Detail publikace

Graph convolutional neural networks for sentiment analysis

MYŠKA, V.

Originální název

Graph convolutional neural networks for sentiment analysis

Anglický název

Graph convolutional neural networks for sentiment analysis

Jazyk

en

Originální abstrakt

Commonly used approaches based on deep learning for sentiment analysis task operating over data in Euclidean space. In contrast with them, this paper presents, a novel approach for sentiment analysis task based on a graph convolutional neural networks (GCNs) operating with data in Non-Euclidean space. Text data processed by the approach have to be converted to a graph structure. Our GCNs models have been trained on 25 000 data samples and evaluated 5 000 samples. The Yelp data set has been used. The experiment is focused on polarity sentiment analysis task. Nevertheless, a relatively small training data set has been used, our best model achieved 86.12% accuracy.

Anglický abstrakt

Commonly used approaches based on deep learning for sentiment analysis task operating over data in Euclidean space. In contrast with them, this paper presents, a novel approach for sentiment analysis task based on a graph convolutional neural networks (GCNs) operating with data in Non-Euclidean space. Text data processed by the approach have to be converted to a graph structure. Our GCNs models have been trained on 25 000 data samples and evaluated 5 000 samples. The Yelp data set has been used. The experiment is focused on polarity sentiment analysis task. Nevertheless, a relatively small training data set has been used, our best model achieved 86.12% accuracy.

Dokumenty

BibTex


@inproceedings{BUT164699,
  author="Vojtěch {Myška}",
  title="Graph convolutional neural networks for sentiment analysis",
  annote="Commonly used approaches based on deep learning for sentiment analysis task operating over data in Euclidean space. In contrast with them, this paper presents, a novel approach for sentiment analysis task based on a graph convolutional neural networks (GCNs) operating with data in Non-Euclidean space. Text data processed by the approach have to be converted to a graph structure. Our GCNs models have been trained on 25 000 data samples and evaluated 5 000 samples. The Yelp data set has been used. The experiment is focused on polarity sentiment analysis task. Nevertheless, a relatively small training data set has been used, our best model achieved 86.12% accuracy.",
  address="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií",
  booktitle="Proceedings I of the 26th Conference STUDENT EEICT 2020",
  chapter="164699",
  howpublished="online",
  institution="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií",
  year="2020",
  month="april",
  pages="340--344",
  publisher="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií",
  type="conference paper"
}