❌

普通视图

Received before yesterday1 - DSH（Digital Scholarship in the Humanities）
✇1 - DSH（Digital Scholarship in the Humanities）

A study on the strategies for cross-cultural innovation and development of Hebei folk music from the perspective of ethnomusicology

2025年10月12日 08:00
Abstract
The folk music of Hebei Province is characterized by its long history and rich variety, exerting a profound influence throughout Chinese history. With the development of digitalization and cross-cultural contexts, many traditional cultures have been rejuvenated through digital integration. However, due to the combined effects of environmental, social, and economic factors, it is challenging to devise appropriate strategies to promote the development and inheritance of Hebei folk music in the digital age. This article explores the innovative development of Hebei folk music from the perspective of ethnomusicology. Through field investigations and in-depth qualitative analyses, it identifies current issues, contributions, and challenges. By integrating literature reviews, field surveys, and user interview coding, it outlines the developmental needs and constraints of Hebei folk music. It further proposes a Human-Centered Music Revitalization (HCMR) framework from an ethnomusicological standpoint to guide the innovative development of digital technology and intangible cultural heritage while preserving their unique characteristics.
✇1 - DSH（Digital Scholarship in the Humanities）

On proximity—exploring experiences of bias and discrimination in digital humanities

2025年10月10日 08:00
Abstract
This article explores proximity as a critical feminist methodology in digital humanities, emphasizing its role in addressing bias in digital technologies. Drawing on the insights of Virginia Eubanks and Ruha Benjamin, this article argues that those closest to systemic issues possess essential knowledge for creating equitable solutions and advocates for community-led, inclusive approaches to digital humanities research. Full Stack Feminism in Digital Humanities (FSF) project, a UK–Ireland collaboration that employed proximity as both a methodological and ethical framework, is offered as a case study, and as such, the article draws on an analysis of semi-structured interviews, carried out by Full Stack Feminism. In line with the proximal approach, interviews were conducted with community groups and organizations as well as researchers, academics, artists, coders, activists, and software developers. By centring marginalized voices, the article proposes a proximal approach as a means to counteract digital bias and foster more just digital landscapes. It aligns with bell hooks’ (1989) and Catherine D'Ignazio and Lauren Klein calls for counter-hegemonic practices rooted in the politics of location.
✇1 - DSH（Digital Scholarship in the Humanities）

A statistical reassessment of rongorongo texts I, Gv, and T: implications for genre and content

2025年10月3日 08:00
Abstract
The content of rongorongo texts I (Santiago Staff), Gv (verso of the Small Santiago Tablet), and T (Honolulu Tablet) has been debated, with hypotheses ranging from name lists and genealogies to cosmogonic chants. This study analyses glyph collocations in these texts, focusing on their relationship with sign 76. Segmentation of text I reveals that it can be divided into at least two segments, with the second segment sharing glyphs with short inscriptions on personal adornments, indicating the presence of personal names. Additionally, structural and content similarities between Gv and the Atua-Mata-Riri creation chant suggest a need to reassess Steven Fischer’s hypothesis for this specific text. This reassessment implies that text I may similarly contain lists of parents and offspring but including personal names. Finally, it is emphasized that categorizing these inscriptions as genealogies or cosmogonies is not contradictory, as these genres often intermingle in Polynesia.
✇1 - DSH（Digital Scholarship in the Humanities）

Application of deep learning for symbol detection on historical maps to explore spatiotemporal changes in the regional tea industry of early 20th-century Taiwan

2025年9月28日 08:00
Abstract
Focusing on the early history of the tea industry in Tamsui, Taiwan, this study uses land used data extracted from maps of the 1900s and 1920s to explore the regional characteristics and changes in the distribution of tea plantations. Map symbol detection modeling was performed using Artificial Intelligence deep learning techniques, which have been growing in the field of map research in recent years. Through the constructed symbol detection model, the land use annotation data of historical maps can be automatically retrieved for GIS-based spatiotemporal analysis. Thus, the study presents the impact of global economic panic and the failure of tea exportation in the 1920s on the local tea industry and reflects the tea plantation landscape in response strategies.
✇1 - DSH（Digital Scholarship in the Humanities）

Can AI replace experts in the evaluation of cultural heritage? Based on the controlled experiments conducted on six architectural heritages

2025年9月28日 08:00
Abstract
This study investigates the potential of artificial intelligence (AI) to replace human experts in evaluating the conservation status of architectural heritage. Five mainstream AI models were employed to assess six architectural heritage sites in Kunming, Yunnan, China, using 18 evaluation indicators. The AI Evaluation Team (AET) and Expert Evaluation Team (EET) conducted comprehensive assessments, and the results were compared using the entropy weight method (EWM), independent sample t-tests, and kernel density estimations. The findings revealed no significant differences between the AET and EET outcomes, demonstrating that the AI’s assessment capability reached expert-level performance. Moreover, AI exhibits higher efficiency in information acquisition and work processes than human expertise. The objectivity of the AI-generated results was enhanced by the data-driven approach and the use of the EWM for indicator weighting. This study highlights the potential of AI in architectural heritage preservation, enabling the assessment of a larger number of heritage buildings within a shorter timeframe and overcoming the limitations of manual evaluation. The proposed method can be extended to assess various types of cultural heritage and predict future trends, providing a more efficient basis for heritage protection.
✇1 - DSH（Digital Scholarship in the Humanities）

Quantifying the faithfulness of poetry translations in four closely related Slavic languages

2025年9月25日 08:00
Abstract
Translating poetry is notoriously difficult—some would claim impossible—because it inherently requires making triage decisions what to preserve and what to sacrifice if necessary. Both form and meaning contribute to the esthetic effects of the original, but translations that faithfully preserve the metrical versification principles of the original might struggle to fully preserve lexically conveyed meanings and connotations, and vice versa. Other esthetically relevant sound-related features (e.g. phonemic patterns) are particularly challenging to preserve. This paper presents a pilot study to empirically test this intuition by assessing the faithfulness of translations to their original. Quantifying aspects of the beauty of sound and meaning, that is, the sonority and the esthetic affective potential, of selected poems and their translations in/from Russian, Polish, Czech, and Slovak, that is, a sample controlled for linguistic and cultural context, we measure the degree to which translations correspond to their originals along these dimensions. The results suggest that, for the poems and languages considered, the beauty of sound and meaning are preserved to varying degrees, which can be sensibly interpreted against specific features of the poems, linguistic distances, and cultural prestige. The study thus serves as a proof of concept that demonstrates the basic feasibility of the method applied and foreshadows its potential for advancing empirical studies in the field of comparative poetics.
✇1 - DSH（Digital Scholarship in the Humanities）

Growing and pruning the archive: an agent-based model to build letter correspondence networks

2025年9月22日 08:00
Abstract
The selection and availability bias concerning digital archives can be a problem for empirical studies. In the context of historical correspondence networks, we still have limited information about how missing data can affect and hinder the variables of our interest. Along these lines, we introduce an agent-based model to reconstruct historical communication using letters. We use this model to simulate the letter-sending process and its subsequent archival. We use it to build counterfactual networks and learn how the missing data caused by the archival of the letters might bias the network statistics.
✇1 - DSH（Digital Scholarship in the Humanities）

Natural language processing as Digital Veda (डिजिटल वेद): a humanistic framework for language, ethics, and AI

2025年9月20日 08:00
Abstract
This article conceptualizes Natural Language Processing (NLP) as the Digital Veda (डिजिटल वेद), framing it as a culturally rooted communicative infrastructure inspired by the Vedic tradition of structured knowledge preservation and ethical discourse. Drawing on India’s linguistic and philosophical heritage, it positions NLP not as a neutral tool, but as an evolving ecosystem shaped by human values, language ideologies, and socio-cultural narratives. By mapping the four Vedas to key NLP domains, Rigveda (language modelling), Yajurveda (syntax and pipelines), Samaveda (phonetics and speech), and Atharvaveda (applied AI), the study illustrates how contemporary language technologies mirror ancient systems of meaning-making. It offers a critical, decolonial lens on mainstream NLP, highlighting digital language hierarchies, the marginalization of low-resource Indian languages, and biases embedded in large language model (LLM) training data. The article further proposes a Vedic-inspired ethical AI framework, grounded in the principles of Dharma (righteous design), Ahimsa (non-harm), and Moksha (AI for truth and well-being). This interdisciplinary perspective contributes to a more inclusive, context-aware vision for language technologies, with practical applications in multilingual NLP, bias mitigation, and ethically aligned AI governance. It is particularly relevant for AI ethicists, digital humanists, NLP researchers, and policymakers committed to culturally informed, responsible innovation.
✇1 - DSH（Digital Scholarship in the Humanities）

Iconicity in large language models

2025年9月18日 08:00
Abstract
Lexical iconicity, a direct relation between a word’s meaning and its form, is an important aspect of every natural language, most commonly manifesting through sound-meaning associations. Since Large language models’ (LLMs’) access to both meaning and sound of text is only mediated (meaning through textual context, sound through written representation, further complicated by tokenization), we might expect that the encoding of iconicity in LLMs would be either insufficient or significantly different from human processing. This study addresses this hypothesis by having GPT-4 generate highly iconic pseudowords in artificial languages. To verify that these words actually carry iconicity, we had their meanings guessed by Czech and German participants (n = 672) and subsequently by LLM-based participants (generated by GPT-4 and Claude 3.5 Sonnet). The results revealed that humans can guess the meanings of pseudowords in the generated iconic language more accurately than words in distant natural languages and that LLM-based participants are even more successful than humans in this task. This core finding is accompanied by several additional analyses concerning the universality of the generated language and the cues that both human and LLM-based participants utilize.
✇1 - DSH（Digital Scholarship in the Humanities）

On audiences’ feelings and needs of Hero: a digital-intelligent humanities perspective

2025年9月15日 08:00
Abstract
Audiences’ reviews are critical to the reception study of movies. This article takes the reviews of Hero as an example, and analyzes the reception effect from a digital-intelligent humanities perspective with transformer-based models, especially bidirectional encoder representations from transformers (BERT)-based sentiment analysis and BERTopic modeling, which are generally regarded as the state-of-the-art deep learning models. The results of sentiment analysis show that positive comments of Hero account for 74.42 per cent, while the proportion of negative comments is 25.58 per cent. Besides, the Maslow’s hierarchy of needs theory is employed to further reveal the actual feelings and needs of audiences, including physiological needs (visual and auditory needs), safety needs, social needs (discussion on plots and cultural sharing), esteem needs (themes and emotional expressions), and self-actualization needs (cultural participation, aesthetics, and knowledge extension).
✇1 - DSH（Digital Scholarship in the Humanities）

Synergizing structure and semantics: a knowledge graph-transformer framework for narrator disambiguation in hadith networks

2025年9月13日 08:00
Abstract
Historical transmission chains (isnads) are fundamental to verifying authenticity in Hadith literature, yet narrator identity resolution is a persistent challenge due to onomastic ambiguity and complex naming conventions. While traditional methods lack scalability and modern language models overlook crucial network structures, this study bridges the gap by synergizing structural and semantic information. We introduce a novel hybrid framework that integrates a Knowledge Graph (KG) representing the narrator network topology with a Transformer-based model for deep contextual understanding. Our approach first leverages the KG to generate a high-probability set of candidate identities, then employs a hybrid scoring model to evaluate them based on both global network prominence and local semantic compatibility. Evaluated on the AR-Sanad 280K-v2 benchmark, our method establishes a new state-of-the-art, achieving 97.8% accuracy and significantly outperforming existing baselines. This work provides a scalable, high-fidelity solution for narrator disambiguation, advancing computational methods in Hadith studies and historical identity resolution.
✇1 - DSH（Digital Scholarship in the Humanities）

Research on the authorship identification of The Tale of Genji based on quantitative analysis

2025年9月13日 08:00
Abstract
Numerous scholarly contributions have enriched our understanding of The Tale of Genji; however, the question of its authorship remains a subject of debate, with no definitive resolution to date. This study addresses this controversy by employing a rigorous quantitative statistical approach. We conducted a comprehensive analysis of various linguistic indicators within The Tale of Genji, encompassing aspects such as distribution of part-of-speech, function words, word length, N-Grams, and sentence-segments. These characteristic parameters were subsequently utilized to perform principal component analysis, perform non-parametric tests, calculate relative entropy, and assess relative distances. The findings of this analysis reveal a remarkable consistency in writing style between Chapters 43–54 and the preceding Chapters 1–42 of The Tale of Genji. Consequently, the quantitative statistical examination presented in this study provides robust evidence to support the conclusion that a single authorship underlies the entire text of The Tale of Genji, refuting the hypothesis of a second author.
✇1 - DSH（Digital Scholarship in the Humanities）

AIGC empowers the sustainable development of traditional Chinese paper-cut

2025年9月13日 08:00
Abstract
This research aims to explore the application of artificial intelligence-generated content (AIGC) technology in traditional Chinese paper-cut design and promote the protection and inheritance of traditional Chinese paper-cut culture. First, the paper-cut works of paper-cut artist are analyzed to extract the characteristic factors of her design styles. Second, based on the characteristics of the paper-cut style, a dedicated dataset for model training is constructed and passed into the fine-tuning network to train and generate a Low-Rank Adaptation (LoRA) fine-tuning model with the design style characteristics of the paper-cut artists. Finally, the paper-cut LoRA model is combined with the stable diffusion model to complete the intelligent design practice of traditional paper-cut. Through experimental verification, the paper-cut model trained in this research can effectively realize the migration design of traditional paper-cut artists’ design style and improve the efficiency of paper-cut design. This research proposes a paper-cut style generation method based on AIGC, which provides a new perspective for the protection and development of paper-cut culture. This method reduces the difficulty of paper-cut design, optimizes the design process, and improves design efficiency, providing technical support for the sustainable development of paper-cut art. At the same time, it also has important significance and value for the digital inheritance and innovation of other intangible cultural heritage.
✇1 - DSH（Digital Scholarship in the Humanities）

Text mining Nahdawi discourses: topic modeling Taha Hussein’s reformist legacy

2025年9月9日 08:00
Abstract
This study re-examines the intellectual, cultural, and literary legacy of Taha Hussein (1889–1973), a pivotal reformist thinker of the Arab Nahda (renaissance or awakening). Integrating computational methods from the digital humanities, specifically topic modeling applied to a 42-work corpus, with traditional close textual analysis, the study uncovers the structural and thematic patterns underpinning Hussein’s discourse on identity, modernization, and cultural reform. The analysis foregrounds on his syncretic humanism, which weaves together Egypt’s Pharaonic, Arab-Islamic, Mediterranean, and European inheritances into a pluralistic national vision. It highlights his critique of essentialist binaries, his advocacy for educational democratization, and his integrative approach to mediation, translation, and nation-building. Situated within the (post)colonial frameworks, the study critically engages debates around Hussein’s perceived Occidentalism while affirming his enduring relevance to contemporary discourses on intellectual sovereignty, cultural revival, and the humanistic foundations of reform. This research contributes to digital humanities by demonstrating the value of topic modeling for mapping the complex intellectual landscape of a major non-Western historical figure across a large corpus. It offers a scalable methodology for revealing latent thematic structures that complement traditional hermeneutic approaches in Arabic and Middle Eastern studies. By bridging digital methodologies with close reading, this study reframes Hussein’s reformism as a dynamic transcultural project that resists reductive polemics and illuminates postcolonial identity formation and the global positioning of Arab thought.
✇1 - DSH（Digital Scholarship in the Humanities）

Crossing boundaries through corpora: innovative corpus approaches within and beyond linguistics. S. Buschfeld, P. Ronan, T. Neumaier, A. Weilinghoff, & L. Westermayer (eds)

2025年8月26日 08:00
Crossing boundaries through corpora: innovative corpus approaches within and beyond linguistics. BuschfeldS., RonanP., NeumaierT., WeilinghoffA., & WestermayerL. (eds), Amsterdam, John Benjamins, 2024, pp. vi + 265, $156.00 (eBook). ISBN 9789027246486.
❌