# Text classification problems via BERT embedding method and graph convolutional neural network

arXiv: https://arxiv.org/abs/2111.15379 · HTML: https://mlsanity.com/paper/2111.15379/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 30 Nov 2021.

## Builds on (most cited first, 8 of 8)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction](https://mlsanity.com/paper/1909.02027/) (2019)
- [Attention Guided Graph Convolutional Networks for Relation Extraction](https://mlsanity.com/paper/1906.07510/) (2019)
- [Alternative Weighting Schemes for ELMo Embeddings](https://mlsanity.com/paper/1904.02954/) (2019)
- [Directed hypergraph neural network](https://mlsanity.com/paper/2008.03626/) (2020)
- [Hypergraph based semi-supervised learning algorithms applied to speech recognition problem: a novel approach](https://mlsanity.com/paper/1810.12743/) (2018)
- [Noise-robust classification with hypergraph neural network](https://mlsanity.com/paper/2102.01934/) (2021)
- [Un-normalized hypergraph p-Laplacian based semi-supervised learning methods](https://mlsanity.com/paper/1811.02986/) (2018)

## Built on by (most cited first, 2 of 2)

- [Compute the edge p-Laplacian centrality for air traffic network](https://mlsanity.com/paper/2512.14749/) (2025)
- [Soft Contextualized Encoder For User Defined Text Classification](https://mlsanity.com/paper/2601.03450/) (2026)

## Abstract (arXiv)

This paper presents the novel way combining the BERT embedding method and the graph convolutional neural network. This combination is employed to solve the text classification problem. Initially, we apply the BERT embedding method to the texts (in the BBC news dataset and the IMDB movie reviews dataset) in order to transform all the texts to numerical vector. Then, the graph convolutional neural network will be applied to these numerical vectors to classify these texts into their ap-propriate classes/labels. Experiments show that the performance of the graph convolutional neural network model is better than the perfor-mances of the combination of the BERT embedding method with clas-sical machine learning models.