Methods and systems for generating textual features

1 . A method for generating textual features corresponding to at least one text document, the method being performed by at least one processor communicably coupled to a memory and comprising:

preprocessing the at least one text document among a plurality of text documents in a raw dataset;

determining a topic probability score (TPS) corresponding to the at least one preprocessed text document, via an unsupervised machine learning (ML) model, wherein the TPS indicates a probability of each of the at least one preprocessed text document among the plurality of text documents, being associated with at least one cluster generated by the unsupervised ML model;

determining a confidence score (CS) corresponding to the at least one preprocessed text document, via a supervised ML model, wherein the CS indicates a reliability level associated with a classification of each of the at least one preprocessed text document among the plurality of text documents, predicted by the supervised ML model;

determining a compound distribution score (CDS) corresponding to each of the at least one preprocessed text document among the plurality of text documents in the raw dataset based on the TPS and the CS, wherein the CDS indicates a weighted average of the TPS and the CS to generate a comprehensive representation for output of the unsupervised ML model and the supervised ML model respectively;

generating a set of textual features corresponding to the at least one preprocessed text document among the plurality of text documents based on inputting the determined TPS, the CS, and the CDS respectively, into a multiclass classification machine learning model, wherein the set of textual features indicates independent variables for a forecasting model, and comprises time series data;

receiving a set of numerical features corresponding to the raw dataset;

inputting the set of textual features and the set of numerical features into the forecasting model; and

outputting, to a display and via the forecasting model, a final forecast based on the set of textual features and the set of numerical features, wherein the final forecast indicates predicting a target variable using the forecasting model.

2 . The method as claimed in claim 1 , wherein prior to determining the TPS and the CS, the method comprises:

determining at least one vector based on the at least one preprocessed text document;

inputting the at least one vector into the unsupervised ML model and the supervised ML model; and

determining the TPS and the CS via the unsupervised ML model and the supervised ML model respectively, based on the at least one vector.

3 . The method as claimed in claim 2 , wherein the at least one vector is determined using one of a counter vectorization technique, a term Frequency-Inverse Document Frequency (TF-IDF) technique, a word2vec technique, and a GloVe technique.

4 . The method as claimed in claim 1 , further comprising:

performing a feature importance analysis based on the set of textual features, wherein the feature importance analysis indicates assigning a score to the set of textual features, to indicate usefulness for predicting the target variable;

correlating the at least one preprocessed text document and the feature importance analysis; and

generating explainability corresponding to the at least one preprocessed text document based on the correlation.

5 . The method as claimed in claim 1 , wherein determining the CDS comprises:

determining a maximum value of the confidence score;

correlating the maximum value of the confidence score and the TPS corresponding to the at least one cluster associated with the at least one preprocessed text document; and

determining the CDS for the at least one document based on the correlation.

6 . The method as claimed in claim 1 , wherein the unsupervised machine learning model is a topic model for determining at least one topic present in the at least one preprocessed document, and wherein the unsupervised machine learning model includes one of a Bidirectional Encoder Representations from Transformers (BERT) topic model, a Correlation Explanation (CorEx) model, a Latent Dirichlet Allocation (LDA) model, a Non-Negative Matrix Factorization (NMF) model, a guided LDA model, and a Gensim mode with natural language processing to understand a context and label the at least one document among the plurality of text documents.

7 . The method as claimed in claim 1 , wherein the supervised machine learning model is one of a sentiment analysis model, a Named Entity Recognition model, an N-Gram model, and a Part-of-speech (POS) labelling Model.

8 . The method as claimed in claim 1 , wherein the at least one text document is preprocessed using one of a stemming and a lemmatization with natural language processing.

9 . A system for generating textual features corresponding to at least one text document, the system comprising:

a memory;

a display; and

at least one processor communicably coupled to the memory, the at least one processor is configured to:

preprocess the at least one text document among a plurality of text documents in a raw dataset;

determine a topic probability score (TPS) corresponding to the at least one preprocessed text document, via an unsupervised machine learning (ML) model, wherein the TPS indicates probability of each of the at least one preprocessed text document among the plurality of text documents, being associated with at least one cluster generated by the unsupervised ML model;

determine a confidence score (CS) corresponding to the at least one preprocessed text document, via a supervised ML model, wherein the CS indicates a reliability level associated with classification of each of the at least one preprocessed text document among the plurality of text documents, predicted by the supervised ML model;

determine a compound distribution score (CDS) corresponding to each of the at least one preprocessed text document among the plurality of text documents in the dataset based on the determined TPS and the determined CS, wherein the CDS indicates a weighted average of the TPS and the CS to generate a comprehensive representation for output of the unsupervised ML model and the supervised ML model respectively;

generate a set of textual features corresponding to the at least one preprocessed text document among the plurality of text documents based on inputting the determined TPS, the CS, and the CDS into a multiclass classification machine learning model, wherein the set of textual features indicates independent variables for a forecasting model, and comprises time series data;

receive a set of numerical features corresponding to the raw dataset;

input the set of textual features and the set of numerical features into the forecasting model; and

output, to the display and via the forecasting model, a final forecast based on the set of textual features and the set of numerical features, wherein the final forecast indicates predicting a target variable using the forecasting model.

10 . The system as claimed in claim 9 , wherein prior to determining the TPS and the CS, the at least one processor is configured to:

determine at least one vector based on the at least one preprocessed text document;

input the at least one vector into the unsupervised ML model and the supervised ML model; and

determine the TPS and the CS via the unsupervised ML model and the supervised ML model respectively, based on the at least one vector.

11 . The system as claimed in claim 9 , wherein the at least one processor is further configured to:

perform a feature importance analysis based on the set of textual features, wherein the feature importance analysis indicates assigning a score to set of textual features, to indicate usefulness for predicting the target variable;

correlate the at least one preprocessed text document and the feature importance analysis; and

generate explainability corresponding to the at least one preprocessed text document based on the correlation.

12 . The system as claimed in claim 9 , wherein to determine the CDS the at least one processor is configured to:

determine a maximum value of the confidence score;

correlate the maximum value of the confidence score and the TPS corresponding to the at least one cluster associated with the at least one preprocessed text document; and

determine the CDS for the at least one document based on the correlation.

13 . The system as claimed in claim 9 , wherein the unsupervised machine learning model is a topic model for determining at least one topic present in the at least one preprocessed document, and wherein the unsupervised machine learning model includes one of a Bidirectional Encoder Representations from Transformers (BERT) topic model, a Correlation Explanation (CorEx) model, a Latent Dirichlet Allocation (LDA) model, a Non-Negative Matrix Factorization (NMF) model, a guided LDA model, and a Gensim mode with natural language processing to understand a context and label the at least one document among the plurality of text documents.

14 . The system as claimed in claim 9 , wherein the supervised machine learning model is one of a sentiment analysis model, a Named Entity Recognition model, an N-Gram model, and a Part-of-speech (POS) labelling Model.

15 . The system as claimed in claim 9 , wherein the at least one text document is preprocessed using one of a stemming and a lemmatization with natural language processing.

16 . The system as claimed in claim 9 , wherein the at least one vector is determined using one of a counter vectorization technique and a term Frequency-Inverse Document Frequency (TF-IDF) technique.