Artículo
Efficiency of automatic text generators for online review content generation
Autor/es | Pérez-Castro, A.
Martínez Torres, María del Rocío Toral, S. L. |
Departamento | Universidad de Sevilla. Departamento de Administración de Empresas y Comercialización e Investigación de Mercados (Marketing) Universidad de Sevilla. Departamento de Ingeniería Electrónica |
Fecha de publicación | 2023-04 |
Fecha de depósito | 2024-01-29 |
Publicado en |
|
Resumen | The evolution of Artificial Intelligence has led to the appearance of automatic text generators able to closely resemble human writing, endangering the development of e-commerce and the consumer confidence. Thus, it is ... The evolution of Artificial Intelligence has led to the appearance of automatic text generators able to closely resemble human writing, endangering the development of e-commerce and the consumer confidence. Thus, it is critical to deeply understand how these text generators work to present the presence of deceptive reviews. This paper analyzes one of the most popular text generators, GPT2 (Generative Pre-trained Transformer 2), and studies its effectivity compared to human-generated reviews using previously published classifiers trained to distinguish between real and deceptive reviews. One parameter of the model is the so-called temperature, which determines how deterministic the model is. The temperature adjusts the probability distribution of the words in the model, so that a higher temperature translates into a higher degree of inventiveness in the generation of the texts. Findings reveal (i) that automatically-generated deceptive reviews worsen the accuracy of existing classifiers, this effect being accentuated by the degree of inventiveness; (ii) that their performance depends on the data used to train the generator; and (iii) that the sentiment polarity has no effect on the performance of detection classifiers. |
Agencias financiadoras | Ministerio de Ciencia e Innovación (MICIN). España Junta de Andalucía |
Identificador del proyecto | PID2020-114527RB-I00
10.13039/501100011033 PY20_00639 |
Cita | Pérez-Castro, A., Martínez Torres, M.d.R. y Toral, S.L. (2023). Efficiency of automatic text generators for online review content generation. Technological Forecasting and Social Change, 189, 122380. https://doi.org/10.1016/j.techfore.2023.122380. |
Ficheros | Tamaño | Formato | Ver | Descripción |
---|---|---|---|---|
Efficiency_of_automatic_text_g ... | 3.999Mb | [PDF] | Ver/ | |