Linguistically independent sentiment analysis using convolutional-recurrent neural networks model
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F19%3APU132720" target="_blank" >RIV/00216305:26220/19:PU132720 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1109/TSP.2019.8768887" target="_blank" >http://dx.doi.org/10.1109/TSP.2019.8768887</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/TSP.2019.8768887" target="_blank" >10.1109/TSP.2019.8768887</a>
Alternative languages
Result language
angličtina
Original language name
Linguistically independent sentiment analysis using convolutional-recurrent neural networks model
Original language description
Text classification is a process which analyses text and assigns one or more classes to it based on its content. This paper introduces a linguistically independent text classifier based on convolutional–recurrent neural networks. The classifier works at character level instead of some higher structures such as words, sentences, etc. To evaluate the accuracy of the proposed methodology, the Yelp data set and other multilingual data set obtained from film review databases containing Czech, German and Spanish languages were used. The resulting accuracy on the Yelp data set is 93,64 %. We also proved that the proposed model can work for various languages.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
20203 - Telecommunications
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
2019 42nd International Conference on Telecommunications and Signal Processing (TSP)
ISBN
978-1-7281-1864-2
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
212-215
Publisher name
IEEE
Place of publication
Budapest, Hungary
Event location
Budapest, Hungary
Event date
Jul 1, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000493442800046