Automated topic modelling and visualization based upon service phase

A device for producing a graphical user interface, the device comprising:

• a processor;
• a memory, the memory including instructions, which when executed by the processor, causes the device to perform operations comprising:
• identifying a corpus of documents comprising natural language descriptions of services provided by a network-based service provider, for each particular document, identifying one of a plurality of service phases during which the particular document was collected, the service phase determined based upon a phase of an account data structure of a particular user to which the particular document relates, a service phase being a stage in the particular user's account lifecycle related to the particular user's use of a network-based service, the corpus of documents comprising postings on a social media platform;
• identifying a set of topic clusters corresponding to topics for the corpus using a neural network topic clustering algorithm, each topic cluster in the set of topic clusters comprising words from the corpus of documents that cluster together as a result of the neural network topic clustering algorithm;
• automatically assigning a topic label to each particular topic cluster in the set of topic clusters based upon a similarity measure between words in the particular topic cluster and predefined topics in a taxonomy;
• calculating a number of documents in each particular topic cluster in the set of topic clusters that are identified as having come from each phase of the plurality of service phases, to produce service phase data;
• receiving input defining rules from a rules engine specifying conversion of the service phase data to a visualization;
• generating a visualization data structure based upon the rules from the rules engine and the service phase data, the generating comprising:
• applying one or more rules from the rules engine to convert the service phase data into the visualization data structure, the one or more rules comprising one or more templates for visualization;
• incorporating visualization settings from a visualization configuration into the visualization data structure, the visualization configuration being set by a client computing device;
• producing the visualization data structure in a format for display by the client computing device;
• and
• transmitting the visualization data structure to a second computing device, the second computing device displaying a visualization corresponding to the visualization data structure, the visualization displaying the service phase data as part of a graphical user interface.

A non-transitory machine-readable medium, storing instructions, which when executed by a machine, causes the machine to perform operations comprising:

• identifying a corpus of documents comprising natural language descriptions of services provided by a network-based service provider, for each particular document, identifying one of a plurality of service phases during which the particular document was collected, the service phase determined based upon a phase of an account data structure of a particular user to which the particular document relates, a service phase being a stage in the particular user's account lifecycle related to the particular user's use of a network-based service, the corpus of documents comprising postings on a social media platform;
• identifying a set of topic clusters corresponding to topics for the corpus using a neural network topic clustering algorithm, each topic cluster in the set of topic clusters comprising words from the corpus of documents that cluster together as a result of the topic clustering algorithm;
• automatically assigning a topic label to each particular topic cluster in the set of topic clusters based upon a similarity measure between words in the particular topic cluster and predefined topics in a taxonomy;
• calculating a number of documents in each particular topic cluster in the set of topic clusters that are identified as having come from each phase of the plurality of service phases, to produce service phase data;
• receiving input defining rules from a rules engine specifying conversion of the service phase data to a visualization;
• generating a visualization data structure based upon the rules from the rules engine and the service phase data, the generating comprising:
• applying one or more rules from the rules engine to convert the service phase data into the visualization data structure, the one or more rules comprising one or more templates for visualization;
• incorporating visualization settings from a visualization configuration into the visualization data structure, the visualization configuration being set by a client computing device;
• producing the visualization data structure in a format for display by the client computing device;
• and
• transmitting the visualization data structure to a second computing device, the second computing device displaying a visualization corresponding to the visualization data structure, the visualization displaying the service phase data as part of a graphical user interface.