Leveraging Automated Machine Learning for Text Classification: Evaluation of AutoML Tools and Comparison with Human Performance
This research addresses the applicability of AutoML to text classification, a domain where its effectiveness is less established, for machine learning practitioners and researchers.
This paper evaluates four AutoML tools on 13 text classification datasets, comparing their performance against human-designed models. The study found that AutoML tools outperformed human performance in 4 out of 13 tasks, with two specific tools demonstrating superior results.
Recently, Automated Machine Learning (AutoML) has registered increasing success with respect to tabular data. However, the question arises whether AutoML can also be applied effectively to text classification tasks. This work compares four AutoML tools on 13 different popular datasets, including Kaggle competitions, and opposes human performance. The results show that the AutoML tools perform better than the machine learning community in 4 out of 13 tasks and that two stand out.