Topic Modeling for Support Ticket using Latent Dirichlet Allocation
Dublin Core
Title
Topic Modeling for Support Ticket using Latent Dirichlet Allocation
Subject
Topic Modeling, Support Ticket, Latent Dirichlet Allocation.
Description
In the business world, communication over customers must be built properly to make it easier for companies to find out what
customers want. Support ticket is one of the business instrument for communication between the customers and the companies.
Through a support ticket, customers can respond, complain or ask questions about products with a support team. Increasing
the business process of the companies will be increasing the support ticket volume that should be handled by support team. It
also has a value for analysis to get business intelligence decision. With that chance, an efficient data processing method is
needed to find topics are being discussed by customers. One way that can be used to solve this problem is Topic Modeling.
This research uses several parameters the number of topics, alpha value, beta value, iteration, and random seed. With this
combination of parameters, the best results based on evaluation of human judgement and topic coherence with 5 topics, an
alpha value of 50, a beta value of 0.01, 100 iterations, and 50 random seeds. The five topics interpretation consists of hosting
migration, error problems in wordpress, domain email settings and domain transfer, ticketing and transaction processing. The
total of 5 topics has a coherence value of 0.507897
customers want. Support ticket is one of the business instrument for communication between the customers and the companies.
Through a support ticket, customers can respond, complain or ask questions about products with a support team. Increasing
the business process of the companies will be increasing the support ticket volume that should be handled by support team. It
also has a value for analysis to get business intelligence decision. With that chance, an efficient data processing method is
needed to find topics are being discussed by customers. One way that can be used to solve this problem is Topic Modeling.
This research uses several parameters the number of topics, alpha value, beta value, iteration, and random seed. With this
combination of parameters, the best results based on evaluation of human judgement and topic coherence with 5 topics, an
alpha value of 50, a beta value of 0.01, 100 iterations, and 50 random seeds. The five topics interpretation consists of hosting
migration, error problems in wordpress, domain email settings and domain transfer, ticketing and transaction processing. The
total of 5 topics has a coherence value of 0.507897
Creator
Wiranto1
, Mila Rosyida Uswatunnisa2
, Mila Rosyida Uswatunnisa2
Publisher
Sebelas Maret University
Date
29-12-2022
Contributor
Fajar bagus W
Format
PDF
Language
Indonesia
Type
Text
Files
Collection
Citation
Wiranto1
, Mila Rosyida Uswatunnisa2, “Topic Modeling for Support Ticket using Latent Dirichlet Allocation,” Repository Horizon University Indonesia, accessed June 7, 2025, https://repository.horizon.ac.id/items/show/9319.