Multi-Label Classification for Low-Resource Issue Tickets with BERT

This study focuses on the problem in the field of issue ticketing systems, where the need for human involvement in classifying work task in the ticket often results in insufficient classification. Our primary focus is on a problem associated with multi-label classification. A significant challenge in this study is the dependency of our dataset on low resources, which is different from the large datasets usually used in current multi-label text classification studies. Therefore, we propose a pre-training approach for our low-resource dataset. Our methodology applies several embedding techniques, including TF-IDF, Word2Vec, and BERT (WangchanBERTa and PhayaThaiBERT). The classification models, such as Logistic Regression, Support Vector Classifiers, Decision Trees, Neural Networks, and Deep Neural Networks, are experimented in this study to assess their performance in a low-resource environment. According to our experimental results, a combination of PhayaThaiBERT and Deep Neural Networks outperforms conventional methods. The combination yielded an F1 score of 0.769 on the test dataset.