user interview research

This study addresses the limitations of conventional interview analysis, which relies heavily on researchers’ specialized qualitative skills, is difficult to scale, and often overlooks participants’ own interpretive logics. To overcome these challenges, the paper proposes the Documentary Mode of Interpretation (DMI), a membership-based method grounded in ordinary people’s natural language competencies. DMI identifies endogenous themes within interview texts to uncover the collective reasoning processes participants employ in making sense of the research topic. Crucially, this approach requires neither predefined coding frameworks nor formal training in social theory, thereby departing from traditional qualitative paradigms by generating themes bottom-up from participants’ perspectives. By significantly lowering the technical and epistemic barriers to qualitative analysis, DMI offers non-specialist researchers an accessible, low-threshold pathway to effectively interpret the collective meaning structures embedded in interview data.

This study investigates whether large language models (LLMs) can bridge the gap between UX experts and non-experts in authoring user scenarios. In a controlled experiment, both groups authored scenarios with LLM assistance; outputs were evaluated via mixed methods—structured scoring and qualitative coding—assessing structural completeness, expressive clarity, and audience orientation. Results demonstrate, for the first time empirically, that LLMs significantly enhance non-experts’ performance: their scenarios achieve structural and clarity levels comparable to experts’, and—remarkably—surpass experts in articulating user perspectives. The findings validate LLMs as effective, democratized tools for requirements analysis and reveal their unique capacity to augment empathic user-centered expression. This work advances accessible UX practice by lowering barriers to rigorous scenario-based design.

In semi-structured interviews, the quality of follow-up questioning is highly dependent on interviewer expertise, and the potential of large language models (LLMs) to augment data collection remains underexplored. Method: We introduce the “AI-augmented puppeteer” paradigm, embedding an LLM into real-time interview workflows via a Wizard-of-Oz experimental design to generate context-sensitive follow-up questions, and systematically examine human–AI dynamics in role allocation, collaborative behavior, and responsibility distribution. Based on an empirical study with 17 participants, we develop a human–AI co-interviewing framework and human-centered design guidelines. Results: Findings confirm that LLMs significantly enhance the depth and topical breadth of follow-up questions—but only when humans retain epistemic authority and ethical oversight. Our core contribution is the first empirical demonstration of how LLMs function as *collaborators*—not substitutes—in qualitative data collection, revealing their impact mechanism on data quality and establishing a methodological foundation and practical pathway for AI-enhanced qualitative research.

This study addresses the absence of empirically validated quality metrics for evaluating the contribution of interview responses to qualitative research objectives. Building a corpus of 343 interview transcripts comprising 16,940 responses, the authors systematically assess the predictive validity of ten established quality indicators with respect to their research utility. Integrating qualitative content analysis, natural language processing, and statistical modeling, the findings demonstrate that direct relevance to the core research question is the strongest predictor of a response’s value, whereas commonly used NLP-based metrics—such as clarity and surprise-based informativeness—show no significant predictive power. These results challenge the applicability of current automated evaluation approaches and provide empirical grounding for assessing response quality in qualitative inquiry.

This study examines the tension between efficiency gains and researcher autonomy arising from AI-assisted analysis in qualitative research. Through in-depth interviews with 16 qualitative researchers, it comparatively analyzes acceptance and underlying mechanisms across three coding paradigms: fully manual, human-initiated AI-assisted, and AI-initiated. The study innovatively conceptualizes AI explicitly as a “supporter”—neither collaborator nor supervisor—and identifies three core determinants of adoption: efficiency enhancement, attribution of interpretive ownership, and algorithmic trust. Findings indicate broad acceptance of AI for accelerating coding and thematic analysis, yet strong consensus on human primacy in meaning-making and interpretive authority. Enhancing procedural transparency, researcher control, and structured human–AI collaboration significantly strengthens trust and mitigates bias risks. The work provides theoretical grounding and actionable guidelines for developing human-centered, accountable AI-augmented qualitative research workflows.

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.

This study addresses the challenges interviewers face in requirements elicitation interviews, where balancing comprehensive topic coverage, active listening, and adaptive follow-up questioning is difficult, compounded by a lack of effective script execution tracking. To overcome these limitations, this work proposes the first end-to-end AI-assisted interview framework, integrating business-goal-driven theoretical script generation, real-time topic coverage monitoring via natural language processing, and an on-demand dynamic probing mechanism. Experimental results demonstrate that the proposed approach significantly improves script quality (92.8 vs. 74.8), probing depth (3.43 vs. 1.15 probes per topic), and granularity of the resulting requirements models (proportion of leaf-level goals: 0.653 vs. 0.598). Notably, 86% of users identified real-time topic tracking as the most practically valuable feature.

Existing LLM-based interview systems struggle to balance predefined topic coverage with adaptive exploration, limiting the scalable acquisition of high-quality qualitative user insights. This work proposes a multi-agent LLM architecture that frames adaptive semi-structured interviewing as a utility optimization problem, formally defining interview utility as a trade-off among topic coverage, discovery of novel insights, and conversational cost. The system dynamically plans high-expected-utility questions through simulated dialogue rollouts. Experiments demonstrate that, in LLM simulations, the approach improves topic coverage by 4.7% and yields richer insights in fewer turns. A user study with 70 participants further validates that domain experts recognize the method’s ability to uncover high-quality insights in professional contexts that existing approaches fail to capture.

This study addresses the limitations of existing automated interview systems, where fixed question sequences lead to insufficient personalization and redundant inquiries. We propose a dynamic interview architecture based on a local large language model. The architecture incorporates a five-module prompt-driven mechanism with persistent state tracking to assess participant expertise in real time, adaptively adjust question depth, maintain semantic continuity, and ensure evidence-traceable interactions. Experimental results demonstrate that the system achieves 78.9% accuracy in expert profiling, with question complexity significantly correlated with user proficiency levels. Furthermore, it attains a satisfaction score of 4.38 out of 5, effectively validating the feasibility and superiority of this adaptive interviewing paradigm.

This study addresses the limitation that analyzing prompts alone is insufficient for comprehensively evaluating developer interactions with AI programming agents. To overcome this, we propose a novel multidimensional interaction analysis framework termed "Say-Do-Understand," which integrates prompt data, screen activity, and comprehension metrics through a systematic five-stage end-to-end workflow. Employing an observational methodology, the analysis utilizes a prompt codebook, a screen activity coding scheme, and dual scoring rubrics. An empirical study involving ten experienced developers validates the proposed approach. Furthermore, four developer personas synthesizing task performance and comprehension levels are introduced to elucidate behavioral variations. Notably, the findings reveal that excessive reliance on agent self-checking significantly reduces developers' autonomous testing time.