# Text Classification using Capsules

arXiv: https://arxiv.org/abs/1808.03976 · HTML: https://mlsanity.com/paper/1808.03976/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Aug 2018.

## Built on by (most cited first, 10 of 10)

- [Learning with Capsules: A Survey](https://mlsanity.com/paper/2206.02664/) (2022)
- [Hater-O-Genius Aggression Classification using Capsule Networks](https://mlsanity.com/paper/2105.11219/) (2021)
- [XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networks](https://mlsanity.com/paper/2111.10854/) (2021)
- [Adversarial Capsule Networks for Romanian Satire Detection and Sentiment Analysis](https://mlsanity.com/paper/2306.07845/) (2023)
- [weighted CapsuleNet networks for Persian multi-domain sentiment analysis](https://mlsanity.com/paper/2306.17068/) (2023)
- [Dual-State Capsule Networks for Text Classification](https://mlsanity.com/paper/2109.04762/) (2021)
- [Machine and Deep Learning Methods with Manual and Automatic Labelling for News Classification in Bangla Language](https://mlsanity.com/paper/2210.10903/) (2022)
- [Towards the Characterization of Representations Learned via Capsule-based Network Architectures](https://mlsanity.com/paper/2305.05349/) (2023)
- [Accelerated materials language processing enabled by GPT](https://mlsanity.com/paper/2308.09354/) (2023)
- [Predicting Transcription Factor Binding Sites using Transformer based Capsule Network](https://mlsanity.com/paper/2310.15202/) (2023)

## Abstract (arXiv)

This paper presents an empirical exploration of the use of capsule networks for text classification. While it has been shown that capsule networks are effective for image classification, their validity in the domain of text has not been explored. In this paper, we show that capsule networks indeed have the potential for text classification and that they have several advantages over convolutional neural networks. We further suggest a simple routing method that effectively reduces the computational complexity of dynamic routing. We utilized seven benchmark datasets to demonstrate that capsule networks, along with the proposed routing method provide comparable results.