Imbalanced Multi-label Classification for Business-related Text with Moderately Large Label Spaces
This provides a useful tool for businesses analyzing complex texts, but it is incremental as it compares existing methods without introducing new ones.
The study tackled multi-label text classification on an imbalanced business dataset, finding that fine-tuned BERT significantly outperformed Binary Relevance, Classifier Chains, and Label Powerset with high accuracy, F1 score, precision, and recall.
In this study, we compared the performance of four different methods for multi label text classification using a specific imbalanced business dataset. The four methods we evaluated were fine tuned BERT, Binary Relevance, Classifier Chains, and Label Powerset. The results show that fine tuned BERT outperforms the other three methods by a significant margin, achieving high values of accuracy, F1 Score, Precision, and Recall. Binary Relevance also performs well on this dataset, while Classifier Chains and Label Powerset demonstrate relatively poor performance. These findings highlight the effectiveness of fine tuned BERT for multi label text classification tasks, and suggest that it may be a useful tool for businesses seeking to analyze complex and multifaceted texts.