Hybrid Tiled Convolutional Neural Networks (HTCNN) Text Sentiment Classification

Maria Truşcǎ, Gerasimos Spanakis

2020

Abstract

The tiled convolutional neural network (TCNN) has been applied only to computer vision for learning invariances. We adjust its architecture to NLP to improve the extraction of the most salient features for sentiment analysis. Knowing that the major drawback of the TCNN in the NLP field is its inflexible filter structure, we propose a novel architecture called hybrid tiled convolutional neural network (HTCNN) that applies a filter only on the words that appear in similar contexts and on their neighbouring words (a necessary step for preventing the loss of some n-grams). The experiments on the IMDB movie reviews dataset demonstrate the effectiveness of the HTCNN that has a higher level of performance of more than 3% and 1% respectively than both the convolutional neural network (CNN) and the TCNN. These results are confirmed by the SemEval-2017 dataset where the recall of the HTCNN model exceeds by more than six percentage points the recall of its simple variant, CNN.

Paper Citation

in Harvard Style

Truşcǎ M. and Spanakis G. (2020). Hybrid Tiled Convolutional Neural Networks (HTCNN) Text Sentiment Classification. In Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-395-7, pages 506-513. DOI: 10.5220/0008946505060513

in Bibtex Style

@conference{icaart20,
author={Maria Truşcǎ and Gerasimos Spanakis},
title={Hybrid Tiled Convolutional Neural Networks (HTCNN) Text Sentiment Classification},
booktitle={Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2020},
pages={506-513},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008946505060513},
isbn={978-989-758-395-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Hybrid Tiled Convolutional Neural Networks (HTCNN) Text Sentiment Classification
SN - 978-989-758-395-7
AU - Truşcǎ M.
AU - Spanakis G.
PY - 2020
SP - 506
EP - 513
DO - 10.5220/0008946505060513