# From Sentiment Annotations to Sentiment Prediction through Discourse Augmentation

arXiv: https://arxiv.org/abs/2011.03021 · HTML: https://mlsanity.com/paper/2011.03021/

## Key facts

- Cited by 5 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 5 Nov 2020.

## Built on by (most cited first, 5 of 5)

- [GCDT: A Chinese RST Treebank for Multigenre and Multilingual Discourse Parsing](https://mlsanity.com/paper/2210.10449/) (2022)
- [Predicting Above-Sentence Discourse Structure using Distant Supervision from Topic Segmentation](https://mlsanity.com/paper/2112.06196/) (2021)
- [HieNet: Bidirectional Hierarchy Framework for Automated ICD Coding](https://mlsanity.com/paper/2212.04891/) (2022)
- [W-RST: Towards a Weighted RST-style Discourse Framework](https://mlsanity.com/paper/2106.02658/) (2021)
- [Aspect-based Sentiment Analysis through EDU-level Attentions](https://mlsanity.com/paper/2202.02535/) (2022)

## Abstract (arXiv)

Sentiment analysis, especially for long documents, plausibly requires methods capturing complex linguistics structures. To accommodate this, we propose a novel framework to exploit task-related discourse for the task of sentiment analysis. More specifically, we are combining the large-scale, sentiment-dependent MEGA-DT treebank with a novel neural architecture for sentiment prediction, based on a hybrid TreeLSTM hierarchical attention model. Experiments show that our framework using sentiment-related discourse augmentations for sentiment prediction enhances the overall performance for long documents, even beyond previous approaches using well-established discourse parsers trained on human annotated data. We show that a simple ensemble approach can further enhance performance by selectively using discourse, depending on the document length.