From Mixed Methods to Insight: AI Qualitative Data Analysis

According to the 2026 PLOS One mixed-methods study on information technology students, AI qualitative data analysis can help researchers organize interview themes alongside survey findings, but human review remains essential when the qualitative evidence is exploratory and the original transcripts are unavailable.

• The study analyzed 1, 924 questionnaires collected from April 20 to May 29, 2025, including 1, 863 students, 37 teachers, and 24 enterprise personnel.
• The study also documented 30 semi-structured interviews conducted with 21 students, 6 teachers, and 3 enterprise personnel.
• According to the study authors, 68.71% of students selected “Frequently” or “Occasionally” when reporting physical discomfort after activities such as prolonged computer use or equipment debugging.
• The qualitative analysis identified three themes: student occupational fitness problems, insufficient institutional resources, and weak alignment between enterprise demands and school-based training.
• The authors proposed a preliminary framework with three dimensions, general physical fitness, occupation-specific physical fitness, and psychological fitness, while stating that further validation is required.

The study examined perceived occupational physical fitness priorities among information technology students at selected vocational colleges in Shanxi Province, China, using a quantitative-dominant cross-sectional mixed-methods design.

According to the study authors, the questionnaire was the primary method and semi-structured interviews were a supplementary explanatory method. The research team analyzed the quantitative and qualitative strands separately before integrating them during interpretation.

The study focused on a population exposed to prolonged sitting, continuous screen use, static postures, repetitive fine-motor work, and cognitive pressure. The authors described occupational physical fitness as including general physical capacity, occupation-specific tolerance, and psychological fitness.

The researchers reported that 44.50% of students selected dry eyes or blurred vision, 38.06% selected cervical or lumbar soreness, and 25.93% selected physical fatigue or insufficient endurance in the questionnaire administered between April 20 and May 29, 2025.

One defining methodological constraint was that the original interview audio, verbatim transcripts, field notes, and detailed coding records were unavailable at the time of manuscript revision. The reported qualitative findings therefore relied on thematic results preserved in the contemporaneous study documentation.

The interviews added context by explaining why the survey patterns might exist, rather than by independently proving the prevalence or causes of physical discomfort.

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 qualitative findings were organized into three themes. The first concerned occupational physical fitness problems and a lack of training methods. The second concerned insufficient institutional resources, including limited equipment, specialist support, and teaching materials. The third concerned inadequate alignment between enterprise job demands and school-based training.

The study reported that 13 of 17 eligible physical education teachers, or 76.47%, selected a lack of specific information about information technology job demands as a training constraint during the survey period from April 20 to May 29, 2025.

The authors summarized the broader interpretation in the phrase “general physical fitness–occupation-specific physical fitness–psychological fitness, ” which became the basis of their preliminary framework.

For qualitative researchers, the key lesson is that interviews can explain mechanisms, barriers, and stakeholder perspectives that a closed-ended questionnaire cannot capture. The study also demonstrates why researchers should preserve transcripts, coding records, and data dictionaries for later verification.

The 2026 PLOS One study shows how survey statistics and qualitative themes can work together to explain an underexamined research problem. The study’s 1, 924 questionnaires and 30 interviews produced a useful preliminary framework, but its authors appropriately emphasized limitations involving convenience sampling, small teacher and enterprise samples, unavailable original qualitative materials, and incomplete structural validation.

AI qualitative data analysis can make this type of mixed-methods workflow more manageable by organizing documents, surfacing themes, comparing stakeholder segments, and helping researchers return to supporting evidence. The strongest results come when researchers use AI for structured assistance while preserving transparent human review.

Researchers can try Evidano for free to analyze interviews, open-ended survey responses, and mixed document collections in a more efficient qualitative research workflow.