Towards an Automatic Generation of Persuasive Messages

No hay miniatura disponible
Lipa-Urbina E.
Condori-Fernandez N.
Suni-Lopez F.
Título de la revista
Revista ISSN
Título del volumen
Springer Science and Business Media Deutschland GmbH
Proyectos de investigación
Unidades organizativas
Número de la revista
In the last decades, the Natural Language Generation (NLG) methods have been improved to generate text automatically. However, based on the literature review, there are not works on generating text for persuading people. In this paper, we propose to use the SentiGAN framework to generate messages that are classified into levels of persuasiveness. And, we run an experiment using the Microtext dataset for the training phase. Our preliminary results show 0.78 of novelty on average, and 0.57 of diversity in the generated messages. © 2021, Springer Nature Switzerland AG.
Acknowledgments. This work has been supported by CONCYTEC - FONDECYT within the framework of the call E038-01 contract 014-2019. N. Condori Fernandez wish also to thank Datos 4.0 (TIN2016-78011-C4-1-R) funded by MINECO-AEI/FEDER-UE.
Palabras clave
Text generation, Persuasive message, SentiGAN