Entity classification based on machine learning techniques

A method, comprising:

• receiving, by a device, information associated with a set of positive entities and a set of negative entities,
• the set of positive entities and the set of negative entities being associated with a set of requirements;
• identifying, by the device, a set of priority terms based on the information associated with the set of positive entities and the set of negative entities;
• identifying, by the device, a set of terms of a phrase that occur within a threshold distance of a priority term of the set of priority terms,
• wherein the set of terms is located at the threshold distance by one of:
• preceding a quantity of terms, or
• subsequent to a quantity of terms;
• identifying, by the device, a first set of ancillary terms and a second set of ancillary terms based on the set of terms that occur within the threshold distance of the priority term,
• the first set of ancillary terms being associated with the information that is associated with the set of positive entities, and
• the second set of ancillary terms being associated with the information that is associated with the set of negative entities;
• generating, by the device, a model based on the set of priority terms, the first set of ancillary terms, and the second set of ancillary terms,
• the model being generated based on a machine learning technique,
• the machine learning technique being implemented to perform entity classification;
• determining, by the device, a set of classification scores, for a set of unclassified entities, based on information associated with the set of unclassified entities and the model;
• and
• providing, by the device, information that identifies the set of classification scores to cause an action to be performed in association with the set of unclassified entities.

A non-transitory computer-readable medium storing instructions, the instructions comprising:

• one or more instructions that, when executed by one or more processors, cause the one or more processors to:
• receive information that identifies a requirement;
• receive information associated with a set of positive entities and a set of negative entities,
• the set of positive entities and the set of negative entities being associated with other requirements that are associated with the requirement;
• identify a set of priority terms based on the information associated with the set of positive entities and the set of negative entities;
• identify a set of terms of a phrase that occur within a threshold distance of a priority term of the set of priority terms,
• wherein the set of terms is located at the threshold distance by one of:
• preceding a quantity of terms, or
• subsequent to a quantity of terms;
• identify a first set of ancillary terms and a second set of ancillary terms based on the set of terms that occur within the threshold distance of the priority term,
• the first set of ancillary terms being associated with the information that is associated with the set of positive entities, and
• the second set of ancillary terms being associated with the information that is associated with the set of negative entities;
• generate a model based on the set of priority terms, the first set of ancillary terms, and the second set of ancillary terms,
• the model being generated based on a machine learning technique,
• the machine learning technique being implemented to perform entity classification;
• determine a set of classification scores, for a set of unclassified entities, based on information associated with the set of unclassified entities and the model;
• and
• provide information that identifies the set of classification scores to permit an action to be performed in association with the set of unclassified entities.