Creativity Unleashed: The Role of AI in Transforming Artistic Expression

Creativity Unleashed: The Role of AI in Transforming Artistic Expression

*Siti Hajar Maizan, Nurul Shima Taharuddin

College of Creative Arts, University Technology MARA (UiTM) Perak Branch, Seri Iskandar Campus, 32610 Perak, Malaysia

*Corresponding author

DOI: https://dx.doi.org/10.47772/IJRISS.2025.90300294

Received: 12 March 2025; Accepted: 15 March 2025; Published: 15 April 2025

ABSTRACT

Artificial Intelligence (AI) is increasingly influencing various domains, including the arts, by transforming traditional forms of artistic expression and creating new possibilities for creativity. This review explores the impact of AI on artistic fields, including visual arts, music, literature, and performance arts. By analyzing recent advancements from 2013 to 2024, the paper examines how AI tools like generative algorithms, neural networks, and deep learning models are reshaping artistic processes and outcomes. The findings highlight both the opportunities AI presents for enhancing creativity and the challenges related to originality and human-AI collaboration. This review aims to provide a comprehensive understanding of AI’s role in artistic transformation and identify future research directions.

Keywords: artificial intelligence, arts, artistic expression, creativity

INTRODUCTION

The intersection of Artificial Intelligence (AI) and the arts represents a dynamic and evolving field that challenges traditional notions of creativity. AI technologies, particularly machine learning and deep learning, have become increasingly sophisticated, offering artists novel tools and methodologies to push the boundaries of artistic expression (McCormick, 2021). AI’s ability to analyze, generate, and transform creative content has led to significant advancements in various artistic domains, including visual arts, music, literature, and performance (Gao et al., 2023). This review article explores the transformative effects of AI on artistic expression, examining how these technologies are being employed to create innovative artworks, enhance creative processes, and expand the possibilities for artistic exploration.

As AI technologies continue to evolve, they bring new perspectives on creativity and challenge conventional definitions of artistic authorship and originality (Williams & Clark, 2022). The integration of AI in the arts has sparked debates about the role of human creativity versus machine-generated outputs and the implications for the future of artistic practice (Smith & Johnson, 2023). This introduction provides an overview of the key areas where AI has made an impact, setting the stage for a detailed examination of AI’s role in transforming artistic expression through subsequent sections of the review.

LITERATURE REVIEW

AI in Visual Arts: AI has made notable contributions to the visual arts by employing generative algorithms and neural networks to create new forms of visual expression. Algorithms such as Generative Adversarial Networks (GANs) have been used to generate original artworks by learning from vast datasets of existing images (Karras et al., 2018). These tools have enabled artists to explore novel styles and aesthetics, blurring the lines between human and machine creativity (Elgammal et al., 2017). Additionally, AI-driven tools have facilitated art restoration and enhancement by analyzing and recreating damaged or incomplete artworks (Liu et al., 2022). AI technologies have significantly impacted the visual arts through the application of generative algorithms and neural networks, introducing novel forms of visual expression that were previously unattainable. One of the most prominent AI techniques in this domain is Generative Adversarial Networks (GANs). GANs, introduced by Goodfellow et al. (2014), have been further refined and employed to create original artworks by learning from extensive datasets of existing images (Karras et al., 2018). GANs work by generating images through a two-part system consisting of a generator and a discriminator. The generator creates new images, while the discriminator evaluates them against real images, leading to the production of increasingly sophisticated visual content. This process has enabled artists to push the boundaries of traditional aesthetics and explore innovative styles that blur the lines between human and machine creativity (Karras et al., 2018). The versatility of GANs has allowed for a range of artistic experiments, from abstract compositions to hyper-realistic portraits, demonstrating the technology’s capacity to enhance artistic creativity.

The advent of AI in visual arts has also facilitated significant advancements in art restoration and enhancement. Traditional art restoration techniques often involve painstaking manual work to repair and reconstruct damaged or incomplete artworks. However, AI-driven tools have introduced a transformative approach to this process by leveraging machine learning algorithms to analyze and recreate artworks with greater precision and efficiency. Liu et al. (2022) highlight how AI techniques, such as image inpainting and style transfer, have been applied to reconstruct missing parts of artworks and enhance their visual quality. By analyzing historical data and comparing it with existing artwork, AI systems can predict and generate restored content that aligns with the original artist’s style and intent. This capability not only accelerates the restoration process but also preserves the integrity and historical value of artistic works, making it a valuable tool for museums and cultural heritage institutions (Liu et al., 2022).

Furthermore, the integration of AI into the visual arts has raised important discussions about the nature of creativity and the role of technology in artistic expression. Elgammal et al. (2017) argue that AI-generated art challenges traditional notions of authorship and creativity by presenting artworks created by algorithms that learn from human inputs. This intersection of human and machine creativity fosters a new understanding of artistic creation, where AI is seen not merely as a tool but as an active collaborator in the creative process. The ability of AI to generate novel visual content and explore aesthetic possibilities that may not be readily conceived by humans underscores the potential of these technologies to expand the horizons of artistic expression. As AI continues to evolve, its role in shaping and redefining artistic practices will likely become more pronounced, prompting ongoing dialogue about the future of art in the age of advanced technologies (Elgammal et al., 2017).

AI in Music Composition: The application of AI in music composition has revolutionized the creative process by enabling the generation of original compositions and the augmentation of traditional music-making techniques. AI algorithms, including recurrent neural networks and deep learning models, have been utilized to compose music in various genres and styles, providing musicians with new sources of inspiration and collaboration (Huang & Chiang, 2019). AI tools have also been employed to analyze musical patterns and trends, offering insights into composition techniques and aiding in the creation of new musical works (Sturm et al., 2020). AI’s integration into music composition has brought about transformative changes in how music is created and understood, fundamentally altering the creative process for musicians. One of the key advancements has been the application of recurrent neural networks (RNNs) and deep learning models, which have been used to generate original compositions across diverse genres and styles. Huang and Chiang (2019) provide a comprehensive survey of how deep learning techniques, including Long Short-Term Memory (LSTM) networks and Transformer models, have been employed to compose music that mimics classical styles or innovates with contemporary sounds. These models are trained on extensive datasets of musical compositions, enabling them to learn patterns and structures inherent in different musical genres. By leveraging these algorithms, musicians can access novel sources of inspiration, as AI can produce compositions that explore new harmonic progressions and rhythmic patterns that may not have been conceived through traditional methods.

Additionally, AI tools have become instrumental in analyzing musical patterns and trends, which provides valuable insights into composition techniques and the evolution of musical styles. Sturm et al. (2020) discuss how AI-driven analytics can dissect and interpret complex musical data, revealing underlying patterns that can inform the creative process. For instance, machine learning algorithms can identify recurring motifs, chord progressions, and stylistic elements across various compositions. This capability not only aids composers in understanding the mechanics of different musical forms but also supports the creation of new works by suggesting variations and innovations based on established patterns. The analysis facilitated by AI tools thus acts as both a historical reference and a creative catalyst, helping musicians to push the boundaries of their compositions while remaining informed by historical and contemporary trends.

Moreover, the collaboration between AI and human composers exemplifies a novel approach to music-making where technology serves as a partner rather than a replacement. AI systems are increasingly being used to augment traditional music-making techniques by offering real-time suggestions and generating complementary elements that enhance the creative output. Huang and Chiang (2019) highlight how AI-generated music can be used as a basis for further human refinement, allowing composers to integrate AI’s creative suggestions into their own artistic visions. This symbiotic relationship between human creativity and AI capabilities facilitates a dynamic and iterative process of music composition, leading to the exploration of new musical landscapes and the enrichment of the artistic experience. As AI technologies continue to advance, their role in music composition is expected to expand, offering even more sophisticated tools for creativity and collaboration (Huang & Chiang, 2019; Sturm et al., 2020).Top of FormBottom of Form

AI in Literature and Writing: AI technologies have impacted literature and writing by generating textual content and assisting in the creative writing process. Natural Language Processing (NLP) models, such as GPT-3, have demonstrated the capability to generate coherent and contextually relevant text, enabling authors to explore new narrative structures and storytelling techniques (Brown et al., 2020). AI tools have also been used to analyze literary works and provide insights into stylistic elements, contributing to the development of new literary forms and genres (Kumar & Sharma, 2021). AI technologies have significantly transformed the landscape of literature and writing by introducing advanced tools for generating and analyzing textual content. One of the most notable advancements is the development of Natural Language Processing (NLP) models such as GPT-3, which have demonstrated an impressive ability to produce coherent and contextually relevant text. Brown et al. (2020) describe how GPT-3, a state-of-the-art language model developed by OpenAI, utilizes deep learning techniques to generate text that is not only syntactically correct but also semantically rich and contextually appropriate. This capability allows authors to experiment with new narrative structures and storytelling techniques by providing a powerful tool for creative exploration. Writers can use AI-generated text to brainstorm ideas, overcome writer’s block, and develop innovative plotlines that may not have emerged through traditional writing processes.

In addition to text generation, AI tools have been instrumental in analyzing literary works, offering new insights into stylistic elements and contributing to the creation of novel literary forms and genres. Kumar and Sharma (2021) highlight how AI-driven text analysis can reveal underlying patterns and stylistic features in literary works, such as recurring themes, narrative techniques, and linguistic structures. By applying machine learning algorithms to large corpora of literature, researchers and authors can gain a deeper understanding of various literary styles and trends. This analytical power supports the development of new genres and forms by identifying gaps and opportunities for innovation. For instance, AI can assist in the creation of hybrid genres or experimental writing forms by analyzing and synthesizing elements from different literary traditions.

Furthermore, the integration of AI in literature and writing extends beyond mere analysis and generation; it also involves enhancing the creative process through interactive tools and collaborative platforms. AI-driven writing assistants can provide real-time feedback, suggest stylistic improvements, and offer contextual recommendations to authors (Kumar & Sharma, 2021). These tools facilitate a more dynamic and iterative writing process, where human creativity is complemented by AI’s analytical capabilities. As AI technologies continue to evolve, their role in literature and writing is likely to expand, offering even more sophisticated tools for generating, analyzing, and enhancing textual content. This evolving partnership between human creativity and AI promises to redefine the boundaries of literary expression and innovation (Brown et al., 2020; Kumar & Sharma, 2021).

AI in Performance Arts: AI has also influenced performance arts by introducing innovative approaches to choreography, stage design, and interactive performances. Machine learning algorithms have been employed to create dynamic and adaptive performances that respond to audience input and environmental factors (Pappalardo et al., 2019). AI-driven technologies have enabled the development of interactive installations and performances that explore the intersection of technology and human expression, expanding the possibilities for creative exploration in the performance arts (Tan et al., 2021). AI’s influence on performance arts has been transformative, offering new methodologies for choreography, stage design, and interactive performances. One of the significant advancements is the use of machine learning algorithms to create dynamic and adaptive performances. Pappalardo et al. (2019) describe how AI technologies can analyze audience reactions and environmental factors in real-time to adjust performances accordingly. For example, machine learning models can process data from sensors and cameras to modify lighting, sound, or movement patterns based on audience engagement or atmospheric conditions. This capability allows for more responsive and personalized performances, creating a more immersive and interactive experience for the audience. Such innovations reflect a shift towards performances that are not only artistically compelling but also technologically advanced, bridging the gap between traditional performance arts and modern technological capabilities.

In addition to dynamic performances, AI-driven technologies have been pivotal in the development of interactive installations and performances. Tan et al. (2021) explore how AI can be integrated into interactive art installations to create experiences that engage audiences in novel ways. For instance, AI can be used to generate real-time visual or auditory feedback based on audience interaction, enhancing the participatory aspect of performance art. This includes using AI to generate custom soundscapes or visual projections that evolve with the audience’s movements or inputs, providing a unique and evolving artistic experience. The integration of AI in these contexts not only enriches the creative possibilities for artists but also transforms the way audiences engage with and interpret performance art.

Furthermore, AI’s role in performance arts extends to the exploration of new creative frontiers through advanced algorithms and data-driven approaches. By leveraging AI, artists can experiment with novel choreography techniques, stage designs, and interactive elements that push the boundaries of traditional performance art. This includes the use of AI to create generative choreography that responds to live data or to design adaptive stage environments that change in response to the performance (Pappalardo et al., 2019; Tan et al., 2021). The synergy between AI and performance arts offers exciting opportunities for innovation, allowing artists to explore new dimensions of expression and audience interaction. As AI technologies continue to advance, their potential to further revolutionize the performance arts is vast, promising even more sophisticated and interactive artistic experiences in the future.

METHODOLOGY

This review employs a systematic literature review methodology to analyze the role of AI in transforming artistic expression. The approach involves a comprehensive search of academic databases such as Google Scholar, Scopus, and IEEE Xplore, using keywords related to AI applications in visual arts, music, literature, and performance arts. Studies published between 2013 and 2024 were selected based on their relevance, methodological rigor, and contributions to the field. Inclusion criteria focused on empirical research, theoretical frameworks, and reviews that provide insights into AI’s impact on artistic creativity and expression (McCormick, 2021).

Data extraction involved summarizing key findings, methodologies, and applications described in the selected literature. The analysis was structured around the main artistic domains affected by AI, highlighting advancements in technology, changes in artistic processes, and emerging trends (Gao et al., 2023). The review also identified gaps in the current literature and proposed areas for future research, focusing on the implications of AI for creativity, authorship, and the role of human input in artistic practices (Williams & Clark, 2022).

FINDINGS

Transformative Impact on Visual Arts: The use of AI in visual arts has led to the creation of innovative artworks and new aesthetic experiences. Generative Adversarial Networks (GANs) have enabled artists to explore unconventional styles and techniques, resulting in unique visual outputs that challenge traditional notions of creativity (Karras et al., 2018). AI-driven tools have also facilitated art restoration and enhancement, demonstrating the potential of AI to contribute to the preservation and revival of historical artworks (Liu et al., 2022).

Innovations in Music Composition: AI technologies have significantly influenced music composition by providing new tools for generating original music and analyzing musical patterns. Recurrent neural networks and deep learning models have been employed to create compositions in diverse genres, offering musicians new sources of inspiration and expanding the creative possibilities in music (Huang & Chiang, 2019). AI-driven analysis of musical trends has also contributed to the development of novel composition techniques and styles (Sturm et al., 2020).

Advancements in Literary Creativity: AI has impacted literary creativity by generating textual content and assisting in the writing process. Natural Language Processing (NLP) models, such as GPT-3, have demonstrated the ability to produce coherent and contextually relevant text, enabling authors to experiment with new narrative forms and storytelling techniques (Brown et al., 2020). AI tools have also provided insights into literary styles and structures, contributing to the evolution of literary forms and genres (Kumar & Sharma, 2021).

Enhancements in Performance Arts: AI has introduced innovative approaches to performance arts, including interactive and adaptive performances that respond to audience input and environmental factors. Machine learning algorithms have been used to create dynamic stage designs and choreographies, expanding the creative possibilities in performance arts (Pappalardo et al., 2019). AI-driven technologies have also facilitated the development of interactive installations that explore the intersection of technology and human expression (Tan et al., 2021).

DISCUSSION

The integration of AI into artistic practices has redefined traditional concepts of creativity and artistic expression. AI technologies, such as GANs and NLP models, have introduced new methods for creating and analyzing artworks, music, literature, and performances. These advancements offer artists novel tools for exploration and expression, pushing the boundaries of conventional artistic practices (McCormick, 2021). However, the use of AI in the arts also raises important questions about originality, authorship, and the role of human creativity in the artistic process (Williams & Clark, 2022).

One of the key challenges associated with AI in the arts is the question of originality and the potential for machine-generated content to overshadow human creativity. While AI can generate impressive and novel outputs, the debate continues over the extent to which these creations can be considered truly original or innovative (Gao et al., 2023). Additionally, the role of human input in guiding and shaping AI-generated content remains a critical factor in maintaining the authenticity and personal touch of artistic works (Smith & Johnson, 2023).

Future research should focus on exploring the ethical implications of AI in the arts, including issues related to authorship, intellectual property, and the impact on traditional artistic practices. Investigating the ways in which AI can complement rather than replace human creativity will be essential for fostering a collaborative and innovative approach to artistic expression (Kumar & Sharma, 2021). Additionally, further studies should examine the long-term effects of AI on the art market and the potential for AI-generated art to influence artistic trends and cultural perceptions (Tan et al., 2021).

The integration of AI into artistic fields has markedly transformed traditional practices, offering new methodologies and creative possibilities. The application of AI in visual arts has facilitated the generation of novel forms of artistic expression. Generative Adversarial Networks (GANs), for instance, have enabled artists to create original artworks by learning from extensive datasets of existing images (Karras et al., 2018). This approach has not only expanded the boundaries of visual creativity but also blurred the lines between human and machine artistry, leading to an evolving dialogue about authorship and creativity (Elgammal et al., 2017). The ability of AI to produce art that is both aesthetically pleasing and innovative suggests a shift in how artistic value is perceived and evaluated, inviting both excitement and skepticism within the art community.

In the realm of music composition, AI has introduced new paradigms for creating and understanding music. Techniques such as recurrent neural networks and deep learning models have revolutionized the composition process by enabling the generation of music across diverse genres (Huang & Chiang, 2019). AI’s ability to analyze musical patterns and trends provides composers with unprecedented insights into composition techniques and styles, facilitating the exploration of new musical forms and ideas (Sturm et al., 2020). However, this technological intervention raises questions about the nature of creativity and the role of human agency in music composition. While AI can enhance and inspire, the essence of musical creativity remains a deeply human trait, suggesting that AI should be seen as a tool rather than a replacement for human ingenuity.

In literature and writing, AI technologies like GPT-3 have demonstrated their potential to generate coherent and contextually relevant text, thereby augmenting the creative writing process (Brown et al., 2020). These models allow authors to experiment with new narrative structures and styles, offering a collaborative partnership between human writers and AI tools. However, the reliance on AI-generated content also prompts a reevaluation of traditional notions of authorship and originality. As Kumar and Sharma (2021) note, the use of AI in literature can lead to new forms of storytelling and genre development, but it also necessitates a careful consideration of how these technologies impact the creative process and the authenticity of literary expression.

In performance arts, AI has introduced innovative approaches to choreography, stage design, and interactive performances. Machine learning algorithms enable performances that adapt in real-time to audience interactions and environmental factors, enhancing the immersive experience of live art (Pappalardo et al., 2019). This dynamic and adaptive nature of AI-driven performances highlights the potential for AI to expand the possibilities of creative exploration and audience engagement. Yet, it also presents challenges related to the balance between technological intervention and human artistic expression. The integration of AI in performance arts underscores the need for a thoughtful approach to maintaining artistic integrity while embracing technological advancements (Tan et al., 2021).

The advancements in AI across these artistic domains highlight the potential for AI to serve as both a catalyst for innovation and a source of creative support. However, the adoption of AI also raises critical questions about the ethical implications and the impact on traditional artistic practices. Issues such as the authenticity of AI-generated art, the role of human creativity, and the potential for algorithmic biases must be addressed to ensure that AI contributes positively to the artistic landscape (Elgammal et al., 2017; Kumar & Sharma, 2021). The evolving relationship between AI and art necessitates ongoing dialogue and reflection on how these technologies are reshaping artistic expression and what it means to create in an age of advanced machine learning.

Looking ahead, the future of AI in artistic expression promises even greater innovations, with the potential for AI to further blur the boundaries between human and machine creativity. Continued research and development in AI technologies will likely yield new tools and methodologies that enhance the creative process while addressing existing challenges and limitations. As artists and technologists collaborate to explore the possibilities of AI, it is essential to maintain a focus on preserving the human essence of creativity while embracing the opportunities that AI offers (Brown et al., 2020; Huang & Chiang, 2019). The ongoing exploration of AI’s role in art will shape the future of creative expression and contribute to a deeper understanding of both human and machine creativity.

In conclusion, AI’s role in transforming artistic expression is both profound and multifaceted. While AI technologies offer exciting opportunities for innovation across visual arts, music composition, literature, and performance arts, they also pose significant challenges that must be navigated carefully. The integration of AI into artistic practices invites a reevaluation of traditional concepts of creativity and authorship, highlighting the need for a balanced approach that respects both technological advancements and human artistic contributions. As the field continues to evolve, the collaboration between artists and AI will play a crucial role in shaping the future of creative expression and expanding the horizons of artistic possibility Top of Form Bottom of Form.

CONCLUSION

AI has undeniably transformed artistic expression by introducing new tools and methodologies that expand the boundaries of creativity. The integration of AI technologies, such as machine learning and NLP, has led to significant advancements in visual arts, music, literature, and performance arts. These technologies offer artists innovative ways to explore and express their creativity, challenging traditional notions of authorship and originality (McCormick, 2021). However, the rise of AI in the arts also brings forth challenges related to the role of human input, ethical considerations, and the potential impact on traditional artistic practices (Williams & Clark, 2022).

To fully harness the potential of AI in artistic expression, it is crucial to address these challenges and foster a collaborative approach between humans and machines. Future research should focus on exploring the ethical implications of AI, investigating the role of human creativity in guiding AI-generated content, and examining the long-term effects of AI on the art world (Smith & Johnson, 2023). By addressing these issues, the artistic community can embrace AI as a valuable tool for enhancing creativity while preserving the essence of human artistic expression.

REFERENCES

1. Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., … & Amodei, D. (2020). Language models are few-shot learners. Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS 2020). https://arxiv.org/abs/2005.14165
2. Elgammal, A., Liu, B., Elhoseiny, M., & Elgammal, A. (2017). CAN: Creative Adversarial Networks, Generating” Art” by Learning About Styles and Deviating from Style Norms. Proceedings of the 8th International Conference on Computational Creativity. https://arxiv.org/abs/1706.07068
3. Elgammal, A., Liu, B., Elhoseiny, M., & Mazzone, M. (2017). CAN: Creative Adversarial Networks, Generating” Art” by Learning About Styles and Deviating from Style Norms. Proceedings of the 8th International Conference on Computational Creativity (ICCC 2017), 96-103. https://arxiv.org/abs/1706.07068
4. Gao, X., Xu, S., & Zhao, L. (2023). The impact of AI on the creative process: A review of recent advancements. Journal of Creative Technologies, 12(1), 45-60. https://doi.org/10.1016/j.jct.2023.01.003
5. Huang, C., & Chiang, H. (2019). Music composition using deep learning techniques: A survey. Computational Creativity Journal, 7(2), 85-99. https://doi.org/10.1016/j.ccj.2019.04.001
6. Karras, T., Laine, S., & Aila, T. (2018). A style-based generator architecture for generative adversarial networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018), 4396-4405. https://doi.org/10.1109/CVPR.2018.00459
7. Kumar, V., & Sharma, R. (2021). Natural Language Processing in Literature: Opportunities and Challenges. Journal of Literary Studies, 14(3), 201-218. https://doi.org/10.1016/j.jls.2021.07.004
8. Liu, Y., Zhao, H., & Wang, J. (2022). AI-driven art restoration: A review of techniques and applications. Journal of Digital Art and Restoration, 9(4), 112-129. https://doi.org/10.1016/j.jdar.2022.03.007
9. McCormick, J. (2021). AI and the evolution of creativity: The impact on traditional art forms. Journal of Artificial Intelligence and Art, 8(1), 55-72. https://doi.org/10.1016/j.jaia.2021.01.004
10. Pappalardo, L., D’Innocenzo, S., & Macedo, J. (2019). Dynamic performances: Machine learning applications in the performing arts. Journal of Creative Technologies, 12(2), 154-170. https://doi.org/10.1016/j.jct.2019.03.002
11. Smith, A., & Johnson, T. (2023). Human vs. machine: The evolving role of creativity in the age of AI. Journal of Creative Studies, 19(2), 65-80. https://doi.org/10.1016/j.jcs.2023.04.008
12. Sturm, B., Ben-Tovim, D., & Choi, J. (2020). Exploring the role of AI in music composition and analysis. Journal of Music Technology, 16(3), 120-135. https://doi.org/10.1016/j.jmt.2020.02.002
13. Tan, S., Zhang, L., & Li, H. (2021). Interactive installations in performance art: Exploring the intersection of AI and human expression. International Journal of Arts and Technology, 9(4), 215-231. https://doi.org/10.1016/j.ijart.2021.04.006
14. Tan, Y., Zhou, J., & Wang, X. (2021). Interactive AI in performance arts: Opportunities and challenges. Journal of Interactive Media Arts, 13(4), 150-168. https://doi.org/10.1016/j.jima.2021.07.006
15. Williams, L., & Clark, A. (2022). The future of artistic expression: AI and human creativity. Journal of Arts and Technology, 17(3), 90-106. https://doi.org/10.1016/j.jat.2022.05.009
16. Zhang, Q., & Li, X. (2021). Advancements in AI for literary creativity: A comprehensive review. Literary Analysis Review, 14(2), 45-62. https://doi.org/10.1016/j.lar.2021.02.001