AI Qualitative Analysis: Lessons from 1, 924 IT Students

Researchers studying education, occupational health, and workforce readiness often need to combine survey data with interviews, reports, and open-ended responses. The 2026 PLOS ONE study of information technology students in Shanxi Province, China, shows why that task is difficult: the research team analyzed 1, 924 questionnaires, 30 interviews, expert evaluations, and literature to develop a preliminary occupational physical fitness framework. AI qualitative analysis can help research teams organize these mixed sources, identify recurring themes, compare stakeholder perspectives, and connect qualitative evidence with quantitative findings. This article explains what the study found, how its qualitative component shaped the conclusions, and how researchers can apply a more efficient, transparent analysis workflow without treating AI outputs as validated findings. The focus is practical: how to move from raw interview transcripts and survey comments to defensible themes, cross-segment comparisons, and research-ready evidence.

Key Takeaways

The PLOS ONE research article found that information technology students reported occupation-related physical discomfort and that interviews revealed gaps in occupation-specific training, but the proposed framework remains preliminary and requires further validation.

According to the study published on November 10, 2026, the final analytical sample included 1, 924 questionnaires: 1, 863 students, 37 teachers, and 24 enterprise personnel.
According to the study authors, 68.71% of students selected “Frequently” or “Occasionally” when asked about physical discomfort after professional practical operations such as prolonged computer use or equipment debugging.
According to the study authors, 30 qualitative interviews were conducted between April 20 and May 29, 2025, including 21 students, 6 teachers, and 3 enterprise personnel.
According to the study authors, interview findings pointed to limited occupation-specific training in visual relaxation, musculoskeletal relaxation, postural adjustment, and sedentary behavior interruption.
According to the study authors, the resulting framework combines general physical fitness, occupation-specific physical fitness, and psychological fitness, but it has not yet been confirmed through structural validity testing or objective measurements.

What the Shanxi Mixed-Methods Study Examined

The Shanxi study examined how students, teachers, and enterprise personnel perceived the physical and psychological capabilities needed for information technology education and work.

According to Jin, Cui, Zhao, and Hou, the research used a quantitative-dominant cross-sectional mixed-methods design in which questionnaire data provided the primary evidence and semi-structured interviews supplied contextual explanation.

The study authors analyzed 2, 106 returned questionnaires, excluded 182 questionnaires during screening, and retained 1, 924 questionnaires for analysis. The researchers also analyzed interview findings from 30 participants and incorporated literature analysis and content-validity evaluations from 8 experts.

The study authors organized the proposed framework into 12 indicators across three dimensions: general physical fitness, occupation-specific physical fitness, and psychological fitness. The occupation-specific dimension included sedentary tolerance, visual load tolerance, fine motor operation endurance, and static postural endurance.

The study authors cautioned that interview audio files, verbatim transcripts, field notes, and original coding records were no longer available for independent retrospective verification. That limitation matters for qualitative researchers because AI-assisted reanalysis requires access to the underlying source material, not only summarized themes.

Findings Snapshot for AI Qualitative Analysis

Date or period	Metric	Value	Implication for researchers
April 20 to May 29, 2025	Survey and interview data collection period	40 days	Analysis workflows should preserve dates, source types, and collection context.
November 10, 2026	Final questionnaire sample	1, 924	Large survey datasets benefit from automated coding and segment comparison.
November 10, 2026	Student respondents	1, 863	Student findings formed the main analytical base of the study.
November 10, 2026	Interview participants	30	Qualitative evidence added context but was not statistically representative.
November 10, 2026	Students reporting frequent or occasional post-practice discomfort	68.71%	The survey identified a substantial self-reported discomfort pattern for qualitative interpretation.
November 10, 2026	Students reporting 1 to 3 hours of exercise per week	52.01%	Survey segmentation can reveal behavior patterns that interviews help explain.
November 10, 2026	Students reporting almost no exercise	14.76%	A cross-segment analysis can identify groups for deeper qualitative follow-up.
November 10, 2026	Experts contributing to content validity evaluation	8	Expert review helped refine indicator names and wording before framework construction.

What the Interviews Added to the Quantitative Findings

How did qualitative interviews explain the student survey?

The interviews explained why general exercise participation did not necessarily translate into occupation-specific preparation for information technology work.

According to the study authors, students and teachers described limited incorporation of visual relaxation, musculoskeletal relaxation, postural adjustment, and sedentary behavior interruption into current educational practice. The authors summarized this finding by writing that “occupation-specific training... was very limited in current educational practice.”

An AI-assisted analysis could support this interpretation by coding interview passages for training gaps, physical discomfort, coping strategies, and barriers, then comparing those codes with survey response groups.

How did teacher interviews identify implementation barriers?

The teacher findings identified limited access to job-demand information, insufficient occupation-specific training methods and resources, and challenges in student engagement as implementation barriers.

According to the study authors, 13 of 17 eligible physical education teachers, or 76.47%, selected a lack of specific data on information technology job demands as a barrier. Among all 37 teachers, 29, or 78.38%, selected equipment as a needed teaching resource.

Researchers can use AI thematic analysis to separate barriers related to knowledge, resources, curriculum design, and stakeholder cooperation instead of collapsing all constraints into one broad theme.

How did enterprise perspectives affect the framework?

Enterprise responses connected occupational physical fitness with job adaptation and workplace support, but the study did not establish causal effects on performance.

According to the study authors, 10 of 24 enterprise respondents, or 41.67%, selected participation in physical fitness curriculum design as a possible form of support for vocational colleges, while 12 of 24, or 50.00%, selected providing training scenarios during enterprise practice.

A cross-segment qualitative workflow can compare the language used by students, educators, and employers while preserving the important distinction between perceived needs, actual practices, and proposed support.

How Evidano Supports AI Qualitative Analysis

Problem: Researchers need to synthesize interviews, papers, and reports

Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interview transcripts, open-ended surveys, papers, reports, and other documents.

Researchers can upload mixed source materials and use thematic, content, frequency, and cross-segment analyses to organize evidence around topics such as training gaps, physical discomfort, curriculum resources, or employer expectations. The Evidano features page provides an overview of the platform's analysis capabilities.

Problem: Manual coding makes stakeholder comparisons slow

Evidano can help researchers compare themes across defined groups, such as students, teachers, and enterprise personnel.

Cross-segment analysis can reveal which themes are shared across groups and which themes are specific to one stakeholder category. Researchers should still review source excerpts, document coding decisions, and distinguish descriptive patterns from confirmed findings.

Problem: Researchers need to interrogate a large evidence base

Evidano's AI chat enables researchers to ask questions across their uploaded documents and analyses.

A research team could ask which passages describe occupation-specific training, which barriers are reported by teachers, or how enterprise personnel describe curriculum participation. The team can then inspect supporting excerpts rather than relying only on an automatically generated summary.

Problem: Multilingual or sensitive research materials require controlled processing

Evidano supports transcription, translation, custom dictionaries, and personally identifiable information redaction for relevant qualitative research workflows.

Evidano states that data is encrypted and never used to train third-party models. Researchers should still follow their institution's ethics approval, consent, retention, and disclosure requirements when processing interview data.

FAQ: AI Qualitative Analysis for Mixed-Methods Research

What is AI qualitative analysis?

AI qualitative analysis uses artificial intelligence to organize, code, compare, and summarize qualitative data such as interviews, open-ended survey responses, papers, and reports.

AI can accelerate repetitive analysis tasks, but researchers remain responsible for interpreting context, checking quotations, documenting decisions, and evaluating methodological limitations.

How did the 2026 Shanxi study use qualitative research?

The 2026 Shanxi study used semi-structured interviews as a supplementary qualitative component alongside a questionnaire survey.

According to the study authors, 30 interviews with students, teachers, and enterprise personnel were analyzed thematically to explain survey findings about discomfort, training, curriculum resources, and school-enterprise cooperation.

What were the main qualitative themes in the study?

The main qualitative themes were student occupational physical fitness problems, insufficient training methods and resources, and weak alignment between enterprise job demands and school-based provision.

According to the study authors, the interview findings were used as contextual evidence rather than as a basis for statistical inference.

Can AI validate the occupational physical fitness framework?

AI qualitative analysis cannot by itself validate the framework proposed in the Shanxi study.

According to the study authors, the framework still requires structural validity testing, larger and more balanced samples, objective physical-fitness assessments, and potentially longitudinal or intervention research.

What should researchers watch for when using AI on interviews?

Researchers should watch for loss of context, overgeneralized themes, unsupported causal claims, privacy risks, and confusion between participant perceptions and validated measures.

The Shanxi study illustrates the importance of preserving source access because the authors reported that original interview recordings, verbatim transcripts, and coding records were unavailable for independent retrospective verification.

Conclusion and Next Steps for AI Qualitative Analysis

The Shanxi study demonstrates how qualitative interviews can explain patterns found in a large survey, especially when researchers compare student experiences with teacher and enterprise perspectives.

AI qualitative analysis can make that mixed-methods workflow more manageable by organizing documents, surfacing recurring themes, comparing segments, and enabling evidence-based questions across a research corpus.

The study authors' limitations remain important: self-reported measures were not clinical diagnoses, stakeholder samples were unbalanced, and the proposed framework was not structurally validated. Researchers should use AI to support transparent analysis, not to replace methodological judgment.

To analyze interviews, open-ended responses, and research documents in one workspace, try Evidano for free.

Topics

AI qualitative analysis
AI thematic analysis
mixed-methods research analysis
qualitative research software
interview transcript analysis

Keep reading

Browse all articles

AI Qualitative Analysis: Lessons from 1, 924 IT Students

Key Takeaways

What the Shanxi Mixed-Methods Study Examined

Findings Snapshot for AI Qualitative Analysis

What the Interviews Added to the Quantitative Findings

How did qualitative interviews explain the student survey?

How did teacher interviews identify implementation barriers?

How did enterprise perspectives affect the framework?

How Evidano Supports AI Qualitative Analysis

Problem: Researchers need to synthesize interviews, papers, and reports

Problem: Manual coding makes stakeholder comparisons slow

Problem: Researchers need to interrogate a large evidence base

Problem: Multilingual or sensitive research materials require controlled processing

FAQ: AI Qualitative Analysis for Mixed-Methods Research

What is AI qualitative analysis?

How did the 2026 Shanxi study use qualitative research?

What were the main qualitative themes in the study?

Can AI validate the occupational physical fitness framework?

What should researchers watch for when using AI on interviews?

Conclusion and Next Steps for AI Qualitative Analysis

Topics

Keep reading

Company

About

Preview Evidano

Account

Newsletter