Method and system for predicting requirements of a user for resources over a computer network

1. A method for training one or more classifiers for predicting one or more user requirements for one or more resources over a computer network, the method comprising:

generating, by one or more processors, a graphical user interface to be displayed on a computing device of a requestor, the graphical user interface including a plurality of tabs selectable by the requestor;

receiving, by a transceiver and the one or more processors, one or more inputs provided by the requestor on the graphical user interface, the one or more inputs relating to a request for identifying the one or more user requirements for the one or more resources;

upon receiving an input from the graphical user interface initiating the identification, retrieving, by the one or more processors from one or more social medial platform servers one or more audio, video, image, or text messages posted by a user on one or more social media websites;

transforming, by the one or more processors, each message of the one or more messages into a first message vector based on at least a comparison with a dictionary;

categorizing, by the one or more processors, each of one or more first message vectors into categories based on a predetermined class label associated with respective message;

for each categorized first message vector in a category from the categories:

transforming, by the one or more processors, the categorized first message vector into a plurality of second message vectors using a wavelet transform technique, wherein each second message vector of the plurality of second message vectors has associated features, and wherein each of the associated features is represented by one or more coefficients;

determining, by the one or more processors, a probability distribution of each of the one or more coefficients;

determining, by the one or more processors, a first score, for each associated feature, based on at least the probability distribution of each of the one or more coefficients associated with the each associated feature;

determining, by the one or more processors, a second score for a first associated feature based on the first score of the first associated feature in the category and the first score of a second associated feature in another category; and

selecting, by the one or more processors, a predefined number of features, from the associated features, based on at least the second score; and

training, by the one or more processors, one or more classifiers on the selected predefined number of features, wherein the one or more classifiers categorize the user as having one or more requirements, the one or more classifiers predict the one or more user requirements for the one or more resources based on the categorization.

2. The method of claim 1 , wherein the one or more resources correspond to one or more of one or more products and one or more services associated with one or more domains, and wherein the one or more domains include one or more of a health domain, a finance domain, an education domain, and a job domain.

3. The method of claim 1 further comprising pre-processing, by the one or more processors, the one or more messages using one or more natural language processing techniques, wherein the pre-processing comprises at least one of a tokenization, a stemming, or a normalization of the one or more messages.

4. The method of claim 1 further comprising eliminating, by the one or more processors, a noisy data from the one or more messages by utilizing a relevance detection technique.

5. The method of claim 1 , wherein selecting the predefined number of features based on at least the second score comprises:

ranking, by the one or more processors, the one or more associated features corresponding to each of the one or more second message vectors based on at least the second score.

6. The method of claim 5 , wherein the predefined number of features is selected based on the ranking.

7. The method of claim 1 , wherein the one or more classifiers are trained based on one or more machine learning techniques comprising at least one of a Support Vector Machine (SVM), a Logistic Regression, a Bayesian Classifier, a Decision Tree Classifier, or a Copula-based Classifier, a K-Nearest Neighbors (KNN) Classifier, or a Random Forest (RF) Classifier.

8. A system for training one or more classifiers for predicting one or more user requirements for one or more resources over a computer network, the system comprising:

a transceiver configured to transmit and receive data from a computing device of a requestor;

one or more processors configured to:

generate a graphical user interface to be displayed on a computing device of a requestor, the graphical user interface including a plurality of tabs selectable by the requestor;

receive, through the transceiver, one or more inputs provided by the requestor on the graphical user interface, the one or more inputs relating to a request for identifying the one or more user requirements for the one or more resources;

upon receiving an input from the graphical user interface initiating the identification, retrieve, from one or more social medial platform servers, by the one or more processors, one or more audio, video, image, or text messages posted by a user on one or more social media websites;

transform each message of the one or more messages into a first message vector based on at least a comparison with a dictionary;

categorize each of one or more first message vectors into categories based on a predetermined class label associated with respective message;

for each categorized first message vector in a category from the categories:

transform the categorized first message vector into a plurality of second message vectors using a wavelet transform technique, wherein each second message vector of the plurality of second message vectors has associated features, and wherein each of the associated features is represented by one or more coefficients;

determine a probability distribution of each of the one or more coefficients;

determine a first score, for each associated feature, based on at least the probability distribution of each of the one or more coefficients associated with the each associated feature;

determine a second score for a first associated feature based on the first score of the first associated feature in the category and the first score of a second associated feature in another category; and

select a predefined number of features, from the associated features, based on at least the second score; and

train one or more classifiers on the selected predefined number of features, wherein the one or more classifiers categorize the user as having one or more requirements, the one or more classifiers predict the one or more user requirements for the one or more resources based on the categorization.

9. The system of claim 8 , wherein the one or more processors are further configured to pre-process the one or more messages using one or more natural language processing techniques, wherein the pre-processing comprises at least one of a tokenization, a stemming, or a normalization of the one or more messages.

10. The system of claim 8 , wherein the one or more processors are further configured to eliminate a noisy data from the one or more messages by utilizing a relevance detection technique.

11. The system of claim 8 , wherein selecting the predefined number of features based on at least the second score comprises:

ranking the one or more associated features corresponding to each of the one or more second message vectors based on at least the second score.

12. The system of claim 11 , wherein the predefined number of features is selected based on the ranking.

13. The system of claim 8 , wherein the one or more classifiers are trained based on one or more machine learning techniques comprising at least one of a Support Vector Machine (SVM), a Logistic Regression, a Bayesian Classifier, a Decision Tree Classifier, or a Copula-based Classifier, a K-Nearest Neighbors (KNN) Classifier, or a Random Forest (RF) Classifier.

14. A computer program product for use with a computer, the computer program product comprising a non-transitory computer readable medium, wherein the non-transitory computer readable medium stores a computer program code executable by a processor to cause the processor to perform a method for training one or more classifiers for predicting one or more user requirements for one or more resources over a computer network, the method comprising:

generating a graphical user interface to be displayed on a computing device of a requestor, the graphical user interface including a plurality of tabs selectable by the requestor;

receiving one or more inputs provided by the requestor on the graphical user interface, the one or more inputs relating to a request for identifying the one or more user requirements for the one or more resources;

upon receiving an input from the graphical user interface initiating the identification, retrieving, from one or more social medial platform servers, one or more audio, video, image, or text messages posted by a user on one or more social media websites;

transforming each message of the one or more messages into a first message vector based on at least a comparison with a dictionary;

categorizing each of one or more first message vectors into categories based on a predetermined class label associated with respective message;

for each categorized first message vector in a category from the categories:

transforming the categorized first message vector into a plurality of second message vectors using a wavelet transform technique, wherein each second message vector of the plurality of second message vectors has associated features, and wherein each of the associated features is represented by one or more coefficients;

determining a probability distribution of each of the one or more coefficients;

determining a first score, for each associated, feature based on at least the probability distribution of each of the one or more coefficients associated with the each associated feature;

determining a second score for a first associated feature based on the first score of the first associated feature in the category and the first score of a second associated feature in another category; and

selecting a predefined number of features, from the associated features, based on at least the second score; and

training one or more classifiers on the selected predefined number of features, wherein the one or more classifiers categorize the user as having one or more requirements, the one or more classifiers predict the one or more user requirements for the one or more resources based on the categorization.