Researchers studying vocational education, occupational health, and student wellbeing often need to combine survey data with interviews, stakeholder perspectives, and documentary evidence. AI qualitative research analysis can make that mixed-methods workflow faster, while preserving the distinctions between participant experiences, perceived priorities, and institutional constraints. This post examines how the November 2026 PLOS One study by Xiaobin Jin, Xiaoying Cui, Yi Zhao, and Yu Hou investigated occupational physical fitness among information technology students in selected vocational colleges in Shanxi Province, China. The study combined 1, 924 questionnaires with 30 qualitative interviews, then proposed a preliminary framework spanning general physical fitness, occupation-specific physical fitness, and psychological fitness. The analysis also shows where AI-assisted thematic analysis is useful, where human interpretation remains essential, and how researchers can move from raw transcripts and survey responses to an auditable evidence structure.
Key Takeaways
According to the PLOS One study on occupational physical fitness among Shanxi IT students, mixed-methods research found that information technology students reported physical discomfort and psychological pressures, while teachers and enterprise personnel identified gaps in occupation-specific training and school-enterprise collaboration.
AI qualitative research analysis can help researchers organize interviews, open-ended responses, and research documents into themes, compare stakeholder segments, and trace conclusions back to supporting evidence. AI does not replace methodological judgment, especially when a study uses convenience sampling, small stakeholder groups, or nonvalidated measures.
- In data collected from April 20 to May 29, 2025, the study retained 1, 924 questionnaires: 1, 863 from students, 37 from teachers, and 24 from enterprise personnel.
- The study reported that 68.71% of students selected “Frequently” or “Occasionally” when asked about physical discomfort after professional practical operations.
- Among students, 44.50% selected dry eyes or blurred vision, 38.06% selected cervical or lumbar soreness, and 25.93% selected physical fatigue or insufficient endurance.
- The qualitative component included 30 interviews conducted with 21 students, 6 teachers, and 3 enterprise personnel.
- The authors proposed three framework dimensions: general physical fitness, occupation-specific physical fitness, and psychological fitness.
What the Shanxi IT Student Study Found
The Shanxi study found that reported discomfort, limited occupation-specific training, and gaps in educational and enterprise resources were connected themes, but the researchers did not treat those themes as proof of causal relationships.
Jin, Cui, Zhao, and Hou used a quantitative-dominant cross-sectional mixed-methods design, with questionnaires as the primary method and semi-structured interviews as supplementary explanatory evidence. The authors analyzed the quantitative and qualitative strands separately before integrating them around student experiences, stakeholder-rated priorities, and provision constraints.
The study reported that weekly exercise was most commonly 1 to 3 hours, selected by 52.01% of students, while 14.76% selected “Almost no exercise.” The questionnaire measured exercise duration but not exercise intensity or frequency, so the authors did not use these results to determine whether students met physical-activity recommendations.
The qualitative findings identified three themes: occupational physical fitness problems and limited training methods, insufficient institutional resources, and inadequate alignment between enterprise job demands and school-based training.
The authors described the proposed framework as preliminary. Their internal-consistency results and expert content evaluation offered exploratory measurement evidence, but the framework had not undergone structural validity testing through methods such as exploratory factor analysis or confirmatory factor analysis.
The study authors wrote that the framework should not be understood as “simply general sports ability.” The authors instead linked information technology work to sedentary tolerance, visual load tolerance, fine-motor endurance, static postural endurance, sustained concentration, stress resistance, and emotional regulation.
Findings Snapshot for AI Qualitative Research Analysis
| Date or study element | Metric | Value | Research implication |
|---|---|---|---|
| April 20 to May 29, 2025 | Survey collection period | 40 days | The quantitative evidence reflects a defined collection window rather than a longitudinal trend. |
| November 10, 2026 | Publication date | PLOS One, volume 21, issue 11 | The study provides a current example of mixed-methods analysis in vocational education research. |
| Final analytical sample | Questionnaires retained | 1, 924 total, including 1, 863 students | The student group supplied most of the descriptive evidence. |
| Qualitative component | Interview participants | 30 total, including 21 students, 6 teachers, and 3 enterprise personnel | The interviews added context but were not designed for statistical representation. |
| Student-reported discomfort | Frequently or occasionally experienced discomfort | 68.71% | The result identifies a prominent experience for thematic follow-up, not a clinical diagnosis. |
| Student symptom selection | Dry eyes or blurred vision | 44.50% | Visual load emerged as a relevant topic for coding and segment comparison. |
| Student exercise duration | Reported 1 to 3 hours per week | 52.01% | Exercise duration was common, but intensity and frequency were not measured. |
| Cross-stakeholder comparisons | Comparisons surviving false-discovery-rate correction | 0 of 15 | The study did not establish robust stakeholder differences in perceived priorities. |
Implications for Researchers Using AI Thematic Analysis
How should researchers separate experiences from perceived priorities?
Researchers should code self-reported experiences, importance ratings, and provision constraints as separate evidence domains.
The Shanxi study distinguished reported discomfort from stakeholder ratings of indicator importance and from teacher and enterprise reports about training resources. AI thematic analysis can preserve those distinctions by using separate code families, respondent metadata, and analytical questions rather than collapsing every mention into one general “need” theme.
Why is stakeholder segmentation important in qualitative research analysis?
Stakeholder segmentation is important because students, teachers, and enterprise personnel answered different research questions and contributed different types of evidence.
The study included 1, 863 students but only 37 teachers and 24 enterprise personnel. An AI research workflow should therefore compare segments transparently while avoiding claims that small teacher or enterprise samples represent their wider populations.
What should human researchers verify after AI-assisted coding?
Human researchers should verify code definitions, contradictory responses, quotations, sampling limitations, and the difference between descriptive patterns and causal claims.
The source study reported that original interview audio, verbatim transcripts, field notes, and detailed coding records were no longer available for independent retrospective verification. That limitation demonstrates why researchers should preserve source files, analytic memos, codebooks, and decision logs alongside AI-generated summaries.
How can researchers turn mixed-methods findings into a defensible framework?
Researchers can build a defensible framework by linking literature, survey patterns, interview themes, expert evaluation, and limitations in an explicit evidence chain.
The study organized its framework into three dimensions and 12 indicators, but the authors stated that further validation was required. AI can accelerate comparison and synthesis, while researchers remain responsible for deciding whether a theme is sufficiently supported to become a conceptual construct.
How Evidano Helps with AI Qualitative Research Analysis
Problem: Mixed-methods evidence is scattered across files
Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, papers, reports, and other documents.
Researchers can bring source documents and survey responses into one analysis environment, then use thematic, content, frequency, and cross-segment analyses to examine how students, teachers, and enterprise respondents differ. Learn more about Evidano's qualitative research features.
Problem: Interview themes are difficult to compare with survey segments
Evidano supports cross-segment analysis that can help researchers compare stakeholder groups, respondent characteristics, or study conditions without losing the underlying source context.
For a study like the Shanxi research, a researcher could organize evidence by students, teachers, and enterprise personnel, then compare themes such as discomfort, training needs, job-demand information, and school-enterprise collaboration.
Problem: Researchers need answers across a large evidence base
Evidano's AI chat over documents and analyses can help researchers ask focused questions across imported papers, reports, transcripts, and survey data.
Useful questions include: Which themes appear in both interviews and open-ended survey responses? Which themes are unique to teachers? Which findings are descriptive rather than causal? Researchers should still inspect the cited source passages before publishing a conclusion.
Problem: Manual synthesis makes auditability difficult
Evidano's hierarchical codes and subcodes, frequency views, word clouds, and co-occurrence networks can make an evolving qualitative framework easier to inspect.
A transparent workflow can begin with broad codes such as general physical fitness, occupation-specific physical fitness, and psychological fitness, then refine those codes into subcodes such as visual load tolerance, sedentary tolerance, sustained concentration, and emotional regulation.
Problem: Sensitive interview and survey data require protection
Evidano encrypts data and states that customer data is never used to train third-party models.
Researchers handling student interviews, employee perspectives, or health-related experiences can review Evidano's data security approach as part of their research governance process.
FAQ: AI Qualitative Research Analysis
What is AI qualitative research analysis?
+
AI qualitative research analysis uses artificial intelligence to organize, code, summarize, compare, and retrieve patterns from interviews, open-ended survey responses, papers, and other textual data.
AI can accelerate repetitive analysis tasks, but researchers must define the research question, assess source quality, review interpretations, and report methodological limitations.
How did the Shanxi study use qualitative research?
+
The Shanxi study used 30 semi-structured interviews as a supplementary qualitative component alongside a questionnaire survey of 1, 924 retained responses.
The authors used thematic analysis to identify three themes concerning student problems, institutional resources, and alignment between enterprise demands and school-based training.
What were the main findings about information technology students?
+
The main findings were that 68.71% of students selected “Frequently” or “Occasionally” for post-practical-operation physical discomfort, and 44.50% selected dry eyes or blurred vision as a symptom category.
The study also reported that 52.01% of students selected 1 to 3 hours of weekly exercise and that occupation-specific training was limited in the educational practice examined.
Can AI prove that computer use caused student discomfort?
+
AI cannot prove that computer use caused student discomfort from this study because the research was cross-sectional and relied on self-reported data.
The authors presented the findings as contextual evidence and stated that causal relationships could not be inferred.
What are the limitations of the study?
+
The study's limitations included convenience and snowball sampling, small teacher and enterprise samples, lack of objective measurements, unavailable original qualitative records, and the absence of structural validity testing for the proposed framework.
The authors also reported that none of the 15 cross-stakeholder comparisons remained statistically supported after false-discovery-rate correction.
How can researchers use Evidano for this type of study?
+
Researchers can use Evidano to ingest documents and survey responses, identify themes, compare stakeholder segments, query the evidence with AI chat, and visualize relationships among codes.
Researchers should use the platform as an analysis aid and retain human review, source verification, codebook decisions, and ethical oversight.
Conclusion and Next Steps for AI Qualitative Research Analysis
The Shanxi IT student study shows why mixed-methods research benefits from a structured qualitative analysis workflow: survey statistics describe patterns, interviews explain context, and stakeholder segmentation clarifies where perspectives converge or differ.
AI qualitative research analysis can reduce the manual effort required to organize those evidence types, but defensible research still depends on transparent sampling, careful coding, source preservation, and appropriately cautious interpretation.
Evidano gives researchers one environment for analyzing interviews, documents, and survey responses through thematic, frequency, cross-segment, and AI-assisted evidence exploration. Try Evidano for free and turn complex qualitative data into a clearer, reviewable research workflow.
Topics
- AI qualitative research analysis
- AI thematic analysis
- mixed-methods research analysis
- qualitative interview analysis
- vocational education research
Keep reading
- Commentary on NewsFrom Interviews to Insight: AI Qualitative Research AnalysisSee how AI qualitative research analysis clarifies mixed-methods findings, stakeholder needs, and vocational education priorities. Explore the evidence.
- Commentary on NewsAI Qualitative Analysis: Lessons from IT Student ResearchLearn how AI qualitative analysis can synthesize mixed-methods research, uncover student health themes, and connect survey findings with interview evidence.
- Commentary on NewsAI Qualitative Analysis for Mixed-Methods ResearchSee how AI qualitative analysis turns mixed-methods evidence into traceable themes, comparisons, and decisions for education and health researchers.