Systems and methods for generating codes and code books based using cosine proximity
Certain aspects of the disclosure provide a system and method for generating codes associated with clusters of sentiments, comprising receiving a text input, partitioning the text input into one or more segments, generating one or more numerical vectors associated with each of the one or more segments, comparing the one or more numerical vectors to generate a plurality of cosine proximity values associated with the one or more numerical vectors, applying a clustering algorithm to the one or more numerical vectors to generate clusters of segments within one or more cosine proximity ranges, and generating one or more codes associated with each of the clusters of segments within the one or more cosine proximity ranges, wherein each cluster represents an overall sentiment.
1 . A computer-implemented method for generating codes, comprising:
receiving a text input comprising a plurality of customer reviews of consumer products and services;
partitioning the text input into one or more segments, each segment associated with a semantic meaning;
generating one or more numerical vectors associated with each of the one or more segments, wherein each numerical vector represents a relationship between the associated segments and the one or more segments;
comparing the one or more numerical vectors to generate, using a pre-trained machine learning model, a plurality of cosine proximity values associated with the one or more numerical vectors, wherein the machine learning model is pre-trained based on previous customer reviews and review sentiments;
applying a clustering algorithm to the one or more numerical vectors to generate clusters of segments within one or more cosine proximity ranges;
generating, using the pre-trained machine learning model, one or more codes associated with each of the clusters of segments within the one or more cosine proximity ranges, wherein each code is a category related to one or more of the customer reviews;
displaying the one or more codes to a user on a graphical user interface;
determining a confidence level for each of the one or more of the customer reviews of a selected code based on the plurality of cosine proximity values associated with the segments in the one or more of the customer reviews; and
displaying the one or more of the customer reviews associated with the selected code in sorted order according to the confidence levels of the one or more of the customer reviews.
2 . The method of claim 1 , wherein the cosine proximity values indicate a level of semantic proximity between segments.
3 . The method of claim 1 , wherein each of the one or more segments comprises a distinct semantic meaning.
4 . The method of claim 1 , wherein partitioning the text input uses Natural Language Processing.
5 . The method of claim 1 , wherein partitioning the text input uses Artificial Intelligence.
6 . The method of claim 1 , wherein partitioning the text input uses a Large Language Model.
7 . The method of claim 1 , wherein the one or more numerical vectors are generated using a Bidirectional Encoder Representations from Transformers algorithm comprising a machine-learning framework.
8 . The method of claim 1 , wherein the clustering algorithm is based on criteria selected by the user using the graphical user interface.
9 . The method of claim 1 , wherein the user can perform drag and drop operations on the one or more codes using the graphical user interface.
10 . A non-transitory computer-program product for grouping customer comments, comprising:
instructions stored on a memory and executable by a computer processor to cause the computer-program product to:
receive a text input comprising a plurality of customer comments and customer reviews of consumer products and services;
display a graphical user interface comprising the text input;
accept a user command on the graphical user interface that causes the computer- program product to:
partition the text input into one or more segments, each segment associated with a semantic meaning;
generate one or more numerical vectors associated with each of the one or more segments, wherein each numerical vector represents a relationship between the associated segments and the one or more segments;
compare the one or more numerical vectors to generate, using a pre-trained machine learning model, a plurality of cosine proximity values associated with the one or more numerical vectors, wherein the machine learning model is pre-trained based on previous customer reviews and review sentiments;
apply a clustering algorithm to the one or more numerical vectors to generate one or more clusters of segments within one or more cosine proximity ranges, wherein each of the one or more clusters of segments corresponds with a sentiment;
generate, using the pre-trained machine learning model, one or more groups of customer comments associated with each of the clusters of segments within the one or more cosine proximity ranges, wherein each group is a sentiment category related to one or more of the customer comments and customer reviews, and the sentiment category comprises positive, negative, neutral, or a combination thereof;
display the one or more groups of customer comments to a user on the graphical user interface;
determine a confidence level for each of the one or more of customer reviews of a selected group based on the plurality of cosine proximity values associated with the segments in the one or more of customer reviews; and
display the one or more of the customer reviews associated with the selected group in sorted order according to the confidence levels of the one or more reviews.
11 . The non-transitory computer-program product of claim 10 , wherein the graphical user interface comprises a coding section, a display section, and an export section.
12 . The non-transitory computer-program product of claim 11 , wherein the coding section comprises criteria determined by the user using the graphical user interface.
13 . The non-transitory computer-program product of claim 12 , wherein the criteria generates a codebook that forms a basis for implementation of the clustering algorithm.
14 . The non-transitory computer-program product of claim 10 , wherein the user can perform drag and drop operations on the one or more groups of customer comments using the graphical user interface.
15 . A system for categorizing codes based on sentiment, comprising:
a processor;
memory coupled with the processor;
instructions stored in the memory and executable by the processor to cause the system to:
receive a text input comprising a plurality of customer comments and customer reviews of products and services;
partition the text input into one or more segments, each segment associated with a semantic meaning;
generate one or more numerical vectors associated with each of the one or more segments, wherein each numerical vector represents a relationship between the associated segments and the one or more segments;
compare the one or more numerical vectors to generate, using a pre-trained machine learning model, a plurality of cosine proximity values associated with the one or more numerical vectors, wherein the machine learning model is pre-trained based on previous customer reviews and review sentiments;
apply a clustering algorithm to the one or more numerical vectors to generate one or more clusters of segments within one or more cosine proximity ranges, wherein each of the one or more clusters of segments corresponds with a sentiment;
generate, using the pre-trained machine learning model, one or more codes associated with each of the clusters of segments within the one or more cosine proximity ranges, wherein each code is a category related to one or more of the customer comments and customer reviews;
display the one or more codes to a user on a graphical user interface;
determine a confidence level for each of the one or more of the customer comments and customer reviews of a selected code based on the plurality of cosine proximity values associated with the segments in the one or more of the customer comments and customer reviews; and
display the one or more of the customer reviews associated with the selected code in sorted order according to the confidence levels of the one or more of the customer comments and customer reviews.
16 . The system of claim 15 , wherein the cosine proximity values indicate a level of semantic proximity between segments.
17 . The system of claim 15 , wherein partitioning the text input uses Natural Language Processing, Artificial Intelligence, or a Large Language Model.
18 . The system of claim 15 , wherein the one or more numerical vectors are generated using a Bidirectional Encoder Representations from Transformers algorithm comprising a machine-learning framework.
19 . The system of claim 15 , wherein the user can perform drag and drop operations on the one or more codes using the graphical user interface.
20 . The method of claim 1 , wherein the graphic user interface comprises a plurality of filtering checkboxes, each filtering checkbox is associated with a confidence level range, the method further comprises:
determining whether one or more of the filtering checkboxes are selected;
in determining that the one or more of the filtering checkboxes are selected, determining whether a confidence level of at least one customer review associated with the selected code is out of a combining confidence level range of the one or more of the filtering checkboxes; and
in determining that the confidence level of the at least one customer review associated with the selected code is out of a combining confidence level range of the one or more of the filtering checkboxes, excluding the at least one customer review from displaying on the graphic user interface.