{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T17:36:43Z","timestamp":1770226603194,"version":"3.49.0"},"reference-count":34,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T00:00:00Z","timestamp":1770163200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Big Data"],"abstract":"<jats:p>Millions of people around the world suffer from depression. While early diagnosis is essential for timely intervention, it remains a significant challenge due to limited access to clinically diagnosed data and privacy restrictions on mental health records. These limitations hinder the training of robust AI models for depression detection. To tackle this, this article proposes a parallel transfer learning framework for depression detection that integrates BERT and T5 through a fusion mechanism, combining the complementary advantages of these two large language models (LLMs). By integrating their semantic embeddings, the method captures a broader range of linguistic cues from transcribed speech. These embeddings are processed through a model with two parallel branches: a one-dimensional convolutional neural network and a dense neural network are used to construct each branch for preliminary prediction, which are then fused for final prediction. Evaluations on the E-DAIC dataset demonstrate that the proposed method outperforms baseline models, achieving a 3.0% increase in accuracy (91.3%), a 6.9% increase in precision (95.2%), and a 1.7% improvement in F1-score (90.0%). The experimental results verify the effectiveness of BERT and T5 fusion in enhancing depression detection performance and highlight the potential of transfer learning for scalable and privacy-conscious mental health applications.<\/jats:p>","DOI":"10.3389\/fdata.2025.1651290","type":"journal-article","created":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T05:34:56Z","timestamp":1770183296000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Depression detection through dual-stream modeling with large language models: a fusion-based transfer learning framework integrating BERT and T5 representations"],"prefix":"10.3389","volume":"8","author":[{"given":"Na","family":"Wang","sequence":"first","affiliation":[{"name":"Faculty of Engineering, Universiti Putra Malaysia, UPM Serdang, Serdang","place":["Selangor, Malaysia"]},{"name":"School of Information and Physical Sciences, The University of Newcastle","place":["Callaghan, NSW, Australia"]},{"name":"School of Automation, Guangdong Polytechnic Normal University, Guangzhou","place":["Guangdong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weijia","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Physical Sciences, The University of Newcastle","place":["Callaghan, NSW, Australia"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raja","family":"Kamil","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Universiti Putra Malaysia, UPM Serdang, Serdang","place":["Selangor, Malaysia"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ian","family":"Renner","sequence":"additional","affiliation":[{"name":"School of Information and Physical Sciences, The University of Newcastle","place":["Callaghan, NSW, Australia"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Syed","family":"Abdul Rahman Al-Haddad","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Universiti Putra Malaysia, UPM Serdang, Serdang","place":["Selangor, Malaysia"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Normala","family":"Ibrahim","sequence":"additional","affiliation":[{"name":"Faculty of Medicine and Health Sciences, Universiti Putra Malaysia, UPM Selangor","place":["Selangor, Malaysia"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Faculty of Engineering, Universiti Malaya","place":["Kuala Lumpur, Malaysia"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,2,4]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2619","DOI":"10.1038\/s41598-022-06392-4","article-title":"Using absolutist word frequency from online searches to measure population mental health dynamics","volume":"12","author":"Adam-Troian","year":"2022","journal-title":"Sci. Rep"},{"key":"B2","doi-asserted-by":"publisher","first-page":"2074","DOI":"10.1109\/TCSS.2022.3200213","article-title":"Depression screening in humans with ai and deep learning techniques","volume":"10","author":"Ahmad Wani","year":"2023","journal-title":"IEEE Trans. Comput. Soc. Syst"},{"key":"B3","doi-asserted-by":"crossref","first-page":"1044","DOI":"10.1109\/ISDA.2011.6121796","article-title":"\u201cTF-SIDF: term frequency, sketched inverse document frequency, \u201d","volume-title":"2011 11th International Conference on Intelligent Systems Design and Applications","author":"Baena-Garc\u00eda","year":"2011"},{"key":"B4","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1007\/s13755-024-00303-9","article-title":"Explainable depression symptom detection in social media","volume":"12","author":"Bao","year":"2024","journal-title":"Health Inform. Sci. Syst."},{"key":"B5","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1207\/s15327752jpa6703_13","article-title":"Comparison of beck depression inventories-IA and-II in psychiatric outpatients","volume":"67","author":"Beck","year":"1996","journal-title":"J. Pers. Assess"},{"key":"B6","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1109\/TAFFC.2023.3238007","article-title":"Towards emotion-aware agents for improved user satisfaction and partner perception in negotiation dialogues","volume":"15","author":"Chawla","year":"2024","journal-title":"IEEE Trans. Affect, Comput"},{"key":"B7","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1017\/S1351324916000334","article-title":"Word2Vec","volume":"23","author":"Church","year":"2017","journal-title":"Nat. Lang. Eng"},{"key":"B8","author":"[Dataset] Devlin","year":"2019","journal-title":"BERT: pre-training of deep bidirectional transformers for language understanding"},{"key":"B9","author":"[Dataset] Liu","year":"2019","journal-title":"RoBERTa: a robustly optimized BERT pretraining approach"},{"key":"B10","article-title":"\u201cLearning from imbalanced data sets,\u201d","volume-title":"Springer Handbook of Computational Intelligence","author":"Fern\u00e1ndez","year":"2015"},{"key":"B11","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","article-title":"Framewise phoneme classification with bidirectional LSTM and other neural network architectures","volume":"18","author":"Graves","year":"2005","journal-title":"Neural Netw"},{"key":"B12","doi-asserted-by":"publisher","first-page":"13075","DOI":"10.1007\/s11227-023-05168-5","article-title":"Textual emotion detection utilizing a transfer learning approach","volume":"79","author":"Hadikhah Mozhdehi","year":"2023","journal-title":"J. Supercomput"},{"key":"B13","doi-asserted-by":"publisher","first-page":"e42","DOI":"10.1016\/S0140-6736(18)32408-5","article-title":"Reducing the global burden of depression: a lancet-world psychiatric association commission","volume":"393","author":"Herrman","year":"2019","journal-title":"Lancet"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1746","DOI":"10.3115\/v1\/D14-1181","article-title":"\u201cConvolutional neural networks for sentence classification,\u201d","author":"Kim","year":"2014","journal-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"B16","first-page":"396","article-title":"Handwritten digit recognition with a back-propagation network","volume":"2","author":"LeCun","year":"1989","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1109\/TCSS.2023.3263056","article-title":"Detecting depression with heterogeneous graph neural network in clinical interview transcript","volume":"11","author":"Li","year":"2024","journal-title":"IEEE Trans. Comput. Soc. Syst"},{"key":"B18","doi-asserted-by":"publisher","first-page":"103917","DOI":"10.1016\/j.ipm.2024.103917","article-title":"QAIE: LLM-based quantity augmentation and information enhancement for few-shot aspect-based sentiment analysis","volume":"62","author":"Lu","year":"2025","journal-title":"Inform. Process. Manag"},{"key":"B19","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/s40708-023-00185-9","article-title":"Towards automatic text-based estimation of depression through symptom prediction","volume":"10","author":"Milintsevich","year":"2023","journal-title":"Brain Inform"},{"key":"B20","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Machine Learn. Res"},{"key":"B21","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/s10742-024-00329-2","article-title":"Multimodal mental state analysis","volume":"25","author":"Rai","year":"2024","journal-title":"Health Serv. Outcomes Res. Methodol"},{"key":"B22","doi-asserted-by":"publisher","first-page":"119862","DOI":"10.1016\/j.eswa.2023.119862","article-title":"A review on sentiment analysis from social media platforms","volume":"223","author":"Rodr\u00edguez-Ib\u00e1nez","year":"2023","journal-title":"Expert Syst. Appl"},{"key":"B23","doi-asserted-by":"publisher","first-page":"e73","DOI":"10.1192\/bjo.2018.90","article-title":"Strengthening mental health systems in low-and middle-income countries: recommendations from the emerald programme","volume":"5","author":"Semrau","year":"2019","journal-title":"BJPsych Open"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1737","DOI":"10.1001\/jama.282.18.1737","article-title":"Validation and utility of a self-report version of prime-MD: the PHQ primary care study","volume":"282","author":"Spitzer","year":"1999","journal-title":"JAMA"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1257591","DOI":"10.3389\/fbioe.2023.1257591","article-title":"Enhancing accuracy in brain stroke detection: multi-layer perceptron with adadelta, RMSProp and AdaMax optimizers","volume":"11","author":"Uppal","year":"2023","journal-title":"Front. Bioeng. Biotechnol"},{"key":"B26","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B27","first-page":"557","article-title":"\u201cApproximating the mental lexicon from clinical interviews as a support tool for depression detection,\u201d","volume-title":"Proceedings of the 2021 International Conference on Multimodal Interaction, ICMI '21","author":"Villatoro-Tello","year":"2021"},{"key":"B28","doi-asserted-by":"publisher","first-page":"3054","DOI":"10.37256\/cm.6320256184","article-title":"Enhancing AI depression detection using transfer learning","volume":"6","author":"Wang","year":"2025","journal-title":"Contemp. Math"},{"key":"B29","doi-asserted-by":"publisher","first-page":"3714","DOI":"10.3390\/s23073714","article-title":"Metaheuristic optimization-based feature selection for imagery and arithmetic tasks: an fNIRS study","volume":"23","author":"Zafar","year":"2023","journal-title":"Sensors"},{"key":"B30","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.patrec.2024.01.005","article-title":"Multilevel depression status detection based on fine-grained prompt learning","volume":"178","author":"Zhang","year":"2024","journal-title":"Pattern Recognit. Lett"},{"key":"B31","doi-asserted-by":"publisher","first-page":"103876","DOI":"10.1016\/j.ipm.2024.103876","article-title":"Leveraging sensory knowledge into text-to-text transfer transformer for enhanced emotion analysis","volume":"62","author":"Zhao","year":"2025","journal-title":"Inform. Proces. Manag"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1038636","DOI":"10.3389\/fncom.2023.1038636","article-title":"Conventional machine learning and deep learning in alzheimer's disease diagnosis using neuroimaging: a review","volume":"17","author":"Zhao","year":"2023","journal-title":"Front. Comput. Neurosci"},{"key":"B33","first-page":"19","article-title":"\u201cAligning books and movies: towards story-like visual explanations by watching movies and reading books,\u201d","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Zhu","year":"2015"},{"key":"B34","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1001\/archpsyc.1965.01720310065008","article-title":"A self-rating depression scale","volume":"12","author":"Zung","year":"1965","journal-title":"Arch. Gen. Psychiatry"}],"container-title":["Frontiers in Big Data"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2025.1651290\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T05:34:58Z","timestamp":1770183298000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2025.1651290\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,4]]},"references-count":34,"alternative-id":["10.3389\/fdata.2025.1651290"],"URL":"https:\/\/doi.org\/10.3389\/fdata.2025.1651290","relation":{},"ISSN":["2624-909X"],"issn-type":[{"value":"2624-909X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,4]]},"article-number":"1651290"}}