Loading...

Table of Content

    28 March 2025, Volume 5 Issue 1

    Humanistic AI: Towards a New Field of Interdisciplinary Expertise and Research

    Mats Fridlund, David Alfter, Ashely Green, Aram Karimi, Cecilia Lindhé, Trans. Hu Yiyi
    2025, 5(1):  3-10. 
    Asbtract ( 27 )   PDF (951KB) ( 5 )  
    Related Articles | Metrics

    The Gothenburg Research Infrastructure in Digital Humanities (GRlDH) have participated in projects within various humanities fields that utilise as well as develop research tools and infrastructural resources that incorporate applications of ‘artificial intelligence’(Al). These applications can include natural language processing, machine learning, computer vision, large language models, image recognition algorithms, classification, clustering, and deep learning. This paper advances the term ‘humanistic Al’ to describe an emergent form of interdisciplinary practice that uses and develops Al-based research applications to answer humanities research questions together with its entangled humanistic reflection. We coin this term to make implicit and visible the epistemological and material particularities of its practice and the new forms of knowledge its affordances make possible. The paper presents GRlDH projects within ‘humanistic Al’ together with its developed Al resources and applications.

    "Integration of Arts and Sciences: Digital Humanities in the Age of AGI”—A Review of the 6th China Digital Humanities Annual Conference (CDH2024)

    LiJiayi, LiXiang, Ma Xiaoke, HuHaotian, Wang Lihua
    2025, 5(1):  11-29. 
    Asbtract ( 21 )   PDF (2293KB) ( 35 )  
    Related Articles | Metrics

    This article systematically reviews and summarizes the proceedings of the academic symposium “Integration of Humanities and Digital Technology: Digital Humanities in the AGI Era” and the 6th China Digital Humanities Annual Conference(CDH2024). It provides an overview of the conference through its keynote speeches, roundtable forums, parallel sessions, press conference, and award—winning projects. By revisiting the core discussions and innovations presented at the2024 conference, this review highlights the current developments and emerging trends in Digital Humanities, while offering critical insights and practical references for researchers and practitioners in related fields.

    From Manual to AI: Exploring History and Humanities in the Age of Artificial Intelligence-Workshop Summary

    Tang Jiajun, Jin Bowen
    2025, 5(1):  30-37. 
    Asbtract ( 18 )   PDF (1115KB) ( 29 )  
    Related Articles | Metrics

    From January11 to12, 2025, the academic workshop "From Artificial to Intelligent-Historical and Humanistic Exploration in the AI Era" organized by the School of History and the Digital Intelligence Documentation Laboratory of Digital History Research Center of Nanjing University was held in Nanjing. From the theoretical basis and methodological innovation of digital history to the construction of databases, artificial intelligence-assisted translation and intelligent knowledge bases, to the discussion of the subjectivity of historical researchers in the era of artificial intelligence, the content of the conference not only presented the cutting-edge practice of technology-enabled historical research, but also further deepened the understanding of the transformation of the production mode of historical knowledge.

    Preserving Original Digital Cultural Heritage: Applications and Challenges of Computational Methods in Digital Game Research

    Adrian Demleitner, Eugen Pfister, Tobias Hodel, Fan Tao
    2025, 5(1):  38-53. 
    Asbtract ( 19 )   PDF (3182KB) ( 16 )  
    Related Articles | Metrics

    How can video game studies and digital humanities mutually enrich the study of digital-born cultural artifacts? This paper presents findings from Confoederatio Ludens, a research project exploring Swiss video game culture from 1968 until 2000 through interdisciplinary methodologies. By applying computational approaches such as distant viewing of visual corpora, critical source code analysis, and metadata modeling among others, we reveal previously overlooked aspects of Switzerland's video game history, such as local adaptations of global gaming trends and the distinctive technological practices of Swiss developers. Furthermore, our project demonstrates how concepts of locality and regional history contribute critically to digital humanities scholarship, challenging established narratives dominated by U.S.-and Japan-centric histories. Reflecting on our initial findings, we discuss both methodological challenges and opportunities emerging from the intersection of these two fields, emphasizing the importance of preservation, computational analysis, and local historical inquiry. Ultimately, our approach highlights the value of interdisciplinary methods for understanding digital artifacts not just as technological objects, but as culturally embedded historical sources.

    Making Use of Digital Data to Build a Research Platform: Developing "Digital Tale of Genji”  by Cooperation of Researchers and Library Staff
    Nakamura Misa, Kigoshi MiChi, Ogawa Kayoko, Trans. Wang Zirui
    2025, 5(1):  54-75. 
    Asbtract ( 94 )   PDF (14455KB) ( 18 )  
    Related Articles | Metrics

    The University of Tokyo Library, prompted by the digitization of its collection of The Tale of Genji manuscripts, organized study sessions involving researchers from various disciplines and library staff to explore the utilization of digital data centered around The Tale of Genji. As a result, the website Digital Tale of Genji was launched with the aim of creating a platform for textual research on The Tale of Genji. This paper discusses the background leading to the organization of these study sessions, the development and functional expansion of the Digital Tale of Genji platform, and the significance of collaboration between researchers and library staff in this initiative.

    Construction and Application of A Two-Stage Embroidery Pattern Automatic Recognition and Segmentation Model for Digital Humanities

    Bao Yalin
    2025, 5(1):  76-96. 
    Asbtract ( 19 )   PDF (66128KB) ( 7 )  
    Related Articles | Metrics

    Image segmentation methods have been used in the field of recognition and segmentation of traditional embroidery patterns. However, due to the characteristics of complex edges, cumbersome details and diverse types of embroidery patterns, traditional image segmentation methods are difficult to meet the requirements of high precision and high efficiency in practical applications. So, this paper presents a dual-stage embroidery pattern recognition and segmentation method based on a YOLO and U-Net cascade. In the first stage, the YOLO algorithm is employed for object detection, quickly and accurately locating the embroidery patterns within the image. In the second stage, an enhanced U-Net algorithm is used for semantic segmentation. The U-Net encoder structure is improved by incorporating a ResBlock-CBAM module as the backbone, enhancing the effectiveness of feature extraction, and integrating an ASPP module for feature enhancement to ensure effective extraction and fusion of various features. This dual-stage cascade network captures the fine details and contextual information of embroidery images, enabling precise segmentation that preserves complex edges and details. The experimental results show that the algorithm in this study reaches 0.8584 and 0.8376 in the evaluation indicators such as Dice and MioU, respectively, and the accuracy rate reaches 84.53%, which is significantly better than other advanced segmentation algorithms. At the same time, this paper establishes an "embroidery intelligent recognition and segmentation" system to achieve efficient and automatic extraction and processing of embroidery patterns. This method not only provides technical support for the digital preservation and transmission of embroidery patterns, but also paves the way for the modernization and customization of embroidery design.

    A Study on Wuzhi Xuanbu of Fujian in the Perspective of  Digital Humanities: Based on DocuSky Metadata Attachment Tool
    Zhou Yuxiang
    2025, 5(1):  97-113. 
    Asbtract ( 19 )   PDF (2780KB) ( 13 )  
    Related Articles | Metrics
    Previous research on military officers of the Wei-so in Fujian during the Ming dynasty lack comprehensiveness.Utilizing the DocuSky Metadata Attachment Tool, researchers can transform pure text historical materials into metadata.This study reveals that military deployment was frequent during the Hongwu and Yongle eras, resulting a higher number of southern officers compared to their northern counterparts within the Wei-so in Fujian. Southern military officials were predominantly founding heroes of the Ming dynasty, while those from the north often rose to prominence due to the Jingnan Campaign, occupying higher military positions within the garrisons. Furthermore, most of Fujian garrison officials were camp followers and submitters, while drafted soldiers were not the main part.Given Fujian's strategic location along the southeast coast, its garrisons primarily concentrated on anti-piracy and defense operations, leading to heavy military service and limited promotion opportunities for local officials.The application of the DocuSky introduces innovative tools for studying of the “partial resume” of garrison officials, thereby enriching research on Wuzhi Xuanbu.
    Towards Digital Accessibility: Concepts, Standards and Pathways
    Huang Wenhan, LiuChenxi, CaiZhuoxi, Zheng Jiaqi, Zhang Zhejun
    2025, 5(1):  114-128. 
    Asbtract ( 16 )   PDF (2330KB) ( 18 )  
    Related Articles | Metrics

    By exploring the concept of digital accessibility and tracing the evolution of the construction of accessible environments at home and abroad, the study proposes a normative path for safeguarding the rights of persons with disabilities in the digital era. The traditional concept of accessibility construction focuses on specialization and particularization, which corresponds to the risk of forming a relatively closed "data greenhouse" or "digital island". The core of creating digital accessibility lies in deeply embedding “universal design” and “standardized standards” into the construction of accessible environments, thereby breaking away from the shallow logic of information accessibility and enhancing the level of digital humanistic care for people with disabilities. To uphold the constitutional principle of "respecting and safeguarding human rights, " it is essential to make full use of the rapid generative capabilities and precise perceived services of artificial intelligence in the future. Furthermore, it is necessary to prospectively establish legal and technical norms to gradually popularize accessibility options or preset supporting tools in mainstream products and public services, to ultimately realize the comprehensive transformation of information accessibility into digital accessibility.