Question classification framework for helpdesk ticketing support system using machine learning
One of the elements that contribute to the nonuniformity of the question data in Helpdesk Ticketing Support (HTS) System is the diversity of services and users. Most questions that were asked in the HTS are in various forms and sentence styles but usually offer the same meaning. Various state-of-the...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Published: |
2021
|
| Subjects: |
| _version_ | 1796866265679134720 |
|---|---|
| author | Harun, Noor Aklima Huspi, Sharin Hazlin A. Iahad, Noorminshah |
| author_facet | Harun, Noor Aklima Huspi, Sharin Hazlin A. Iahad, Noorminshah |
| author_sort | Harun, Noor Aklima |
| collection | ePrints |
| description | One of the elements that contribute to the nonuniformity of the question data in Helpdesk Ticketing Support (HTS) System is the diversity of services and users. Most questions that were asked in the HTS are in various forms and sentence styles but usually offer the same meaning. Various state-of-the-art machine-learning approaches have recently been used to automate the question classification process. Question classification, according to the researchers, is important to solve problems like helpdesk tickets being forwarded to the wrong resolver group and causing the ticket transfer process to take effect, and to associate a help desk ticket with its correct service from the start, reducing ticket resolution time, saving human resources, and improving user satisfaction. The key findings in the exploration results revealed that in HTS, tickets with a high number of transfer transactions take longer to complete than tickets with no transfer transaction. Thus, this research aims to develop an automated question classification model for the HTS and proposes to apply the supervised machine learning methods: Naïve Bayes (NB) and Support Vector Machine (SVM). The domain will use a readily available dataset from IT Unit. It is expected that this study will have a significant impact on the productivity of technical and system owners in dealing with the increasing number of comments, feedbacks, and complaints presented by end-users. This paper will present related works and research frameworks for automated question classification for HTS. |
| first_indexed | 2024-03-05T21:09:33Z |
| format | Conference or Workshop Item |
| id | utm.eprints-96648 |
| institution | Universiti Teknologi Malaysia - ePrints |
| last_indexed | 2024-03-05T21:09:33Z |
| publishDate | 2021 |
| record_format | dspace |
| spelling | utm.eprints-966482022-08-15T07:52:02Z http://eprints.utm.my/96648/ Question classification framework for helpdesk ticketing support system using machine learning Harun, Noor Aklima Huspi, Sharin Hazlin A. Iahad, Noorminshah QA75 Electronic computers. Computer science One of the elements that contribute to the nonuniformity of the question data in Helpdesk Ticketing Support (HTS) System is the diversity of services and users. Most questions that were asked in the HTS are in various forms and sentence styles but usually offer the same meaning. Various state-of-the-art machine-learning approaches have recently been used to automate the question classification process. Question classification, according to the researchers, is important to solve problems like helpdesk tickets being forwarded to the wrong resolver group and causing the ticket transfer process to take effect, and to associate a help desk ticket with its correct service from the start, reducing ticket resolution time, saving human resources, and improving user satisfaction. The key findings in the exploration results revealed that in HTS, tickets with a high number of transfer transactions take longer to complete than tickets with no transfer transaction. Thus, this research aims to develop an automated question classification model for the HTS and proposes to apply the supervised machine learning methods: Naïve Bayes (NB) and Support Vector Machine (SVM). The domain will use a readily available dataset from IT Unit. It is expected that this study will have a significant impact on the productivity of technical and system owners in dealing with the increasing number of comments, feedbacks, and complaints presented by end-users. This paper will present related works and research frameworks for automated question classification for HTS. 2021 Conference or Workshop Item PeerReviewed Harun, Noor Aklima and Huspi, Sharin Hazlin and A. Iahad, Noorminshah (2021) Question classification framework for helpdesk ticketing support system using machine learning. In: 7th International Conference on Research and Innovation in Information Systems, ICRIIS 2021, 25 - 26 October 2021, Johor Bahru, Malaysia. http://dx.doi.org/10.1109/ICRIIS53035.2021.9617077 |
| spellingShingle | QA75 Electronic computers. Computer science Harun, Noor Aklima Huspi, Sharin Hazlin A. Iahad, Noorminshah Question classification framework for helpdesk ticketing support system using machine learning |
| title | Question classification framework for helpdesk ticketing support system using machine learning |
| title_full | Question classification framework for helpdesk ticketing support system using machine learning |
| title_fullStr | Question classification framework for helpdesk ticketing support system using machine learning |
| title_full_unstemmed | Question classification framework for helpdesk ticketing support system using machine learning |
| title_short | Question classification framework for helpdesk ticketing support system using machine learning |
| title_sort | question classification framework for helpdesk ticketing support system using machine learning |
| topic | QA75 Electronic computers. Computer science |
| work_keys_str_mv | AT harunnooraklima questionclassificationframeworkforhelpdeskticketingsupportsystemusingmachinelearning AT huspisharinhazlin questionclassificationframeworkforhelpdeskticketingsupportsystemusingmachinelearning AT aiahadnoorminshah questionclassificationframeworkforhelpdeskticketingsupportsystemusingmachinelearning |