ShodhKosh: Journal of Visual and Performing Arts

SPECIAL ISSUE ON AI-DRIVEN CREATIVITY AND INTELLIGENT PRACTICES IN VISUAL ARTS

Dr. Krishna Sankar Kusuma — Thu, 25 Dec 2025 00:00:00 +0000

It is with great pleasure that we present this special issue of ShodhKosh: Journal of Visual and Performing Arts titled “AI-Driven Creativity and Intelligent Practices in Visual Arts.” As artificial intelligence and intelligent design systems increasingly shape contemporary artistic practice, visual arts are evolving into data-driven, interactive, and computational processes. The contributions in this issue examine how AI influences artistic creation, pedagogy, curation, and creative management. Reflecting interdisciplinary perspectives from visual arts, computational intelligence, emotion analytics, and education technology, this special issue documents and critically evaluates emerging paradigms, offering scholars and practitioners an academic platform to explore innovation in creative practice.

Issue Editor:

Dr. Krishna Sankar Kusuma
Professor, AJK Mass Communication Research Centre, Jamia Millia Islamia, New Dehli, India
Email: kusumakk@gmail.com

Dr. Naresh Kshetri
Assistant Professor (Cybersecurity), Department of Math, CS & IT, Lindenwood University, USA
Email: kshetrinaresh@gmail.com

Dr. Gabriel Kabanda
Adjunct Professor of Machine Learning, Woxsen University, Hyderabad, India
Email: gabrielkabanda@gmail.com

Stephen Olatunde Olabiyisi
Professor, Department of Computer Science Ladoke Akintola University of Technology Ogbomoso, Nigeria
Email: tundeolabiyisi@gmail.com

Dr. Dipti Chauhan
Professor & Head in the Department of Artificial Intelligence & Data Science, Prestige Institute of Engineering Management & Research, Indore, M.P., India
Email: diptichauhan09@gmail.com

CULTURAL STYLE TRANSFER USING DEEP LEARNING FOR DIGITAL ILLUSTRATION AND VISUAL STORYTELLING

Thu, 25 Dec 2025 00:00:00 +0000

The paper explores how cultural style is transferred with the help of deep learning as a computational method in digital illustration and visual narration. Whereas neural style transfer has shown effectiveness in reproducing the visual qualities of painterly images, models currently do not pay much attention to the richer cultural semantics and symbolic motifs, as well as narrative coherence of traditional and modern works of art. The proposed structure fills this gap by considering culturally annotated visual features, semantic and contextual modeling to allow style transfer to be culturally informed. A wide range of works of art and digital images that represent various cultural traditions are organized and annotated in a systematic way with motifs, symbolic patterns, semantics of colors and narrative qualities. Convolutional and transformer based architectures are used to separate content, style, and cultural symbolism and attention mechanisms are used to control preservation of motifs and alignment of stories to the transferred text. Visual fidelity, cultural consistency and storytelling coherence are tested by experimental analysis through the application of both quantitative and expert-based qualitative measures. Findings show that more culturally significant aspects are preserved, there is greater narrative continuity and the style is not so ambiguous as with traditional neural style transfer baselines. The frame work favors the uses of digital illustration, concept art, animation, graphic narrative, and educational media and allows artists and designers to produce culturally expressive images without having to hand render the styles.

AI-DRIVEN AESTHETIC EVALUATION IN FINE ARTS: A MACHINE LEARNING APPROACH TO STYLE CLASSIFICATION

Thu, 25 Dec 2025 00:00:00 +0000

In the past, people with a lot of experience judged the beauty of fine arts by looking at them in the context of their deep cultural, political, and academic backgrounds. Now that artificial intelligence (AI) and machine learning (ML) are getting better, computers can better analyze and group artworks, making it possible to evaluate art in a way that is both scalable and objective. This study suggests a system for classifying styles in fine arts that is based on machine learning and combines both hand-made visual descriptions and deep learning-based feature extraction methods. The study uses a variety of datasets, such as WikiArt, Kaggle art collections, and selected museum records, to make sure that all types and movements of art are covered. To improve the quality of a dataset and lower its noise, preprocessing steps like colour normalization, cutting, and data addition are used. Feature extraction mixes common techniques like colour histograms, edge recognition, and texture analysis with deep features gathered from CNNs like VGGNet, ResNet, and EfficientNet that have already been trained. Transfer learning is used to make models fit the unique features of fine art images, which leads to better classification performance across a wide range of artistic fields. According to the results of experiments, hybrid feature fusion is much better at classifying things than single-method. It also gives us useful information about the visual elements that define different art styles. The suggested method can be used in systems for verifying, collecting, and suggesting art. It fills the gap between computer analysis and human-centered aesthetic judgement. This paper shows how AI could be used to help professional art critics do their jobs better, leading to progress in both computer vision and the fine arts.

AI-POWERED ANALYSIS OF BRAND-CONSUMER ENGAGEMENT IN THE DIGITAL ERA: INSIGHTS FROM INDIAN MILLENNIALS

Tanushree Sharma, Shilpi Jha — Thu, 25 Dec 2025 00:00:00 +0000

Brand-consumer interaction has changed into a dynamic and data-driven process in the fast-changing digital era. This is especially true for Indian millennials, who are tech-savvy and use social media a lot. Their brand loyalty habits are also changing. This research investigates how Artificial Intelligence (AI) can help us understand and predict how brand-consumer interaction trends will change in this group. The study uses a mixed-method research approach that combines social media analytics, polls, and data on how people connect with brands to get both numeric and qualitative information about involvement and behaviour. To look at big datasets, AI-powered methods are used. These include natural language processing (NLP) for figuring out how people feel about something, machine learning algorithms for guessing how engaged people will be, and grouping models for dividing people into groups based on their behaviour. The results show clear patterns of interaction that are affected by culture connection, content personalization, and brand trustworthiness. Personalized marketing strategies that use AI to create profiles of consumers lead to a big rise in involvement and brand loyalty, especially when they are tuned to people's language tastes and living goals. Predictive models also show that real-time mood tracking lets brands change their campaigns on the fly, which makes customers happier and more loyal over time. The results have important implications for marketers who want to improve their digital efforts. They highlight the importance of AI in revealing complex customer behaviour and making hyper-personalized interaction strategies possible. This study adds to the growing amount of research on AI in marketing by looking at how to connect young consumers in India. It does this by closing the gap between using technology and communicating with brands in a way that is culturally relevant.

SPECIAL ISSUE ON INTELLIGENT EVALUATION EMOTION ANALYTICS AND AI-BASED ASSESSMENT IN DIGITAL ART

Saurabh Bhattacharya — Sat, 20 Dec 2025 00:00:00 +0000

It is with great pleasure that we present this special issue of ShodhKosh: Journal of Visual and Performing Arts, titled “Intelligent Evaluation, Emotion Analytics, and AI-Based Assessment in Digital Art.” This special issue responds to a critical and timely need within contemporary creative practice and education, where digital art has evolved beyond static visual expression into an intelligent, data-driven, and emotionally responsive domain.
With the integration of Artificial Intelligence, digital artworks today function as interactive systems capable of adaptation, interpretation, and emotional engagement. While such advancements have expanded the expressive and pedagogical possibilities of digital art, they have also introduced complex challenges related to evaluation, assessment, and interpretation of creativity and emotional impact. Traditional evaluative frameworks often fall short in addressing the multidimensional, subjective, and experiential nature of digital creativity.
Recent developments in emotion analytics, affective computing, machine learning, and intelligent assessment systems offer promising pathways to address these challenges. AI-based models now enable the analysis of visual features, emotional responses, interaction patterns, and contextual data, allowing for more objective, scalable, and reproducible approaches to evaluating digital art and creative performance. These technologies also hold transformative potential for art education, supporting automated feedback, learning analytics, and fair assessment mechanisms.
The papers selected for this special issue reflect a rich interdisciplinary dialogue bridging technology, visual culture, psychology, pedagogy, and creative practice. Contributions explore intelligent evaluation models for digital art, AI-driven creativity assessment frameworks, deep learning approaches to aesthetic quality measurement, emotion recognition in visual and interactive art, and multimodal emotion analysis using image, video, and interaction data. Several studies also address automated grading systems, feedback generation, and data-driven evaluation strategies within digital art education environments.
This special issue welcomes both theoretical insights and applied research, highlighting how intelligent systems can support meaningful evaluation without undermining artistic subjectivity. A recurring theme across the contributions is the importance of ethical responsibility, interpretability, and human-centered design in AI-based assessment systems, ensuring that technological advancement complements rather than constrains creative expression.
P4C1T1#y6
P4C1T1#y5
P4C1T1#y4
P4CT#y3
P4CT#y
P4CT#y
ShodhKosh: Journal of Visual and Performing Arts 2
The call for papers attracted a diverse range of submissions from researchers, educators, technologists, and practitioners working at the intersection of art and artificial intelligence. All manuscripts underwent a rigorous peer-review process to maintain the scholarly standards of ShodhKosh. The resulting collection represents a curated body of work that advances current understanding while opening new avenues for research and pedagogical innovation.
We express our sincere gratitude to all authors for their valuable contributions, to the reviewers for their critical insights, and to Granthaalayah Publications for their continued support in promoting interdisciplinary research in the visual and performing arts. Their commitment has been instrumental in bringing this special issue to fruition.
We hope this volume will stimulate thoughtful discussion, inspire future research, and contribute meaningfully to the evolving discourse on intelligent evaluation and emotional analytics in digital art. May it serve as a resource for scholars and practitioners seeking to navigate the complex relationship between creativity, emotion, and artificial intelligence.

Issue Editor:

Dr. Saurabh Bhattacharya
Assistant Professor, School of Computer Science & Engineering, Galgotias University, Greater Noida, UP, India
Email: babu.saurabh@gmail.com

Anuj Kumar
Assistant Professor, Department of Hindi, Nagaland Univeristy, Kohima Campus, Meriema, Nagaland, India
Email: anujkumarg@gmail.com

Prof Dr Shreyas Dingankar
Institute of Management and Entrepreneurship Development, Bharati vidyapeeth Deemed to be university, Pune, India
Email: shreyas.dingankar@bharatividyapeeth.edu

Dr. Pastor R. Arguelles Jr.
Director, Research and Publication Office, University of Batangas Lipa City, Philippines
Email: pastor.arguelles@ub.edu.ph

M. Rajendra Nath Babu
Associate Professor, Department of Education, Nagaland University, Kohima Campus, Meriema, Kohima (dt.), Nagaland, India
Email: mrnb.svu@gmail.com

Dr. Indrani Hazarika
Department of Business and Specialization Accounting, Higher Colleges of Technology, United Arab Emirates
Email: ihazarika@hct.ac.ae

GANS FOR MUSICAL STYLE TRANSFER AND LEARNING

Thu, 25 Dec 2025 00:00:00 +0000

Generative Adversarial Networks (GANs) are considered to be disruptive models of computational creativity, especially in music style transfer and learning. This study examines how GAN architecture may be incorporated in translating pieces of music between different stylistic domains without compromising their time and harmonious integrity. The conventional approaches including Autoencoders, RNNs, and Variational Autoencoders (VAEs) have shown a low success rate in the fine-grained representations of music which has led to the adoption of GANs due to their better generative realism. The suggested model uses Conditional GANs and CycleGANs, which allows supervised and unpaired learning with various musical data. The data normalization and preprocessing is done using feature extraction methods that are Mel-frequency cepstral coefficient (MFCCs), chroma features, and spectral contrast. The architecture focuses on balanced loss optimization between the discriminator and the generator and makes sure that there is convergence stability and audio fidelity. The results of experimental analysis show significant enhancement of melody preservation, timbre adaptation, and rhythmic consistency of genres. Moreover, the paper describes the use in AI-assisted composition, intelligent sound design, and interactive music education systems. These results highlight the value of GANs as creative processes, as well as educational instruments, enabling real-time modification of the style and music specifically synthesized to the user. The study, with its developed methodology of learning musical style using GAN and cross-domain adaptation, adds to an area of investigation of machine learning, cognition of music and digital creativity, which is being recently reshaped.

MANAGING MUSIC CURRICULUM WITH PREDICTIVE ANALYTICS

Thu, 25 Dec 2025 00:00:00 +0000

The given research provides a data-driven model of improving music education based on predictive modeling and learner analytics. Music programs based on traditional curriculum management are mostly subjective-based and lack flexibility to accommodate the needs of different learners due to their fixed progression. Three predictive algorithms Multiple Linear Regression (MLR), Random Forest (RF), and Long Short-Term Memory (LSTM) networks were used to predict performance, engagement, and creative development of students to increase accuracy and response rates. The data used in experimental assessment with 620 music learners in six institutions found that LSTM was the highest predicted accuracy of 94.6, better than RF (89.3) and MLR (83.7). In addition, the efficiency of curriculum adaptation increased by 28 percent and the general student engagement was increased by 32 percent as compared to the manual approaches to planning. The most important predictors included such essential features as practice frequency, tonal recognition, rhythmic precision, and ensemble collaboration scores. As the comparative analysis shows, predictive analytics can be of great benefit when it comes to designing, evaluating, and personalizing music curricula. With the assistance of ongoing data-feedback and smart prediction, teachers will be able to make evidence-based choices, which will enhance creativity, inclusiveness, and quantifiable artistic progress. This paradigm signifies the transition to smart, flexible, and results-focused music education paradigms.

CHATGPT AS A CO-TEACHER IN ART EDUCATION

Thu, 25 Dec 2025 00:00:00 +0000

The fast pace of integrating artificial intelligence in the educational setting has created new learning possibilities especially in creative subjects like art education. In this paper, it is suggested to consider ChatGPT as a Co-Teacher to demonstrate how generating AI may aid instructional procedures, increase student engagement, and facilitate differentiated learning opportunities. Being a smart assistant, ChatGPT aids in ideation, explanations of techniques, exploration of concepts and formative critique, hence replacing human art educators, rather than consuming them. The paper reviews the abilities of ChatGPT in a variety of creative settings, including painting, digital illustration, printmaking, 3D modeling, sculpting, and art history, and how AI-guided prompts, descriptions, and judgments can support the creative efforts of students and broaden their visual thinking. An organized Teacher-AI Collaboration Model is provided that describes the workflow of the art lessons that incorporate the points of ChatGPT intervention including: brainstorming, procedural guidance, assessment, and reflective practice. The model illustrates the advantages of the personalized coaching of learners, alternative perspectives, and trial and error through a series of case studies. Meanwhile, the paper touches on the most important issues concerning originality, authorship, and over-trust in algorithmic suggestions. Ethical concerns such as biases in datasets, cultural representation, and human creativity maintenance are taken care of to make the implementation responsible.

MANAGEMENT MODELS FOR DIGITAL ART ACADEMIES

Thu, 25 Dec 2025 00:00:00 +0000

The emergence of digital art academies is a paradigm shift in the organization, management, and delivery of creative education. The present paper explores in-depth management models that would apply to digital and hybrid creative institutions that are a combination of traditional studio pedagogy and AI-powered and data-driven models. The paper starts with an examination of traditional art academy governance and how they are constrained to deal with digitally mediated creative practices. After that, it examines the digitalization of academic organizations, including virtual forms of governance, interdisciplinary cooperation and the use of AI in administrative procedures. Particular focus is given to the pedagogical models in which new technologies are combined: AI, VR/AR, and multimodal learning tools to improve curricula based on creative competencies. The paper also expounds on technological infrastructures that support distributed creative ecosystems including cloud-based learning management systems, digital asset repositories as well as virtual studios. Besides, the human resource aspect is also handled, with innovative hiring, upskilling processes and faculty-industry cooperations. Outside operational management, such issues as sustainability and ethics are crucial, and it is highlighted to offer inclusive, accessible, and eco-friendly creative education. A conclusion has been offered at the end of the paper by suggesting the framework of resilient, adaptive, and ethically justified management systems, which can bring digital art academies on the road to future preparedness. The suggested models do not only redefine the administrative effectiveness, but also enhance the cultural and educational purpose of the digital age art institutions.

HUMAN–COMPUTER INTERACTION MODELS IN ART PEDAGOGY

Thu, 25 Dec 2025 00:00:00 +0000

Incorporation of the Human-Computer Interaction (HCI) models in the art pedagogy has changed the way learners interact with the digital creativity with the focus on the interactive, experiential and multimodal approaches to the artistic education. This paper discusses the role of cognitive and behavioral modeling in the HCI models in improving the digital art learning conditions using adaptive and feedback-based systems. The study is based on the theories of constructivist and experiential learning, investigating how creativity and self-expression can be supported by the direct manipulation interface, immersive platform, and generative AI tools. The methodology is a combination of both qualitative and quantitative data gathered through observations in the classroom, surveys, and interviews with the art educator and students in the use of digital art software and interactive learning systems. The measurement of interaction patterns, engagement rates, and learning outcomes are measured by analytical methods in order to determine the pedagogic importance of interface design and multimodal feedback. The results show that properly developed HCI systems have a positive influence on engagement, experimentation, and increase the confidence of students in their creativity. In addition, multimodal interfaces with visual, auditory, and touch-hearing aspects help to build deeper cognitive associations, which lead to better conceptual knowledge and aesthetic decision-making. The discussion indicates the necessity of adaptive digital tools, inclusive, and contextual, which are compatible with the artistic cognition. This study is part of the new body of art-oriented HCI, which promotes an educational model in which interactivity is the medium of creativity, as well as an agent of learning, and the future of online art education.