<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Emotional analysis of English and American literary works constitutes a significant facet of literary scholarship. This study employs a cognitive operation model for analyzing emotional expressions in English and American literature, constructing a multi-featured method for emotion recognition and analysis, which serves as the principal analytical tool of the cognitive operation model. The research involves collecting and processing textual data from English and American literary works, followed by the application of the Senti-BERT model for vectorized representation. Subsequently, a bidirectional Long Short-Term Memory (LSTM) network is used to extract emotional vectors. Furthermore, a softmax function equipped with a multi-attention mechanism facilitates the classification and recognition of emotions. The efficacy of this model was evaluated using a pertinent dataset, with four literary works selected for empirical analysis. Results indicate that the predominant emotional tone across these works is negative. Specifically, the emotion of “anger” in Charles Dickens’s “Bleak House” was predominantly observed in chapters 0-2200, with an emotion value ranging between 20-30. This study provides a robust methodological framework for dissecting the complex emotional expressions in English and American literary texts, thereby enhancing readers’ comprehension of the nuanced meanings embedded within these works.</p>
</abstract>

Emotional analysis of English and American literary works constitutes a significant facet of literary scholarship. This study employs a cognitive operation model for analyzing emotional expressions in English and American literature, constructing a multi-featured method for emotion recognition and analysis, which serves as the principal analytical tool of the cognitive operation model. The research involves collecting and processing textual data from English and American literary works, followed by the application of the Senti-BERT model for vectorized representation. Subsequently, a bidirectional Long Short-Term Memory (LSTM) network is used to extract emotional vectors. Furthermore, a softmax function equipped with a multi-attention mechanism facilitates the classification and recognition of emotions. The efficacy of this model was evaluated using a pertinent dataset, with four literary works selected for empirical analysis. Results indicate that the predominant emotional tone across these works is negative. Specifically, the emotion of “anger” in Charles Dickens’s “Bleak House” was predominantly observed in chapters 0-2200, with an emotion value ranging between 20-30. This study provides a robust methodological framework for dissecting the complex emotional expressions in English and American literary texts, thereby enhancing readers’ comprehension of the nuanced meanings embedded within these works.

Multi-featured Emotional Expressions in English and American Literature - Based on the Application of Thinking Operations Modeling

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Emotional analysis of English and American literary works constitutes a significant facet of literary scholarship. This study employs a cognitive operation...

Multi-featured Emotional Expressions in English and American Literature - Based on the Application of Thinking Operations Modeling

Publié en ligne: 07 juin 2024

Pages: -

Reçu: 08 févr. 2024

Accepté: 18 avr. 2024

DOI: https://doi.org/10.2478/amns-2024-1392

Mots clés
Senti-BERT, Softmax function, Vectorization, Emotional features, Literary emotional expression

© 2024 Xiaoke Cui et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Multi-featured Emotional Expressions in English and American Literature - Based on the Application of Thinking Operations Modeling

Publié en ligne: 07 juin 2024

Pages: -

Reçu: 08 févr. 2024

Accepté: 18 avr. 2024

DOI: https://doi.org/10.2478/amns-2024-1392

Mots clésSenti-BERT, Softmax function, Vectorization, Emotional features, Literary emotional expression

© 2024 Xiaoke Cui et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Mots clés
Senti-BERT, Softmax function, Vectorization, Emotional features, Literary emotional expression