Identificación de Patrones Emocionales Básicos en Publicidad Audiovisual Utilizando Modelos Vectoriales por Adaptación
Abstract
At present, the analysis of the results of advertising and marketing studies is done qualitatively in terms of the experience of a marketing analyst, thus generating little certainty and uncertainty of the effectiveness of the feelings and the message emitted. Brands are connected with the idea that the sender wants to transmit. For this, the marketing has studied the behavior of the consumer when exposed to different advertising stimuli, in order to understand the behavior at the time of the stimulus and to achieve alignment of the message to be transmitted with what is actually perceived. In this paper we propose a vector model based on computational intelligence and Neuromarketing studies that allows the identification of four basic emotions: joy, fear, anger and sadness from the bioelectric brain activity recorded by a person exposed to a certain audiovisual advertising. The results of the model allowed the identification of emotions in audiovisual advertising, which constitutes a tool that allows companies to create audiovisual advertising that guarantees greater commitment and effectiveness of the advertising segments with which it wants to impact the market
Keywords: Neuromarketing, audiovisual advertising, basic emotions, neural networks, Emotiv-EPOC®, vector support machines
References
[1] Arango, J. Cárdenas, J., Peña, A. (2013) Sistema para Rehabilitación del Síndrome del Miembro Fantasma utilizando Interfaz Cerebro-Computador y Realidad Aumentada, Iberian Journal of Information Systems and Technologies, no. 11, pp. 93-106, 2013, doi:10.4304/risti.11.93-106.
[2] Braidot, N. (2011) Neuromarketing En Acción, Editorial Granica, 234 pags. [3] Colomer, A. Naranjo, V. Guixeres, J. Rojas, J.C. Coret, J. Alcañiz, M. (2015) Brain Activity Quantification for Sport Audiovisual Content Visualization using EEG, 8th International Conference on Bio-inspired Systems and Signal Processing (BIOSIGNALS 2015).
[4] Dan-Glauser, E. S. Scherer, K. R. (2011) The Geneva Affective PicturE Database (GAPED): a new 730-picture database focusing on valence and normative significance, Behavior Research Methods, pp. 468-477.
[5] Deak, A. (2011) Brain and emotion: Cognitive neuroscience of emotions, Review of Psychology, pp. 71-80.
[6] Eser, Z. Isin, F., Tolon, M. (2011) Perceptions of marketing academics, neurologists and marketing professionals about neuromarketing, Journal of Marketing Management 27(7-8).
[7] Ferrer, A. (2009) Neuromarketing: la tangibilización de las emociones, Bachelor Thesis, Universitat Abat Oliva CEU.
[8] González, P. (1991) Error Cuadrático Medio de Predicción Para Modelos Estructurales de Series Temporales Estadística Española, vol. 34, no. 129, p. 117–135, 1992.
[9] Gómez, V. Jaramillo, E. Peña P., A. Osuna, S. Lopera, L. (2016) Identificación automática de patrones visuales emocionales en publicidad audiovisual mediante la actividad bioeléctrica cerebral de un individuo, Conferencia Ibérica de Sistemas y Tecnologías de la Información - CISTI2016.
[10] Guevara Mosquera, S. D. Adquisición de señales electroencefalográficas para el movimiento de un prototipo de silla de reuedas en un sistema BCI, Tesis de Maestría, Universidad Politécnica Salesiana, Cuenca, 2012.
[11] Hippe, Z. S. Kulikowski, J. L. Mroczek, T. Human – Computer Systems Interaction: Backgrounds and Applications, Computational Intelligence and Complexity (2), Springer, 2012.
[12] Hamelin, N. El Moujahidc, O. Thaichonb, P. (2017) Emotion and advertising effectiveness: A novel facial expression analysis approach, Journal of Retailing and Consumer Services 36, Pages 103–111.
[13] Isazi, P. Galván, I. Redes de Neuronas Artificiales - Un enfoque práctico, 2004.
[14] León, A.C. (2010) El Neuromarketing: La Llave De La Caja De Pandora, Universidad del Rosario, Repositorio Institucional 2010.
[15] Morin, C. (2011) Neuromarketing: The new science of consumer behavior, Society Journal 48(2) pp. 131-135.
[16] Peña P., A. Bello, C. Osuna, S. Identificación de la afinidad en publicidad audiovisual mediante la utilización de modelos vectoriales adaptables, Conferencia Ibérica de Sistemas y Tecnologías de la Información CISTI2015, El Aveiro, Portugal.
[17] Sánchez, M. J. La persuasión de la música en la publicidad, Revistas científicas complutenses, vol. 18, 2013.
[18] Santos, J.P. Moutinho, L. Seixas, D. Brandao, S. Neural correlates of the emotional and symbolic content of brands: A neuroimaging study, Journal of Customer Behaviour, vol. 11, no. 1, pp. 69-93, 2012.
[19] Schaefer, M. Berens, H. Heinze, H-J, Rotte, M. (2006) Neural correlates of culturally familiar brands of car manufacturers, Neuroimage 31(2) pp. 861-865.
[20] Tong, Y. C. San, E., Rizon, M. Classification of Human Emotions form EEG Signals using Statistical Features and Neural Network, International Journal of Integrated Engineering 1(3), pp. 71-80, 2009.
[21] Wang, J. Ma, X. Sun, J. Zhao, Z. Zhu, Y (2014) Puzzlement Detection from Facial Expression Using Active Appearance Models and Support Vector Machines” International Journal of Signal Processing, Image Processing and Pattern Recognition, 7(5), pp. 349-360.
[22] Velásquez, A. Cardona and A. Peña, ”Modelo Vectorial para la Inferencia del Estado Cognitivo de Pacientes en Estados Derivados del Coma,” Revista Ibérica de Sistemas y Tecnologías de la Información - RISTI, vol. 13, pp. 65-81, 2014, ISSN: 1646-9895.
[23] Zurawicki, L. (2010) Neuromarketing: Exploring the brain of the consumer, Business & Management Book, Springer, Verlag, 2010.