# Structural Attention Neural Networks for improved sentiment analysis

arXiv: https://arxiv.org/abs/1701.01811 · HTML: https://mlsanity.com/paper/1701.01811/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jan 2017.

## Built on by (most cited first, 6 of 6)

- [Mapping the Internet: Modelling Entity Interactions in Complex Heterogeneous Networks](https://mlsanity.com/paper/2104.09650/) (2021)
- [Large-Scale News Classification using BERT Language Model: Spark NLP Approach](https://mlsanity.com/paper/2107.06785/) (2021)
- [xASTNN: Improved Code Representations for Industrial Practice](https://mlsanity.com/paper/2303.07104/) (2023)
- [A Novel Deep Learning Method for Textual Sentiment Analysis](https://mlsanity.com/paper/2102.11651/) (2021)
- [Measuring Linguistic Diversity During COVID-19](https://mlsanity.com/paper/2104.01290/) (2021)
- [Syntax-Aware Complex-Valued Neural Machine Translation](https://mlsanity.com/paper/2307.08586/) (2023)

## Abstract (arXiv)

We introduce a tree-structured attention neural network for sentences and small phrases and apply it to the problem of sentiment classification. Our model expands the current recursive models by incorporating structural information around a node of a syntactic tree using both bottom-up and top-down information propagation. Also, the model utilizes structural attention to identify the most salient representations during the construction of the syntactic tree. To our knowledge, the proposed models achieve state of the art performance on the Stanford Sentiment Treebank dataset.