Journal Analysis for Monitoring Students’ emotional Well-Being with Natural Language Processing: A Comparative Study of Typed and Transcribed Entries with Personalized Feedback

Journal Analysis for Monitoring Students’ emotional Well-Being with Natural Language Processing: A Comparative Study of Typed and Transcribed Entries with Personalized Feedback - JAM-STEP

Status

Recruiting

Phases

Unknown

Study type

Observational

Source

DRKS

Registry ID

DRKS00034660

Enrollment

100

Registered

2024-10-16

Start date

2024-09-30

Completion date

Unknown

Last updated

2025-04-07

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Emotional Well-Being

Interventions

Group 1: The study involves collecting journaling entries and EMA (Ecological Momentary Assessment) questionnaires over a 14-day period. Participants use the Famedly messenger to submit a daily evenin

Eligibility

Sex/Gender

All

Age

18 Years to No maximum

Inclusion criteria

Inclusion criteria: 1) Participants should have a smartphone with internet access (Android/iOS). 2) Participants should have good German language skills. 3) Participants may, but are not required to, have a psychological condition.

Exclusion criteria

Exclusion criteria: Participation in the JAM-STEP project is not allowed for individuals experiencing a severe psychological crisis that requires immediate action, such as acute suicidality. In such situations, inpatient treatment is recommended, as the support offered by JAM-STEP would not be adequate.

Design outcomes

Primary

Measure	Time frame
The German and EMA versions of the Multidimensional Mood State Questionnaire (MDBF). We hypothesize that emotional well-being, as measured by the MDBF, can be predicted through the analysis of journaling entries using natural language processing (NLP). Furthermore, we expect that the prediction accuracy for spoken journaling entries will be higher compared to typed entries.	—

Secondary

Measure	Time frame
Additionally, we hypothesize that stress levels, as measured by the PSS-4 (Perceived Stress Scale), can be predicted through the analysis of journaling entries using NLP. Moreover, we expect that higher state self-control (measured by two items from the SSCCS - State Self-Control Capacity Scale) will be associated with greater adherence to the study, while higher trait self-control (measured by the SCS-K-D - German adaption of the short form of the Self-Control Scale) will be negatively correlated with dropout rates. Lastly, we anticipate that participants will evaluate the individual feedback positively.	—

Measure

Time frame

Additionally, we hypothesize that stress levels, as measured by the PSS-4 (Perceived Stress Scale), can be predicted through the analysis of journaling entries using NLP. Moreover, we expect that higher state self-control (measured by two items from the SSCCS - State Self-Control Capacity Scale) will be associated with greater adherence to the study, while higher trait self-control (measured by the SCS-K-D - German adaption of the short form of the Self-Control Scale) will be negatively correlated with dropout rates. Lastly, we anticipate that participants will evaluate the individual feedback positively.

—

Countries

Germany

Contacts

Public ContactNadine Nicole Schmitt

Universitätsklinikum Tübingen - Abteilung Psychiatrie, Psychosomatik und Psychotherapie im Kindes- und Jugendalter

nadine.schmitt@med.uni-tuebingen.de+49 1637949042

Outcome results

None listed

Source: DRKS (via WHO ICTRP) · Data processed: Aug 30, 2026