Desirability of product attributes
A method, computer system, and computer program product for determining a desirability of a product attribute are provided. The embodiment may include extracting a plurality of product features corresponding to one or more products. The embodiment may also include analyzing a plurality of product reviews to determine a sentiment toward the extracted product features. The embodiment may further include calculating a desirability score for each product feature. The embodiment may also include, in response to receiving a user query associated with a product, identifying a product feature to which the received user query relates. The embodiment may further include generating a response to the received user query based on the calculated desirability score.
1. A processor-implemented method comprising:
in response to receiving a user query in a conversational system related to an item, extracting, by a processor, a plurality of features and a plurality of attributes corresponding to the item;
generating a machine learning model of user preferences associated with the plurality of features and the plurality of attributes based on one or more historical user queries with the conversational system;
analyzing a plurality of reviews of the item from a plurality of databases using conjoint analysis to determine a sentiment toward the extracted features and attributes, wherein the plurality of reviews are separated into cohorts based on intended use by a review writer;
calculating a desirability score for each feature and each attribute within a cohort, wherein each feature and each attribute is assigned a tag based on the desirability score satisfying one or more thresholds related to a level of necessity that a specific feature or attribute be included in the item, and wherein the desirability score is calculated as a comparison between a total number of positive reviews of a feature or attribute and a total number of negative reviews of the feature or attribute;
generating a data analytics model that determines in which cohort the user corresponds and orders each feature and each attribute within the cohort based on each calculated desirability score satisfying a threshold value;
generating a response to the user query based on the generated data analytics model; and
predicting a user approval of the generated response based on the generated machine learning model.
2. The method of claim 1 , wherein a cohort of reviews is extracted from a variety of sources and categorized by reviewer to create one or more cohorts of users specific to a given category, and wherein the variety of sources comprise social media sites, online retailers, online review sites, or data analytics repositories.
3. The method of claim 1 , wherein the plurality of extracted features comprises attribute information, and wherein the attribute information is selected from a group consisting of a model number, a product number, and a plurality of performance specifications.
4. A computer system comprising:
one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage media, and program instructions stored on at least one of the one or more tangible storage media for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:
in response to receiving a user query in a conversational system related to an item, extracting a plurality of features and a plurality of attributes corresponding to the item;
generating a machine learning model of user preferences associated with the plurality of features and the plurality of attributes based on one or more historical user queries with the conversational system;
analyzing a plurality of reviews of the item from a plurality of databases using conjoint analysis to determine a sentiment toward the extracted features and attributes, wherein the plurality of reviews are separated into cohorts based on intended use by a review writer;
calculating a desirability score for each feature and each attribute within a cohort, wherein each feature and each attribute is assigned a tag based on the desirability score satisfying one or more thresholds related to a level of necessity that a specific feature or attribute be included in the item, and wherein the desirability score is calculated as a comparison between a total number of positive reviews of a feature or attribute and a total number of negative reviews of the feature or attribute;
generating a data analytics model that determines in which cohort the user corresponds and orders each feature and each attribute within the cohort based on each calculated desirability score satisfying a threshold value;
generating a response to the user query based on the generated data analytics model; and
predicting a user approval of the generated response based on the generated machine learning model.
5. The computer system of claim 4 , wherein a cohort of reviews is extracted from a variety of sources and categorized by reviewer to create one or more cohorts of users specific to a given category, and wherein the variety of sources comprise social media sites, online retailers, online review sites, or data analytics repositories.
6. The computer system of claim 4 , wherein the plurality of extracted features comprises attribute information, and wherein the attribute information is selected from a group consisting of a model number, a product number, and a plurality of performance specifications.
7. A computer program product comprising:
one or more computer-readable tangible storage media and program instructions stored on at least one of the one or more tangible storage media, the program instructions executable by a processor of a computer to perform a method, the method comprising:
in response to receiving a user query in a conversational system related to an item, extracting a plurality of features and a plurality of attributes corresponding to the item;
generating a machine learning model of user preferences associated with the plurality of features and the plurality of attributes based on one or more historical user queries with the conversational system;
analyzing a plurality of reviews of the item from a plurality of databases using conjoint analysis to determine a sentiment toward the extracted features and attributes, wherein the plurality of reviews are separated into cohorts based on intended use by a review writer;
calculating a desirability score for each feature and each attribute within a cohort, wherein each feature and each attribute is assigned a tag based on the desirability score satisfying one or more thresholds related to a level of necessity that a specific feature or attribute be included in the item, and wherein the desirability score is calculated as a comparison between a total number of positive reviews of a feature or attribute and a total number of negative reviews of the feature or attribute;
generating a data analytics model that determines in which cohort the user corresponds and orders each feature and each attribute within the cohort based on each calculated desirability score satisfying a threshold value;
generating a response to the user query based on the generated data analytics model; and
predicting a user approval of the generated response based on the generated machine learning model.
8. The computer program product of claim 7 , wherein a cohort of reviews is extracted from a variety of sources and categorized by reviewer to create one or more cohorts of users specific to a given category, and wherein the variety of sources comprise social media sites, online retailers, online review sites, or data analytics repositories.
9. The computer program product of claim 7 , wherein the plurality of extracted features comprises attribute information, and wherein the attribute information is selected from a group consisting of a model number, a product number, and a plurality of performance specifications.