Conceptual model of the process of determining the emotional tonality of the text.
Abstract
The task of recognizing the emotional tonality of text fragments is an important problem in the field of natural language processing with significant academic and commercial potential. This paper presents a conceptual model of the process of determining the emotional tonality of text. The model provides a formalized and detailed description of the task, facilitating the development of appropriate tools for recognizing the emotional coloring and tonality of text fragments. It systematizes the key stages, including the formation of training data, selection of the neural network architecture, its configuration and training, as well as direct use for recognizing emotional coloring and tonality. The conceptual model defines the dependencies between various factors that affect the efficiency of the emotional tonality recognition process, such as the quality of input data, parameters of the neural network model, resource consumption, and errors during training and recognition. This allows identifying critical aspects that should be considered to improve the overall efficiency of the system. The model also provides for the involvement of expert knowledge at various stages to improve the quality of input data and optimize model parameters. The proposed conceptual model can serve as a basis for the development of effective means of recognizing emotional coloring and tonality, which will have practical applications in various fields, such as social network analysis, customer service, and marketing.
References
2. S. Toliupa, Y. Kulakov, I. Tereikovskyi, O. Tereikovskyi, L. Tereikovska, and V. Nakonechnyi, "Keyboard Dynamic Analysis by Alexnet Type Neural Network," in 2020 IEEE 15th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET), Lviv-Slavske, Ukraine, 2020, pp. 416-420,
3. I. A. Dychka, I. A. Tereikovskyi, O. S. Korovii, L. O. Tereikovska, and V. O. Romankevych, "Evaluation of the effectiveness of means for recognizing the emotional tonality of text fragments," Scientific notes of Taurida National V.I. Vernadsky University. Series: Technical Sciences, vol. 34 (73), no. 3, part 1, pp. 130-135, 2023.
4. Z. Halim, M. Waqar, and M. Tahir, "A machine learning-based investigation utilizing the in-text features for the identification of dominant emotion in an email," Knowledge-Based Systems, vol. 208, pp. 1–17, 2020.
5. A. Adikari, G. Gamage, D. de Silva, N. Mills, S.-M. J. Wong, and D. Alahakoon, "A self structuring artificial intelligence framework for deep emotions modelling and analysis on the social web," Future Generation Computer Systems, vol. 116, pp. 302–315, 2021.
Abstract views: 33 PDF Downloads: 48