China and Vietnam share both land and maritime borders, rendering the exchange and cooperation in ethnic arts along these frontiers crucial for their cultural evolution. This significance underscores the importance of organizing and analyzing the artistic expressions of the Zhuang people, particularly the “Tien Jumping” art form prevalent along the Sino-Vietnamese border. This study introduces an innovative method for text feature expansion utilizing Citespace, integrated with a deep learning-based text classification model, to establish a systematic framework for text classification within this cultural context. Furthermore, acknowledging the multidisciplinary nature of “Tien Jumping” art research, this paper develops a Citespace-based cross-collection system. This system harnesses a thematic network that amalgamates various disciplines to aggregate pertinent data efficiently. Empirical analysis validates the model’s robustness, evidencing an accuracy of 0.95, a recall of 0.87, and an F1 score of 0.91. The investigation into the current state and future trends of “Tien Jumping” research reveals a significant increase in publication volume, from 500 articles in 2013 to 1,108 in 2022— an increment of 608 articles. This growth highlights the strengthening focus on inheritance development, cultural preservation, and the artistry of the Zhuang people, with scores surpassing 7.5 in these emergent research areas. These findings affirm the effectiveness of the proposed methodologies in this study. The approach not only provides a rigorous analysis but also forecasts the trajectory of “Tien Jumping” art research along the Sino-Vietnamese border, offering a scientific foundation for future scholarly inquiries.