social networking applications has successfully connected billions of users with each other. The use 15 of social networking applications not only provides a platform to connect people, but also generates a plethora of information that can be analysed and used for various purposes. One particular area of interest to social network analysts is obtaining gender information of various users.
The gender information of different users, i.e. whether a user is a male, or a 20 female may be obtained by implementing various approaches. One of the existing approaches to determine the gender type (i.e. male or female or other gender type) of a particular user involves analysis of the user’s first name as given in his/her user-profile, and subsequently predicting the probability of a user’s gender based on said name. Such approaches base the prediction on 25 previously known names, that are typically associated with a particular gender
3
type. For instance, ‘John’ is mostly named by a male user and the name ‘Christine’ is likely to be female name. However, such approach of gender prediction fails when a name cannot be typically associated with a particular gender type. For example, the name ‘Harpreet’ can be of a male person as well as a female person. In such instances, the prediction of gender type may not be 5 accurately carried out.
Another prior art methodology for determining gender includes analysing the social connections of a user. For instance, if the gender of a connection of a particular user is male and the user has been marked as a spouse of said connection, then it can be easily interpreted that the gender of the first user is 10 female. Although, many a times, users of the social networking applications are hesitant in providing and sharing their actual first username or their gender information in their social networking user-profile. In such instances, gender information of the user may be obtained by looking up the user on other social platforms wherein said user may have provided such information. 15
However, the above-mentioned solution for obtaining the gender information have certain limitations, as primarily the existing approach/solution require a fore knowledge of a user’s connections. Another limitation or drawback of existing systems lies in the dependency on the data provided on other social platforms, wherein the chances of error for identifying a user’s corresponding 20 profile on another platform are very high. Therefore, there exists a need in the art to develop a method and system for efficiently predicting the gender of a user of a social network.
Therefore, in view of the above drawbacks and limitations of the existing solutions, there exists a need to provide a system and a method for procuring 25 gender information of a user by accurately analysing social networking data of the said user.
4
SUMMARY
This section is provided to introduce certain objects and aspects of the present disclosure in a simplified form that are further described below in the detailed description. This summary is not intended to identify the key features or the scope of the claimed subject matter. 5
An object of the present invention is to provide a system and method for procuring gender information of a user of a social networking application by analysing social network application data in respect of the user.
Another object of the invention is to provide systems and methods for predicting the gender of a user without any foreknowledge of the gender or any other 10 demographic details of the user’s social connections.
Yet another object of the present invention is to obtain name information of the user to identify any gender connotations associated with the name of the user, wherein the gender connotations may include relationship synonyms like ‘son’, daughter’, ‘uncle’, ‘aunt’ etc. that may be associated with the name of the user 15 to form a name information of a user, for example, “John Uncle” or “Aunt Mary”.
The present invention discloses a system and a method for predicting gender of a user of a social networking application. In one embodiment herein, the method comprises retrieving one or more address book entries made in respect of the user from one or more address books, the entries pertaining to at least a name 20 information of the user; storing, by a gender prediction module configured in a server, the retrieved one or more address book entries to create a reverse address book of the user; extracting the name information of the user from the reverse address book, to identify at least one gender connotation of said user, wherein each of the gender connotation corresponds to a gender type; 25 processing the identified at least one gender connotation by automatically comparing said gender connotation with one or more pre-configured gender
5
connotations stored in a storage unit; and predicting the gender of the user based at least on the comparison.
In one embodiment, a system is provided for predicting gender of a user of a social networking application. The system comprises one or more devices storing one or more address books having one or more address book entries made in 5 respect of the user, the entries pertaining to at least a name of the user. The system further comprises a server connected to the one or more devices, said server comprising a gender prediction module configured to: retrieve the stored address book entries from the one or more devices, create a reverse address book by storing the retrieved entries in a memory coupled to the server, extract 10 the name information of the user from the reverse address book, to identify at least one gender connotation of said user, wherein each of the gender connotation corresponds to a gender type; process the identified at least one gender connotation by automatically comparing said gender connotation with one or more pre-configured gender connotations stored in a storage unit; and 15 predict the gender of the user based at least on the comparison.
BRIEF DESCRIPTION OF THE DRAWINGS
The accompanying drawings, which are incorporated herein, and constitute a part of this disclosure, illustrate exemplary embodiments of the disclosed methods and systems in which like reference numerals refer to the same parts 20 throughout the different drawings. Components in the drawings are not necessarily to scale, emphasis instead being placed upon clearly illustrating the principles of the present disclosure. Some drawings may indicate the components using block diagrams and may not represent the internal circuitry of each component. It will be appreciated by those skilled in the art that disclosure 25 of such drawings includes disclosure of electrical components or circuitry commonly used to implement such components.
6
Figure 1 is a block diagram illustrating a system architecture [100] for predicting gender of a user of a social networking application, in accordance with an embodiment of the present invention.
Figure 2 illustrates a table [200] of the pre-configured gender connotations, in accordance with an exemplary embodiment of the present invention. 5
Figure 3 is a flow chart illustrating a method [300] for predicting gender of a user of a social networking application, in accordance with an embodiment of the present invention.
DETAILED DESCRIPTION
In the following description, for the purposes of explanation, various specific 10 details are set forth in order to provide a thorough understanding of embodiments of the present disclosure. It will be apparent, however, that embodiments of the present disclosure may be practiced without these specific details. Several features described hereafter can each be used independently of one another or with any combination of other features. An individual feature 15 may not address any of the problems discussed above or might address only one of the problems discussed above. Some of the problems discussed above might not be fully addressed by any of the features described herein. Example embodiments of the present disclosure are described below, as illustrated in various drawings in which like reference numerals refer to the same parts 20 throughout the different drawings.
The present invention would now be discussed in context of embodiments as illustrated in the accompanying drawings.
Figure 1 is a block diagram illustrating a system architecture [100] for predicting gender of a user of a social networking application, in accordance with an 25 embodiment of the present invention. The system [100] comprises a server [104]
7
communicatively connected to at least one electronic device [102]. Each of the said electronic devices [102] stores at least one address book [110] comprising one or more address book entries made in respect of the user. The server [104] comprises a Gender prediction module [112] coupled to a processing unit [114]. The server [104] is further coupled to a storage unit [106] that stores a reverse 5 address book [116] for the user.
Each of the address books [110] stored in the electronic device [102], comprises one or more address book entries made in respect of one or more users. Each of the one or more users are associated with a unique identifier that facilitates in creating a unique reverse address book [116] for each user. The address book 10 entries may, inter-alia, include the unique identifier and respective name information [108] of the one or more users. Various name information [108] of a particular user may be stored in one or more devices [102]. For example, as shown in figure 1, Electronic Device 1, Electronic Device 2, and Electronic Device 3 may respectively store Address Book 1, Address Book 2, and Address Book 3. 15 Each of the respective address books [110] of each of the devices [102], may store name information [108] of ‘User1’ that may be extracted by the server [104] for gender prediction, wherein ‘User1’ may be associated with a unique identifier includes any one of a multi-digit number and an alpha-numeric user ID.
In one embodiment of the present invention, the server [104] is an Internet-20 based server or system that is configured to communicate with the electronic devices [102] via at least one communication network, such as Internet. In various embodiments herein, the at least one electronic device [102] includes, but is not limited to, a personal computer (PC), a mobile phone, a Personal Digital Assistant (PDA), a smart phone, a smart TV, a wearable electronic device 25 [102] and any other electronic communication device [102] that is, inter-alia, equipped with at least one processor, a memory, a display screen, operating system, etc. The at least one electronic device [102] may be registered with the
8
server [104] for procuring gender information of the users whose name information [108] are stored in the address books [110] of the electronic devices [102]. Further, each of the electronic devices [102] may be capable of executing a social networking application, wherein a user profile as created in the social networking application, may be added in the address books [110] along with the 5 name information [108] of the user in the one or more electronic devices [102]. The user profile may include information such as contact numbers, photos, postal address, email addresses, company names, birthdays, social profiles, instant message numbers or IDs, etc., of the user. Further, the social networking application may facilitate the server [104] in identifying ‘social network’ of the 10 user. As used herein, the “social network” refers to a network of social connections of any user, wherein such connections may be on one or more social networking platforms being executed on any electronic device [102]. Each user in a social network is associated or connected to one or more other users. As used herein, “connection” of a user refers to one or more users that are connected to 15 said user on one or more social platforms. In addition to the ‘connections’, the address books may also be retrieved from one or more memory cards, hard drives, pen drives and any other devices that may be connected to the server and that can be accessed by the server [104] to retrieve the required information. 20
The invention encompasses receiving a request on the server [104] for predicting the gender of a user, wherein such request may be received from a human operator/stakeholder or from a program module. This request includes the name and details of a user whose gender is required to be determined/ predicted, wherein details may include by way of an example, the mobile number of the 25 user, unique identification number assigned by the system, etc.
9
Accordingly, the Gender prediction module [112] is configured to receive such requests and thereby retrieve the name information [108] of the user, from the address books [110] of the one or more electronic devices [102]. The name information [108] of the user may be associated with gender connotations, wherein the gender connotations may be defined as the synonyms, that are used 5 in one or more languages, for depicting any relationship name, and that corresponds to a gender type. The address book entries of a particular user are extracted from different devices [102] to create a ‘reverse address book’ [116] of the user. The reverse address books [116] are created for each of the users and are stored in the storage unit [106] operatively coupled to the server [104]. In 10 one embodiment of the present invention, the storage unit [106] may be internally configured within the server [104]. Further, as illustrated in figure 1, a reverse address book [116] may be uniquely created for a particular user. For example, ‘Reverse address book 1’ [116] may be created for ‘User 1’; ‘Reverse address book [116] 2’ may be created for ‘User 2’; and so on, wherein each of 15 the reverse address books [116] comprises name information [108] of the user and its associated gender connotations. Further, in this example, the ‘Reverse address book 1’ [116] of ‘User1’ may include information related to other users, for instance ‘User2’, ‘User3’ etc., who can be ‘connections’ of ‘User1’. In other words, if ‘User2’ has stored name of ‘User1’ as “my-sister” and phone number as 20 “229922”, then this entry “my-sister, 229922” forms a part of the ‘Reverse address book1’ [116] for ‘User1’, wherein ‘sister’ will be the associated gender connotation and ‘female’ will be its corresponding gender type.
The reverse address book [116] of the user is accessed to extract name information [108] of the user for identifying at least one gender connotation of 25 said user, wherein each of the gender connotation corresponds to a gender type. The identified gender connotations are further processed by the processing unit [114] by automatically comparing said gender connotation with one or more pre-configured gender connotations stored in the storage unit [106]. The output of
10
the compared entities, predict the gender of the user based at least on the comparison. In one embodiment of the present invention, the one or more pre-configured gender connotations are stored in the storage unit [106] along with one or more family relationship names in one or more languages, said name associated with the one or more pre-configured gender connotations and 5 corresponding gender type.
According to the embodiments of the present invention, the Gender prediction module [112] is may be further configured to run a first counter check mechanism for comparing a threshold value, with a first count of occurrence of any identified gender connotations for the user in the reverse address book 10 [116]. A second counter check mechanism may also be executed by the the Gender prediction module [112] for maintaining a count value associated with each gender type. In an event of variations in the gender type associated with the identified gender connotations, the predicted gender output is the gender type with a highest count value. 15
Figure 2 illustrates a dictionary [200] of the pre-configured gender connotations associated with a gender type, in accordance with an exemplary embodiment of the present invention. As described earlier, the gender prediction module [112] is configured to retrieve the name information [108] of the user, from the reverse address book [116] of the user. The name information [108] is generally 20 associated with a gender connotation that facilitates in identifying one or more family relationships of the user. Hence, the dictionary [200] is generated in the server [104] by the Gender prediction module [112], wherein the dictionary [200] comprises one or more relationship-names’, ‘pre-configured gender connotations’, and ‘gender type’. Each of the ‘relationship-names’ is associated 25 with a plurality of ‘pre-configured gender connotations’, and each of the ‘pre-configured gender connotations’ depicts a particular ‘gender type’. The dictionary [200] is generated by forming various groups for each of the
11
relationship-names. Each group of a particular relationship-name is provided with a set of ‘pre-configured gender connotations’, in one or more languages, that are likely to be associated with the said relationship-name. Further, a single ‘gender type’ is pre-assigned for each of the ‘pre-configured gender connotations’. For example, and as shown in the table, the dictionary [200] may 5 include gender specific family relationship names such as father, mother, brother, sister, grandfather, grandmother, uncle, aunt, spouse, maternal grandmother, paternal grandmother, maternal grandfather, paternal grandfather, etc. The dictionary [200] may include a plurality of pre-configured gender connotations for said family relationship names in multiple languages, 10 including but not limited to, different Indian languages, for example, Hindi, English, Assamese, Bengali, Gujarati, Kannada, Malayalam, Marathi, Oriya, Punjabi, Tamil, Telugu, Urdu and Sinhala, and/or international language, for example, German, English, French, Hebrew, etc. The pre-configuration of the multi-language gender connotations facilitates in quick processing time of the 15 retrieved name information [108] as it is readily available within the server [104]. For instance, if the reverse address book [116] entry of ‘User1’ includes a gender connotation “Maa”, then the Gender prediction module [112] retrieves “Maa” and processes it for predicting its gender. Thereafter, the module searches for the said name “Maa” in the pre-defined dictionary [200], wherein said 20 connotation is stored as a synonym for the relationship name ‘Mother’. Further, one or more rules, may be pre-defined to facilitate the Gender prediction module [112] to map the retrieved gender connotation with the pre-configured gender connotation of the dictionary [200] and thereby determine that “Maa” is to be classified as a female. Therefore, the gender of ‘User1’ may be predicted to 25 be ‘Female’.
Figure 3 is a flow chart illustrating a method [300] for predicting gender of a user of a social networking application, in accordance with an embodiment of the present invention.
12
At step 302, one or more address book entries are retrieved from one or more address books [110]. The address book entries are created in respect of the user pertaining to at least a name information [108] of the user. The one or more address book entries may be stored on the electronic devices [102] registered with the server [104]. Further, the reverse address book [116] of said user is re-5 analysed periodically, to accommodate any new or updated address book entry of the user made in the devices [102]. Furthermore, the reverse address book [116] of the user is also updated based on said re-analysis.
At step 304, the retrieved one or more address book entries are stored in the server [104] to create a reverse address book [116] of the user. The Gender 10 prediction module [112] may be configured to create a plurality of reverse address books [116], wherein each address book [110] is uniquely created for each user, and each reverse address book [116] comprises name information [108] of the respective user.
At step 306, the name information [108] of the user is extracted from the reverse 15 address book [116], to identify at least one gender connotation of said user. The gender connotations are the synonyms, used in one or more languages, for depicting any relationship name, and also corresponds to a gender type. For example, “Maa” is a synonym of mother in Hindi and Sanskrit languages, and it corresponds to the ‘female’ gender type. 20
At step 308, the gender connotation identified by the gender prediction module [112] is processed and automatically compared with one or more pre-configured gender connotations listed in the dictionary [200] within the storage unit [106].
At step 310, the gender of the user is predicted based on the comparison of the identified gender connotation and the pre-configured gender connotations. In an 25 embodiment of the present invention, the gender of the user may be predicted based on a first counter check mechanism. The first counter check mechanism
13
checks for the occurrences of the identified gender connotation from the reverse book address of a particular user. Thereafter, a first count of occurrence of said identified gender connotations for the user in the reverse address book [116] is compared with a threshold value. If the first count is equal to, or higher than the threshold value; then the result of the gender prediction is outputted. However, 5 if the first count is less than the threshold value, then the gender information of the user is not predicted until the first count exceeds the threshold value. For example, if the threshold value is set as ‘4’, then 4 or higher number of gender connotations will be required to be identified to obtain the gender prediction output. 10
In an embodiment of the present invention, a user’s gender is predicted based on each of the reverse address book [116] entries that are retrieved from the various devices [102]. For example, if five entries exist in the reverse address book [116] made in respect of ‘User1’, then for each of the five entries, the gender type may be identified on the basis of all the gender connotations that 15 are associated in these five entries. Thereafter, each of these results (i.e. identified gender connotations) is used by the second counter check mechanism to determine the final gender prediction result. Further, in an event of occurrence of two out of the five results as one gender type, and rest of the three results as another gender type; the final result of the gender prediction will 20 be based on the majority i.e. the three results that predicted another gender type. Thus, predicting the gender of the user is also based on the second counter check mechanism, wherein a count value for each gender type occurrence is maintained. In any event of variations in the gender type associated with the identified gender connotations, the final predicted gender is outputted as the 25 gender type occurring the highest number of times, i.e. the final output is based on the gender type having the highest count value.
14
The present invention provides immense improvement over the existing system for procuring gender information, and has numerous advantages. Some of these advantages may include, but are not limited to, obtaining gender information of a user in a quick time due to the pre-configuration of the gender connotation dictionary [200] that is readily available in the server [104] for the mapping 5 process. In addition, the embodiments of the present invention facilitate in identifying gender connotations in various languages that are popularly used in various geographical regions.
The various elements of the present invention as discussed above may be present in the form of a hardware or a software or a hardware-software 10 combination for performing functions and/or operations for the implementation and execution of the rich media content. The connections and/or links between each device [102], elements, modules, and/or databases shown in the figures are exemplary and may be connected or linked together in various other possible ways. The connections and/or links may be physical (such as wired or wireless 15 connections/links) or logical (such as implementing in semiconductor device [102]).
The gender prediction system [100] may include a bus or other communication mechanism for communicating information, and a processor or processing unit coupled with the bus for processing information and data or set of data. The 20 hardware processor may be, for example, a general-purpose microprocessor.
According to the embodiments of the present disclosure, the techniques described herein are implemented by one or more special-purpose computing devices. The special-purpose computing devices may be hard-wired to perform the techniques, or may include digital electronic devices such as one or more 25 application-specific integrated circuits (ASICs) or field programmable gate arrays (FPGAs) that are persistently programmed to perform the techniques, or may include one or more general purpose hardware processors programmed to
15
perform the techniques pursuant to program instructions in firmware, memory, other storage, or a combination. Such special-purpose computing devices may also combine custom hard-wired logic, ASICs, or FPGAs with custom programming to accomplish the techniques.
The memory used for storing various data and contents may include a random-5 access memory (RAM) or other dynamic storage device, coupled to the bus for storing information and instructions to be executed by the processing unit. The memory may also be used for storing temporary variables or other intermediate information during execution of instructions to be executed by the processing unit. Such instructions, when stored in non-transitory storage media accessible 10 to the processing unit, render the computer system into a special-purpose machine that is customized to perform the operations specified in the instructions.
The memory may further include a read only memory (ROM) or other static storage device coupled to the bus for storing static information and instructions 15 for the processor. A storage unit [106], such as a magnetic disk, optical disk, or solid-state drive or device is provided and coupled to the bus for storing information and instructions.
The gender prediction system [100] may be coupled via the bus to a display, such as a cathode ray tube (CRT), for displaying information to a computer user. An 20 input device, including alphanumeric and other keys, is coupled to the bus for communicating information and command selections to the processor. A cursor control, such as a mouse, a trackball, or cursor direction keys, may also be coupled to the bus for communicating direction information and command selections to the processor and for controlling cursor movement on the display. 25 The cursor control typically has two degrees of freedom in two axes, a first axis (e.g., x) and a second axis (e.g., y), that allows the cursor control to specify positions in a plane.
16
The term “store” as used herein refers to any non-transitory media that store data and/or instructions that cause a machine to operate in a specific fashion. Such storage media may comprise non-volatile media and/or volatile media. Non-volatile media includes, for example, optical disks, magnetic disks, or solid-state drives, such as the storage device. Volatile media may include dynamic 5 memory, such as the main memory. Common forms of storage media include, for example, a floppy disk, a flexible disk, hard disk, solid-state drive, magnetic tape, or any other magnetic data storage medium, a CD-ROM, any other optical data storage medium, any physical medium with patterns of holes, a RAM, a PROM, and EPROM, a FLASH-EPROM, NVRAM, or any other memory chip or 10 cartridge.
Various forms of store may be involved in carrying one or more sequences of one or more instructions to the processor for execution. For example, the instructions may initially be carried on a magnetic disk or solid-state drive of a remote computer. The remote computer can load the instructions into its 15 dynamic memory and send the instructions over a telephone line using a modem.
The gender prediction system [100] also includes a communication interface coupled to the bus. The communication interface provides a two-way data communication coupling to a network link that is connected to a local network. 20 For example, the communication interface may be an integrated service digital network (ISDN) card, cable modem, satellite modem, or a modem to provide a data communication connection to a corresponding type of telephone line. As another example, the communication interface may be a local area network (LAN) card to provide a data communication connection to a compatible LAN. 25 Wireless links may also be implemented. In any such implementation, the communication interface sends and receives electrical, electromagnetic or
17
optical signals that carry digital data streams representing various types of information.
Although, the present invention has been described with respect to a scenario where the address book entries of a user of a social networking application is received by a server [104] sends a request to extract name information [108] and 5 perform gender prediction, however, it will be appreciated by those skilled in the art that the present invention is also applicable in scenarios where any end user may be the registered user of any mobile application being executed in a device and thereafter extract and use the name-information of the user via said mobile application. Further, a limited number of the devices [102] in figure 1, and a 10 limited number of the pre-configured gender connotations in figure 2 have been shown; however, it will be appreciated by those skilled in the art that the overall system of Figure. 1 of the present invention encompasses any number of devices [102], and the pre-configured gender connotations.
While considerable emphasis has been placed herein on the disclosed 15 embodiments, it will be appreciated that many embodiments can be made and that many changes can be made to the embodiments without departing from the principles of the present disclosure. These and other changes in the embodiments of the present disclosure will be apparent to those skilled in the art, whereby it is to be understood that the foregoing descriptive matter to be 20 implemented is illustrative and non-limiting.

We Claim:
1. A method for predicting gender of a user at a social networking application, the method comprising:
- retrieving one or more address book entries made in respect of the user from one or more address books [110], the entries 5 pertaining to at least a name information [108] of the user;
- storing, by a gender prediction module [112] configured in a server [104], the retrieved one or more address book entries to create a reverse address book [116] of the user;
- extracting the name information [108] of the user from the 10 reverse address book [116], to identify at least one gender connotation of said user, wherein each of the gender connotation corresponds to a gender type;
- processing the identified at least one gender connotation by automatically comparing said gender connotation with one or 15 more pre-configured gender connotations stored in a storage unit [106]; and
- predicting the gender of the user based at least on the comparison.
2. The method as claimed in claim 1, wherein the user is associated with a 20 unique identifier.
3. The method as claimed in claim 1, further comprising registering the one or more devices [102] with the server [104] for retrieving the one or more address book entries made therein in respect of the user.
4. The method as claimed in claim 1, wherein predicting the gender of the 25 user may be further based on a first counter check mechanism including comparing a first count of occurrence of said identified gender
19
connotations for the user in the reverse address book [116] with a threshold value.
5. The method as claimed in claim 1, wherein predicting the gender of the user may be further based on a second counter check mechanism including maintaining a count value associated with each gender type, 5 and in an event of variations in the gender type associated with the identified gender connotations, the predicted gender may be the gender type with a highest count value.
6. The method as claimed in claim 1, wherein the storage unit [106] stores at least one family relationship name in one or more languages, said 10 name associated with one or more pre-configured gender connotations and gender type.
7. The method as claimed in claim 1, wherein the predicted gender may provide a basis for recommending at the social networking application, one or more gender specific features or content to the user. 15
8. The method as claimed in claim 1, further comprising re-analysing periodically, the reverse address book [116] of said user, based on an updated address book entry of the user in the one or more devices [102] and updating the reverse address book [116] of the user based on said re-analysis. 20
9. The method as claimed in claim 1, wherein the address books [110] are stored in one or more devices [102].
10. A system for predicting gender of a user of a social networking application, the method comprising:
- one or more devices [102] storing one or more address books 25 [110] comprising one or more address book entries made in
20
respect of the user, the entries pertaining to at least a name of the user; and
- a server [104] connected to the one or more devices [102], said server [104] comprising a gender prediction module [112] configured to: 5
retrieve the stored address book entries from the one or more devices [102],
create a reverse address book [116] by storing the retrieved entries in a storage unit [106] coupled to the server [104],
extract the name information [108] of the user from the 10 reverse address book [116], to identify at least one gender connotation of said user, wherein each of the gender connotation corresponds to a gender type;
process the identified at least one gender connotation by automatically comparing said gender connotation with one or 15 more pre-configured gender connotations stored in a storage unit [106]; and
predict the gender of the user based at least on the comparison.