检索结果-内蒙古大学图书馆

Differences in User Perception of Artificial Intelligence-Driven Chatbots and Traditional Tools in qualitative data analysis

引用

APPLIED SCIENCES-BASEL 2025年第2期15卷

作者： Sumak, Bostjan Pusnik, Maja Kozuh, Ines Sorgo, Andrej Brdnik, Sasa Univ Maribor Fac Elect Engn & Comp Sci Maribor 2000 Slovenia Univ Ljubljana Fac Social Sci Ljubljana 1000 Slovenia Univ Maribor Fac Nat Sci & Math Maribor 2000 Slovenia

qualitative data analysis (QDA) tools are essential for extracting insights from complex datasets. This study investigates researchers' perceptions of the usability, user experience (UX), mental workload, trust, task complexity, and emotional impact of three tools: Taguette 1.4.1 (a traditional QDA tool), ChatGPT (GPT-4, December 2023 version), and Gemini (formerly Google Bard, December 2023 version). Participants (N = 85), Master's students from the Faculty of Electrical Engineering and Computer Science with prior experience in UX evaluations and familiarity with AI-based chatbots, performed sentiment analysis and data annotation tasks using these tools, enabling a comparative evaluation. The results show that AI tools were associated with lower cognitive effort and more positive emotional responses compared to Taguette, which caused higher frustration and workload, especially during cognitively demanding tasks. Among the tools, ChatGPT achieved the highest usability score (SUS = 79.03) and was rated positively for emotional engagement. Trust levels varied, with Taguette preferred for task accuracy and ChatGPT rated highest in user confidence. Despite these differences, all tools performed consistently in identifying qualitative patterns. These findings suggest that AI-driven tools can enhance researchers' experiences in QDA while emphasizing the need to align tool selection with specific tasks and user preferences.

关键词： user experience UX usability qualitative data analysis QDA chatbots

来源：评论

学校读者我要写书评

暂无评论

AI and qualitative data analysis in Education Research: Familiarization and Exploration of Interview Transcripts Enhanced with ChatGPT

AI and Qualitative Data Analysis in Education Research: Fami...

引用

International Conference on Communication and Applied Technologies, ICOMTA 2024

作者： Etesse, Manuel Pontificia Universidad Católica del Perú Lima15088 Peru

ISBN: (纸本)9789819604258

This study investigates the efficacy of ChatGPT in enhancing the initial phases of qualitative data analysis (QDA), particularly in data familiarization and exploration in education research. Analyzing interview data from young adults in Lima, Peru, the research explores how AI can complement traditional methods by speeding up the generation of relevant statements, case-cluster summaries, and initial codes. Despite ChatGPT’s ability to rapidly process data, the study highlights the need for human oversight to ensure the specificity and relevance of AI-generated outputs. Furthermore, while AI can enhance the reflexivity of researchers by providing alternative analyses, it does not substitute the nuanced judgment required in qualitative research. The findings suggest that while AI can significantly aid the research process, it must be used judiciously, with careful consideration of its limitations and potential biases. This research contributes to a deeper understanding of AI’s role in QDA, proposing that it be used as a supportive tool in the initial phases rather than a replacement for human expertise in education research. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Artificial intelligence ChatGPT Education research Generative artificial intelligence Methodology qualitative data analysis qualitative inquiry Social research

来源：评论

学校读者我要写书评

暂无评论

LLM-Assisted qualitative data analysis: Security and Privacy Concerns in Gamified Workforce Studies

引用

Procedia Computer Science 2025年 257卷 60-67页

作者： Aisvarya Adeseye Jouni Isoaho Tahir Mohammad Department of Computing University of Turku Vesilinnantie 5 Turku 20014 Finland

Large language models (LLMs) have transformed textual or qualitative data processing and analysis by automating and enhancing interpretive accuracy, particularly in complex areas like cybersecurity, ethics, and compliance. This study examines the effective-ness of local LLMs in analyzing qualitative research using the data gathered from the case study on “perspectives on security and privacy issues associated with the introduction of gamified workforce studies”. The research presented in this paper utilized 23 interview transcripts to evaluate three popular LLMs, namely LLaMA, Gemma, and Phi, running on a local infrastructure. We observed that LLaMA focuses on practical data security, Gemma on regulatory compliance, and Phi on ethical transparency and trust-building. By combining these models, researchers can gain a more comprehensive understanding of the complex implications of gamification in workforce studies. Local LLMs provide the added benefit of enhanced data privacy and security by processing sensitive data entirely within a controlled environment. This study explores the system and user prompts that can improve the interpretive accuracy of various qualitative research approaches, such as thematic analysis, frequency analysis, impact level analysis, sensitivity analysis, and disclosure analysis, demonstrating the potential of local LLMs for qualitative analysis for sensitive data. This study recommends the usage of LLMs for the initial stage of the qualitative analysis process to enhance the efficiency and effectiveness of subsequent completely manual or software-assisted manual analysis.

关键词： Large Language Models qualitative data analysis Prompt Engineering Privacy Security Gamification Workforce Studies

来源：评论

学校读者我要写书评

暂无评论

qualitative data analysis of Issue Interrelations and Interdependencies for E-Government Research Planning 1

引用

8th International Conference on Electronic Government

作者： Wimmer, Maria A. Bicking, Melanie Univ Koblenz Landau Inst Informat Syst D-56070 Koblenz Germany

ISBN: (数字)9783642035166

ISBN: (纸本)9783642035159

Science and technology roadmapping is currently a popular method to develop long-term strategies for e-government. In the scope of the EC-co-funded research project eGovRTD2020, an innovative methodology has been developed, which combines scenarios and roadmapping to support long-term strategic policy-making for e-government research. This approach bases on systematically analyzing qualitative data throughout the whole roadmapping process based on individual issues and their interrelations. The paper explores the complex analysis of the network of relations and interdependencies between these issues. We introduce a concept for the systematic analysis of interlinks between single issues, which helps improving the quality of analysis and advances the consolidation of results to form well grounded strategic policy-making. A case example extracted from the project serves as proof of concept.

关键词： qualitative data analysis roadmapping strategic policy planning e-government

来源：评论

学校读者我要写书评

暂无评论

The QDAcity-RE method for structural domain modeling using qualitative data analysis

引用

REQUIREMENTS ENGINEERING 2019年第1期24卷 85-102页

作者： Kaufmann, Andreas Riehle, Dirk Friedrich Alexander Univ Erlangen Nurnberg Dept Comp Sci Martensstr 3 D-91052 Erlangen Germany

The creation of domain models from qualitative input relies heavily on experience. An uncodified ad-hoc modeling process is still common and leads to poor documentation of the analysis. In this article we present a new method for domain analysis based on qualitative data analysis. The method helps identify inconsistencies, ensures a high degree of completeness, and inherently provides traceability from analysis results back to stakeholder input. These traces do not have to be documented after the fact. We evaluate our approach using four exploratory studies.

关键词： Domain modeling Domain model Requirements engineering Requirements elicitation qualitative data analysis

来源：评论

学校读者我要写书评

暂无评论

A validation of QDAcity-RE for domain modeling using qualitative data analysis

引用

REQUIREMENTS ENGINEERING 2022年第1期27卷 31-51页

作者： Kaufmann, Andreas Krause, Julia Harutyunyan, Nikolay Barcomb, Ann Riehle, Dirk Friedrich Alexander Univ Erlangen Nurnberg Dept Comp Sci Martensstr 3 D-91058 Erlangen Germany Univ Calgary Elect & Software Engn Schulich Sch Engn 2500 Univ Dr NW Calgary AB T2N 1N4 Canada

Using qualitative data analysis (QDA) to perform domain analysis and modeling has shown great promise. Yet, the evaluation of such approaches has been limited to single-case case studies. While these exploratory cases are valuable for an initial assessment, the evaluation of the efficacy of QDA to solve the suggested problems is restricted by the common single-case case study research design. Using our own method, called QDAcity-RE, as the example, we present an in-depth empirical evaluation of employing qualitative data analysis for domain modeling using a controlled experiment design. Our controlled experiment shows that the QDA-based method leads to a deeper and richer set of domain concepts discovered from the data, while also being more time efficient than the control group using a comparable non-QDA-based method with the same level of traceability.

关键词： Domain model Domain modeling qualitative data analysis Requirements engineering Controlled experiment

来源：评论

学校读者我要写书评

暂无评论

Users' experiences with qualitative data analysis software - Neither Frankenstein's monster nor muse

引用

SOCIAL SCIENCE COMPUTER REVIEW 1996年第4期14卷 423-432页

作者： Smith, BA HesseBiber, S Boston College

The use of qualitative data analysis software has been increasing in recent years. A number of qualitative researchers have raised questions concerning the effect of such software in the research process. Pears have been expressed that the use of the computer for qualitative analysis may interfere with the relationship between the researcher and the research process itself by distancing the researcher from both the data and the respondent. Others have suggested that the use of a quantitative tool, the computer, would lead to data dredging, quantification of results, and loss of the ''art'' of qualitative analysis. In this study of 12 qualitative researchers, including both faculty members and graduate students, we have found that these fears are exaggerated. Users of qualitative data analysis software in most cases use the computer as an organizational time-saving tool and take special care to maintain close relationships with both the data and the respondents. It is an open question, however, whether or not the amount of time and effort saved by the computer enhance research creativity. The research findings are mixed in this area. At issue is the distinction between creativity and productivity when computer methods are used.

关键词： qualitative data analysis computer software ethnograph research methodology

来源：评论

学校读者我要写书评

暂无评论

Proximity and distance: phases of intersubjective qualitative data analysis in a research team

引用

QUALITY & QUANTITY 2014年第2期48卷 1089-1106页

作者： Doos, Marianne Wilhelmson, Lena Stockholm Univ Dept Educ S-10691 Stockholm Sweden

In qualitative field studies, researchers frequently deal with comprehending a multifaceted reality. Large quantities of data are collected for analysis at a later stage. Alternation between proximity and distance is a crucial mechanism in the analysis of qualitative data. This article's aim is to make intersubjective analysis of qualitative data comprehensible through the investigation and description of phases and key components in a case of productive team co-operation. The argument is methodological, and addresses how empirical data can make a difference within a certain theoretical framework in analytical generalisation. Experiences from a case of intersubjective analysis work between four researchers are described and made sense of. Phases and key components are discussed. Close co-operation of a research team is suggested as a possibility in qualitative fieldwork and analysis. It is concluded that: (a) the idea of collectivity has hitherto been an underdeveloped possibility for qualitative research;(b) purposely intertwining data collection with analysis can be a powerful route for gaining reliable qualitative research;and (c) data analysis as close teamwork is promising as a means of keeping an openness to discoveries, thus gaining validity in the qualitative research endeavour. Coordinating with others in concentrated teamwork may defend the analytical task against other demands an academic post entails.

关键词： Analytical generalisation qualitative data analysis Intersubjective analysis Metaphor qualitative research Team analysis

来源：评论

学校读者我要写书评

暂无评论

Teaching qualitative data analysis to graduate students

引用

SOCIAL SCIENCE COMPUTER REVIEW 2004年第2期22卷 187-196页

作者： Blank, G American Univ Washington DC 20016 USA

This article reports the author's experience teaching sociology graduate students how to analyze qualitative data. The course focused on teaching practical skills of defining coding categories, coding text, analyzing coded text, and writing up the results of analysis. The assignments used Qualrus software to give students hands-on practice doing all of these. The course was enthusiastically received and will become a permanent part of the sociology methods course offerings at American University.

关键词： teaching qualitative data analysis coding Qualrus

来源：评论

学校读者我要写书评

暂无评论

A discussion of qualitative data analysis in hospitality research with examples from an ethnography of English public houses

引用

International Journal of Hospitality Management 2007年第3期26卷 724-742页

作者： Sandiford, Peter John Seymour, Diane School of Human Resources Management Leeds Metropolitan University Leeds LS6 3QS Headingley United Kingdom Business School Department of Hospitality Leisure and Tourism Management Oxford Brookes University Oxford Gypsy Lane Headington United Kingdom

This paper argues that qualitative Hospitality research is infrequently reported in Hospitality journals and that when such research does appear, the processes of data analysis seldom receive rigorous attention. Different analytic practices are discussed using a real-life example of qualitative research-an ethnography of English pubs-showing some techniques in action and highlighting issues and challenges that often face qualitative researchers. data reduction, deconstruction (data management) and reconstruction (interpretation and conceptualization) are discussed and techniques such as reflective note-taking, line-by-line analysis, domain and taxonomic charting, visual/diagrammatic constructions and metaphor are considered. It is argued that greater reporting of and discussion of data analysis would enhance the qualitative literature in hospitality research. © 2006 Elsevier Ltd. All rights reserved.

关键词： Ethnographic research Public houses qualitative data analysis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：