BERT and BERTopic for screening clinical depression on open-ended text messages collected through a mobile application from older adults
Abstract Background Despite the high suicide rate in South Korea, older adults are reluctant to see a psychiatrist. Recently, text mining has gained popularity to detect depression in social media posts, but older adults rarely use social media. However, more than 90% of them use smartphones. South...
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-06-01
|
| Series: | BMC Public Health |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12889-025-23337-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850100495493890048 |
|---|---|
| author | Moo-Kwon Chung Sang Yup Lee Taeksoo Shin Ji Young Park Sangwon Hwang Min-Hyuk Kim Jinhee Lee Kyoung-Joung Lee Hyo-Sang Lim Erdenebayar Urtnasan YeonSu Jung Dan-Kyung Kim Eunji Shin Jin-kyung Lee |
| author_facet | Moo-Kwon Chung Sang Yup Lee Taeksoo Shin Ji Young Park Sangwon Hwang Min-Hyuk Kim Jinhee Lee Kyoung-Joung Lee Hyo-Sang Lim Erdenebayar Urtnasan YeonSu Jung Dan-Kyung Kim Eunji Shin Jin-kyung Lee |
| author_sort | Moo-Kwon Chung |
| collection | DOAJ |
| description | Abstract Background Despite the high suicide rate in South Korea, older adults are reluctant to see a psychiatrist. Recently, text mining has gained popularity to detect depression in social media posts, but older adults rarely use social media. However, more than 90% of them use smartphones. South Korea has also made a public effort to utilize a mobile application to manage chronic health problems. In these situations, this study explores the possibility of screening the risk of depression through textual data reporting major stressors collected from older adults via a mobile application. Methods We collected the data regarding stress and depressive symptoms through our mobile application. Pre-trained Bidirectional Encoder Representations from Transformers (BERT)-based Natural Language Processing (NLP) models were utilized, using Python and the Hugging Face Transformers. A total of 1,332 text messages collected from 230 participants were analyzed using BERT modeling to detect clinical depression, as screened by the PHQ-9. For Korean data, we used KcBERT and KLUE BERT. BERTopic and dynamic BERTopic were used to see what stress topics appeared among a high-risk group and how they changed. Results The results demonstrate that KcBERT (precision = .89, recall = .86, F1 score = .87) was slightly better than KLUE BERT (precision = .81, recall = .78, F1 score = .79), although both performed well in identifying clinical depression. In BERTopic results, hierarchical clustering were re-grouped into four categories: financial problems, family-oriented stressful situations, physical and mental health problems, and work-related or acutely stressful situations. Dynamic BERTopic results show longitudinal changes. While event-related words such as family death or disease diagnosis were found more often for the cases when depression risk increased, words related to continued stressful situations appeared more often when the risk remained high. Conclusion These results imply that collecting respondents’ reports regarding stressful experiences can be useful to screen the risk of clinical depression. Including this function within a smartphone application publicly administered by community health care professionals can help monitor mental health in older adults. It can approach a hidden high-risk population suffering from depression in the community, providing enriched information about their risk factors. |
| format | Article |
| id | doaj-art-0651447c246a417e816e9cbfa7d684c9 |
| institution | DOAJ |
| issn | 1471-2458 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Public Health |
| spelling | doaj-art-0651447c246a417e816e9cbfa7d684c92025-08-20T02:40:17ZengBMCBMC Public Health1471-24582025-06-0125111410.1186/s12889-025-23337-4BERT and BERTopic for screening clinical depression on open-ended text messages collected through a mobile application from older adultsMoo-Kwon Chung0Sang Yup Lee1Taeksoo Shin2Ji Young Park3Sangwon Hwang4Min-Hyuk Kim5Jinhee Lee6Kyoung-Joung Lee7Hyo-Sang Lim8Erdenebayar Urtnasan9YeonSu Jung10Dan-Kyung Kim11Eunji Shin12Jin-kyung Lee13Department of Global Public Administration, Yonsei University Mirae CampusDepartment of Communication, Yonsei University Sinchon CampusDepartment of Business Administration, Yonsei University Mirae CampusDepartment of Social Welfare, Sangji UniversityDepartment of Precision Medicine, Yonsei University Wonju College of MedicineDepartment of Psychiatry, Yonsei University Wonju College of MedicineDepartment of Psychiatry, Yonsei University Wonju College of MedicinePresident, Songho UniversityDivision of Software, Yonsei University Mirae CampusInstitute of Yonsei AI Data Convergence Science, Yonsei University Mirae CampusInterdisciplinary Program in Comparative Literature, Yonsei University Sinchon CampusDepartment of Public Administration, Korea University Seoul CampusDivision of Health Administration, Yonsei University Mirae CampusMo-Im Kim Nursing Research Institute, Yonsei University Sinchon CampusAbstract Background Despite the high suicide rate in South Korea, older adults are reluctant to see a psychiatrist. Recently, text mining has gained popularity to detect depression in social media posts, but older adults rarely use social media. However, more than 90% of them use smartphones. South Korea has also made a public effort to utilize a mobile application to manage chronic health problems. In these situations, this study explores the possibility of screening the risk of depression through textual data reporting major stressors collected from older adults via a mobile application. Methods We collected the data regarding stress and depressive symptoms through our mobile application. Pre-trained Bidirectional Encoder Representations from Transformers (BERT)-based Natural Language Processing (NLP) models were utilized, using Python and the Hugging Face Transformers. A total of 1,332 text messages collected from 230 participants were analyzed using BERT modeling to detect clinical depression, as screened by the PHQ-9. For Korean data, we used KcBERT and KLUE BERT. BERTopic and dynamic BERTopic were used to see what stress topics appeared among a high-risk group and how they changed. Results The results demonstrate that KcBERT (precision = .89, recall = .86, F1 score = .87) was slightly better than KLUE BERT (precision = .81, recall = .78, F1 score = .79), although both performed well in identifying clinical depression. In BERTopic results, hierarchical clustering were re-grouped into four categories: financial problems, family-oriented stressful situations, physical and mental health problems, and work-related or acutely stressful situations. Dynamic BERTopic results show longitudinal changes. While event-related words such as family death or disease diagnosis were found more often for the cases when depression risk increased, words related to continued stressful situations appeared more often when the risk remained high. Conclusion These results imply that collecting respondents’ reports regarding stressful experiences can be useful to screen the risk of clinical depression. Including this function within a smartphone application publicly administered by community health care professionals can help monitor mental health in older adults. It can approach a hidden high-risk population suffering from depression in the community, providing enriched information about their risk factors.https://doi.org/10.1186/s12889-025-23337-4BERTText MiningTopic ModelingDepressionOlder Adults |
| spellingShingle | Moo-Kwon Chung Sang Yup Lee Taeksoo Shin Ji Young Park Sangwon Hwang Min-Hyuk Kim Jinhee Lee Kyoung-Joung Lee Hyo-Sang Lim Erdenebayar Urtnasan YeonSu Jung Dan-Kyung Kim Eunji Shin Jin-kyung Lee BERT and BERTopic for screening clinical depression on open-ended text messages collected through a mobile application from older adults BMC Public Health BERT Text Mining Topic Modeling Depression Older Adults |
| title | BERT and BERTopic for screening clinical depression on open-ended text messages collected through a mobile application from older adults |
| title_full | BERT and BERTopic for screening clinical depression on open-ended text messages collected through a mobile application from older adults |
| title_fullStr | BERT and BERTopic for screening clinical depression on open-ended text messages collected through a mobile application from older adults |
| title_full_unstemmed | BERT and BERTopic for screening clinical depression on open-ended text messages collected through a mobile application from older adults |
| title_short | BERT and BERTopic for screening clinical depression on open-ended text messages collected through a mobile application from older adults |
| title_sort | bert and bertopic for screening clinical depression on open ended text messages collected through a mobile application from older adults |
| topic | BERT Text Mining Topic Modeling Depression Older Adults |
| url | https://doi.org/10.1186/s12889-025-23337-4 |
| work_keys_str_mv | AT mookwonchung bertandbertopicforscreeningclinicaldepressiononopenendedtextmessagescollectedthroughamobileapplicationfromolderadults AT sangyuplee bertandbertopicforscreeningclinicaldepressiononopenendedtextmessagescollectedthroughamobileapplicationfromolderadults AT taeksooshin bertandbertopicforscreeningclinicaldepressiononopenendedtextmessagescollectedthroughamobileapplicationfromolderadults AT jiyoungpark bertandbertopicforscreeningclinicaldepressiononopenendedtextmessagescollectedthroughamobileapplicationfromolderadults AT sangwonhwang bertandbertopicforscreeningclinicaldepressiononopenendedtextmessagescollectedthroughamobileapplicationfromolderadults AT minhyukkim bertandbertopicforscreeningclinicaldepressiononopenendedtextmessagescollectedthroughamobileapplicationfromolderadults AT jinheelee bertandbertopicforscreeningclinicaldepressiononopenendedtextmessagescollectedthroughamobileapplicationfromolderadults AT kyoungjounglee bertandbertopicforscreeningclinicaldepressiononopenendedtextmessagescollectedthroughamobileapplicationfromolderadults AT hyosanglim bertandbertopicforscreeningclinicaldepressiononopenendedtextmessagescollectedthroughamobileapplicationfromolderadults AT erdenebayarurtnasan bertandbertopicforscreeningclinicaldepressiononopenendedtextmessagescollectedthroughamobileapplicationfromolderadults AT yeonsujung bertandbertopicforscreeningclinicaldepressiononopenendedtextmessagescollectedthroughamobileapplicationfromolderadults AT dankyungkim bertandbertopicforscreeningclinicaldepressiononopenendedtextmessagescollectedthroughamobileapplicationfromolderadults AT eunjishin bertandbertopicforscreeningclinicaldepressiononopenendedtextmessagescollectedthroughamobileapplicationfromolderadults AT jinkyunglee bertandbertopicforscreeningclinicaldepressiononopenendedtextmessagescollectedthroughamobileapplicationfromolderadults |