Mining Salient Concepts of IT-Support-Tasks from Daily IT-Support Ticket Reports
Keywords:
word cooccurrence, help-desk ticket, salient conceptAbstract
IT help-desk staff at a university computer center create tickets and record end-user request calls as request documents containing explanations of IT-Support-Task (IST) concepts. The ticket’s request document contains several elementary discourse units (EDUs, which are simple sentences) including a salient IST-concept EDU. The research focuses on mining, including the extraction of EDUs with salient IST-concepts from consecutive daily IT-support ticket reports to classify the salient IST-concepts EDUs (IT, Network, Mix and Miscellaneous). Classification results are used to represent daily task loads graphically, which helps with planning and decision-making for resource reallocation. There are three main research gaps: how to determine the IST-concept EDUs with noun phrase ellipses in the documents, where the noun phrase ellipses of the EDUs may result in loss of contextual information; how to determine/extract the salient IST-concept EDU as the main content of the request, and how to classify the tickets’ salient IST-concept EDUs with ambiguous task concepts. We then propose using a word-Verb cooccurrence (wrdVCo) set with IST concepts to determine the IST-concept EDUs (where wrdVCo can be used as primary keywords to analyze the meaning, main idea, and context of an EDU). We also applied a salient-concept occurrence rule to extract the salient IST-concept EDU from the document. Machine learning techniques, SVM and MLP, are then applied to classify the tickets’ salient IST-concept EDUs. The research results show high F1-scores of the salient IST-concept EDU extraction and classification from the tickets.
References
Al-Hawari, F., & Barham, H. (2021). A machine learning based help desk system for IT service management. Journal of King Saud University-Computer and Information Sciences, 33(6), 702-718. https://doi.org/10.1016/j.jksuci.2019.04.001
Aun-a-nan, A., & Meesad, P. (2020). The classification of credibility of Thai news source websites using data mining techniques [In Thai]. EAU Heritage Journal Science and Technology (online), 14(2), 101–116. https://he01.tci-thaijo.org/index.php/EAUHJSci/article/view/241729
Bouckaert, R. R., Frank, E., Hall, M., Kirkby, R., Reutemann, P., Seewald, A., & Scuse, D. (2016). WEKA manual for version 3-9-1. University of Waikato.
Carlson, L., Marcu, D., & Okurowski, M. E. (2003). Building a discourse-tagged corpus in the framework of rhetorical structure theory. In J. van Kuppevelt & R. W. Smith (Eds.), Current directions in discourse and dialogue (pp. 85–112). Springer.
Chanlekha, H., & Kawtrakul, A. (2004). Thai named entity extraction by incorporating maximum entropy model with simple heuristic information. In K. Su, J. Tsujii, J. Lee & O. Y. Kwong (Eds.), Proceedings of the First International Joint Conference on Natural Language Processing (pp. 1–7). Springer-Verlag.
Chareonsuk, J., Sukvakree, T., & Kawtrakul, A. (2005). Elementary discourse unit segmentation for Thai using discourse cue and syntactic information [In Thai]. In International Annual Symposium on Computational Science and Engineering (Ed.), The 9th Annual National Symposium on Computational Science and Engineering (ANSCSE 9) (pp. 85–90). ANSCSE.
Cristianini, N., & Shawe-Taylor, J. (2000). An introduction to support vector machines. Cambridge University Press.
Diwanji, P., Guo, H., Singh, M. P., & Kalia, A. (2020). Lin: Unsupervised extraction of tasks from textual communication. In D. Scott, N. Nuria & C. Zong (Eds.), Proceedings of the 28th International Conference on Computational Linguistics (pp. 1815-1819). International Committee on Computational Linguistics
Guthriee, J. A., Guthrie, L., Aidinejad, H., & Wilks, Y. (1991). Subject-dependent co-occurrence and word sense disambiguation. In D. E. Appelt (Ed.), 29th Annual Meeting of The Association for Computational Linguistics (pp. 146-152). The Association for Computational Linguistics.
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., & Witten, I. H. (2009). The WEKA data mining software: An update. ACM SIGKDD Explorations Newsletter, 11(1), 10-18. https://doi.org/10.1145/1656274.1656278
Hassan, S., & Mihalcea, R. (2011). Semantic relatedness using salient semantic analysis. Proceedings of the AAAI Conference on Artificial Intelligence, 25(1), 884–889. https://doi.org/10.1609/aaai.v25i1.7971
Haykin, S. (1999). Neural networks: A comprehensive foundation. Prentice Hall.
Hee, Y. E. (2018). A comparative study of subject ellipsis in Chinese and Korean sentence. International Journal of Humanities and Social Science Invention (IJHSSI), 7(4), 11-21. https://www.ijhssi.org/papers/vol7(4)/Version-1/A0704010110.pdf
Huang, Y., Yu, L., & Lin, I. C. (2013). Text categorization for service request classification. International Journal of Signal Processing Systems, 1(1), 54-58. https://doi.org/10.12720/ijsps.1.1.54-58
Ketui, N., Theeramunkong, T., & Onsuwan, C. (2013). Thai elementary discourse unit analysis and syntactic-based segmentation. International Information Institute (Tokyo) Information, 16(10), 7423-7436. https://bit.ly/4wlKBfN
Lin, C. C., Kang, D., Gamon, M., & Pantel, P. (2018). Actionable email intent modeling with reparametrized RNNs. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1), 4856-4864. https://doi.org/10.1609/aaai.v32i1.11931
Miller, G. A. (1995). WordNet: A lexical database. Communications of the ACM, 38(11), 39-41. https://doi.org/10.1145/219717.219748
Pakamwang, J., Khoomsab, K., & Timsorn, K. (2020). Investigation of factors for student’s decision in studying at Phetchabun Rajabhat University by data mining technique [In Thai]. EAU Heritage Journal Science and Technology (online), 14(1), 24–33. https://he01.tci-thaijo.org/index.php/EAUHJSci/article/view/240508
Paramesh, S. P., Ramya, C., & Shreedhara, K. S. (2018). Classifying the unstructured IT service desk tickets using ensemble of classifiers. In M. N. Vijayalakshmi (Ed.), The 3rd International Conference on Computational Systems and Information Technology for Sustainable Solutions (CSITSS 2018) (pp. 221-227). IEEE.
Pawar, S., Palshikar, G., & Banerjee, A. S. (2021). Weakly supervised extraction of tasks from text. In S. Bandyopadhyay, S. L. Devi & P. Bhattacharyya (Eds.), Proceedings of the 18th International Conference on Natural Language Processing (ICON) (pp. 583-592). NLP Association of India (NLPAI).
Pechsiri, C., & Piriyakul, R. (2016). Extraction of a group-pair relation: Problem-solving relation from web-board documents. SpringerPlus, 5, 1265. https://doi.org/10.1186/s40064-016-2864-3
Pechsiri, C., Piriyakul, I., & Pechsiri, J. S. (2025). Grouped semantic-feature relation extraction from texts to represent medicinal-plant property knowledge on social media. Frontiers in Artificial Intelligence, 8, 1579357. https://doi.org/10.3389/frai.2025.1579357
Sudprasert, S., & Kawtrakul, A. (2003). Thai word segmentation based on global and local unsupervised learning [In Thai]. In National Computer Science and Engineering Department (Ed.), The 7th National Computer Science and Engineering Conference (pp. 1–8). National Computer Science and Engineering Department.
Sutta, S., Jivnot, T., & Settawatcharawanit, T. (2025). Development of an inventory management system on a mobile application using machine learning technology [In Thai]. EAU Heritage Journal Science and Technology (online), 19(3), 76–90. https://he01.tci-thaijo.org/index.php/EAUHJSci/article/view/277291
Thimsanthia, R., & Soemphol, C. (2025). Design and development of a video-based work time analysis system for industrial production lines [In Thai]. EAU Heritage Journal Science and Technology (online), 19(3), 212–226. https://he01.tci-thaijo.org/index.php/EAUHJSci/article/view/279822
Tongtep, N., & Theeramunkong, T. (2015). Pattern-based extraction of named entities in Thai news documents. Science & Technology Asia, 15(1), 70–81. https://ph02.tci-thaijo.org/index.php/SciTechAsia/article/view/41311
Whiteley, E. K. (2024). Order-based salience patterns in language: What they are and why they matter. Ergo: An Open Access Journal of Philosophy, 11(26), 689–715. https://doi.org/10.3998/ergo.6166
