Automated generation of presentations based on the cognitive-aesthetic paradigm

Purpose of research. The objective of this study is to develop a software solution for automated presentation generation, focused on integrating principles of cognitive psychology and aesthetics. The research aims to create an intelligent platform capable of generating presentations that not only convey information but also ensure its effective visual perception, capturing and retaining audience attention. In an era of rapidly increasing data volumes and decreasing time resources, there is a growing need for tools that can automate the creation of visual content without compromising its quality. The proposed solution takes into account the specific characteristics of human information perception by relying on cognitive principles such as cognitive load theory, Gestalt laws, and visual emphasis. In addition, it applies aesthetic design techniques to create a balanced and expressive visual structure.

Methods. The study combines various approaches and methods, including cognitive and aesthetic aspects, objectoriented programming, and integration with artificial intelligence technologies. This allows the system to automatically generate both textual and visual content, adapting it to the predefined structure of the presentation.

Results. The developed software solution demonstrated advantages over existing tools across several key parameters: reduced presentation creation time, improved visual quality, adaptability, and alignment with cognitive strategies of information perception. Experimental results involving users confirmed the high efficiency of the proposed approach in terms of usability, design quality, and content perception.

Conclusion. The proposed solution, based on the cognitive-aesthetic paradigm, represents a promising direction in the field of automated visual communication. It demonstrates potential for scalability and integration across various domains that require the creation of presentation content combining informativeness, visual expressiveness, and a human-centered design approach. 

1. Zlatopolsky D.M. Fundamentals of programming in Python. Moscow: DMK Press; 2017. 284 p. (In Russ.).

2. Sveygart, El. Automation of routine tasks using Python: a practical guide for beginners. Moscow: Williams; 2016. 592 p. (In Russ.)

3. Gaddis T. Starting to program in Python. St. Petersburg: BHV-Petersburg; 2019. 768 p. (In Russ.)

4. Fedorov D. Yu. Programming in a high-level Python language: a textbook for applied bachelor's degree. Moscow: Yurait; 2019. 161 p. (In Russ.). Available at: https://urait.ru/bcode/437489

5. Reitz K., Schlusser T. The Hitchhiker's guide to Python. St. Petersburg: Piter; 2017. 336 p. (In Russ.)

6. Butch G. Object-oriented analysis and design using application examples. Moscow: DMK Press; 2007. 520 p. (In Russ.)

7. Gamma E., Helm R., Partner R., Vlissides D. Object-oriented design techniques. Design patterns. St. Petersburg: Peter; 2009. 368 p. (In Russ.)

8. Chirvinsky A. Fundamentals of color theory in graphic design. Zhurnal dizaina i teorii tsveta = Journal of Design and Color Theory. 2019; (3): 45-53. (In Russ.)

9. Hein J. Algorithms for automatic color adjustment for image processing applications. Zhurnal tsifrovoi obrabotki izobrazhenii = Journal of Digital Image Processing. 2020; 33 (4): 124-130. (In Russ.).

10. Stevens H. Intelligent generation of presentations in dynamic environments. Mezhdunarodnyi zhurnal peredovoi komp'yuternoi nauki i prilozhenii = International Journal of Advanced Computer Science and Applications. 2019; 10(6): 155-161. (In Russ.)

11. Osborn A.F. Development of presentations for visual clarity. Zhurnal delovoi i tekhnicheskoi kommunikatsii = Journal of Business and Technical Communication. 2018; 32 (1): 87-102. (In Russ.)

12. Smith J. Designing an adaptive user interface. Trudy IEEE po sistemam «chelovekmashina» = IEEE Proceedings on human-machine systems. 2022; 52 (2): 320-330. (In Russ.)

13. Roy P., Pandi S., Jain K. Deep learning for natural language processing: the application of deep neural networks to machine learning tasks in the field of natural language processing. Cham: Springer; 2018. 280 p. (In Russ.)

14. Rotman D. Transformers for natural language processing: creation and deployment of modern natural language processing pipelines. Birmingham: Packt Publishing; 2021. 374 p. (In Russ.).

15. Yarichev M. GPT-3: Creating innovative natural language processing products using the OpenAI GPT-3 API. Independent edition, 2021. 210 p. (In Russ.)

16. Scriabin A. Practical image generation with TensorFlow: creation of generative models using VAE, GAN and diffusion models. Birmingham: Packt Publishing; 2022. 380 p. (In Russ.)

17. Javad M., Longhi A. Machine learning for visual data analytics: from deep learning models to GAN and VAE. Cham: Springer; 2021. 420 p. (In Russ.).

18. Foster D. Generative deep learning: teaching machines to draw, write, compose and play. Sevastopol: O'Reilly Media; 2019. 352 p. (In Russ.).

19. Wong D. M., Shankaranarayanan, G. Automated Data Visualization: A Review and Future Directions. Shankaranarayanan. Journal of Visual Languages & Computing. 2022.

20. Allison J., McNamara S. Data Storytelling for Business: The Essential Guide to Engaging Visualization. Springer; 2021.

21. Gomez E., Decker S. Generative Design for Data Visualization: A Review and Framework. Computer Graphics Forum. 2022.