English

A Systematic Comparison of Architectures for Document-Level Sentiment Classification

Computation and Language 2022-02-03 v2 Machine Learning

Abstract

Documents are composed of smaller pieces - paragraphs, sentences, and tokens - that have complex relationships between one another. Sentiment classification models that take into account the structure inherent in these documents have a theoretical advantage over those that do not. At the same time, transfer learning models based on language model pretraining have shown promise for document classification. However, these two paradigms have not been systematically compared and it is not clear under which circumstances one approach is better than the other. In this work we empirically compare hierarchical models and transfer learning for document-level sentiment classification. We show that non-trivial hierarchical models outperform previous baselines and transfer learning on document-level sentiment classification in five languages.

Keywords

Cite

@article{arxiv.2002.08131,
  title  = {A Systematic Comparison of Architectures for Document-Level Sentiment Classification},
  author = {Jeremy Barnes and Vinit Ravishankar and Lilja Øvrelid and Erik Velldal},
  journal= {arXiv preprint arXiv:2002.08131},
  year   = {2022}
}

Comments

5 pages, 2 figures

R2 v1 2026-06-23T13:46:42.170Z