conduct cross-cultural ethnography

This study addresses the lack of systematic understanding regarding the types and motivations of visual representations in qualitative research. Building upon and extending Verdinelli & Scagnoli’s (2013) work through a data-driven literature review, it conducts a content analysis of articles and their visualizations published between 2020 and 2022 in three leading qualitative methods journals. Integrating epistemological stance classification with visualization-type coding, the study innovatively combines correspondence analysis and cognitive network analysis for the first time. Findings indicate that while visualizations remain underutilized in qualitative research, their typological diversity is increasing, and the choice of graphical representation appears largely independent of the authors’ epistemological positions. These results offer both empirical grounding and methodological innovation for integrating interdisciplinary visualization tools into qualitative inquiry.

A critical gap exists in ethnographic pedagogical resources tailored to graduate students and instructors in software engineering. Method: This study addresses this gap by developing China’s first ethnography teaching framework specifically designed for software engineering contexts, integrating qualitative research methodology, instructional design principles, case-based learning, reflective practice, and course-based action research. The framework comprises methodological exposition, structured instructional modules, scaffolded practical exercises, instructor guidance notes, and a guide to avoiding common pitfalls. Contribution/Results: The framework has been embedded in an empirical software engineering course and rigorously validated through teaching practice, yielding significant improvements in students’ ethnographic literacy and qualitative research competencies. Its key innovation lies in the first systematic localization of ethnographic methodology for software engineering education—filling a discipline-specific pedagogical void and establishing a reusable, transferable instructional paradigm for cultivating qualitative researchers in computing disciplines.

Traditional questionnaires struggle to simultaneously capture qualitative depth and quantitative structure, limiting comprehensive understanding of complex social phenomena. This study proposes a dynamic survey platform powered by large language models (LLMs) that, for the first time, enables real-time semantic clustering of open-ended responses. Through an interactive feedback mechanism, users can rate, rank, and reflect on these clusters, generating visual reports that integrate qualitative insights with quantitative analysis. Innovatively embedding LLMs within a closed-loop data collection framework, the approach facilitates dynamic comparisons between individual perspectives and group-level trends. Empirical validation across two field studies involving 93 participants demonstrates that the platform significantly enhances data richness and user engagement compared to conventional survey tools, while effectively fostering collaborative sensemaking.

The rise of artificial intelligence poses methodological challenges to qualitative social science research (e.g., ethnography, in-depth interviews). This paper advances a pragmatic sociological approach that moves beyond the binary of techno-optimism and rejectionism, proposing a four-fold typology of human–AI collaboration grounded in methodological commitments and emphasizing deliberate, context-sensitive tool integration. We embed AI chatbots, automated workflows, and big data techniques into qualitative research processes—not to supplant deep interpretive understanding, but to support coding, analytical reasoning, and computationally augmented social interpretation. Our contributions are threefold: (1) a methodological framework demonstrating compatibility between computational tools and qualitative epistemic aims; (2) reusable, scalable computational-augmented workflow templates for qualitative analysis; and (3) empirical validation within large-scale ethnographic projects, confirming enhanced analytical efficiency without compromising interpretive depth or theoretical richness.

Existing computational tools for qualitative data analysis often fall short in effectively supporting causal exploration due to insufficient contextual awareness, limited trustworthiness, or overly complex outputs. To address these limitations, this work proposes QualCausal, the first interactive causal analysis system grounded in user research–driven design principles. Developed through formative user studies, QualCausal integrates context-aware processing, cognitive scaffolding, and explainability mechanisms to facilitate efficient exploration and validation of causal hypotheses within qualitative datasets. The system enables researchers to extract causal relationships, construct interactive causal networks, and examine findings through coordinated multi-view visualizations. User evaluations demonstrate that QualCausal significantly reduces analytical burden, provides robust cognitive support, and prompts critical reflection on how computational tools can be meaningfully integrated into social science research practices, thereby bridging the gap between computational assistance and qualitative inquiry paradigms.

This study addresses how dominant data storytelling practices often overlook the cultural contexts of communities with low digital literacy, thereby reinforcing their marginalization. Through a ten-month ethnographic investigation across three villages in Bangladesh, the research examines traditional performative forms—such as Puthi, Bhandari Gaan, and Pot—and how they interweave factual content, emotion, and aesthetics to convey moral lessons and historical memory. Building on these insights, the work proposes a novel data narrative paradigm that challenges Western-centric assumptions by integrating pluralistic voices, Indigenous ethical frameworks, and local artistic practices. This approach offers culturally sensitive and technologically adaptive design pathways for human-computer interaction (HCI) and data visualization, particularly suited to low-literacy communities.

This study investigates how museums can foster prosocial behavior toward vulnerable populations—such as refugees—through thematic curation. A randomized controlled field experiment was conducted at the Santa Maria della Scala Museum in Siena, where student participants were randomly assigned to either a care- and hospitality-themed guided tour or a standard art-focused tour, followed by an opportunity to donate to a refugee-supporting NGO. Results reveal that participants who received the thematic tour donated significantly more, with the effect particularly pronounced among female participants. This work provides the first empirical evidence that museums can function as effective instruments of behavioral public policy, demonstrating that targeted cultural experiences can meaningfully promote prosocial attitudes and actions, thereby offering cultural institutions a novel pathway to engage with pressing social issues.

This study explores the effective integration of large language models (LLMs) into qualitative and mixed-methods social network analysis to augment—rather than replace—the deep analytical capacities of human researchers. Focusing on core issues such as relational meaning, narrative interpretation, and identity construction, the work proposes an LLM application paradigm oriented toward enhancing methodological rigor. This paradigm emphasizes human–AI collaboration, reflexive practice, and ethical accountability. By incorporating LLM-assisted data coding, theory generation, and abductive reasoning, the project develops a methodologically innovative yet practically feasible framework for qualitative social network analysis. The approach significantly improves analytical efficiency while upholding scholarly standards and ethical compliance.