This study aimed to develop innovative media using artificial intelligence (AI) to predict depression from social media texts. Utilizing natural language processing techniques and machine learning algorithms, the developed model focused on analyzing words, messages, or images that tend to indicate negative, neutral, or positive emotional states. Data were sourced from social media platforms such as Facebook, X (Twitter), and Instagram. These data were processed through sentiment analysis to categorize the messages into three levels of severity: severe, moderate, and mild. The predictive data were validated by experts from various fields, including computer science and information technology, psychology, and media studies, to ensure accuracy and reduce potential biases in the model. The findings indicated that the naïve Bayes classifier demonstrates the highest efficiency in predicting negative sentiment, achieving an average accuracy of 88.17% for training sets and 85.00% for testing sets. The F1-measure for negative messages reached 76.70%, reflecting the model’s strong capability to detect depression-related text. However, the model encountered limitations in predicting neutral messages, particularly those involving sarcasm or metaphorical expressions. This research highlights the potential of AI applications in predicting and managing depression on social media. The system can provide timely alerts to individuals at risk and recommend seeking professional psychiatric consultation, offering an effective approach for early detection and intervention in depressive disorders.

1. [1] P. Wongvachrapaiboon, “In 2024, 17.20% of Thai people are at risk of depression, and 15.48% experience high stress; highlighting the case of a “pharmacist” facing pressure,” 2024 (in Thai). https://www.hfocus.org/content/2024/11/32116 [Accessed May 20, 2025]
2. [2] A. Nabi, M. A. Dar, M. A. Dar, and Z. Maqbool, “Depression Diagnosis with Artificial Intelligence: A Bibliometric Analysis,” J. for ReAttach Therapy and Developmental Diversities, Vol.6, No.7s, pp. 1063-1072, 2023. https://doi.org/10.53555/jrtdd.v6i7s.2791
3. [3] K. U. Philips, “The Future of Feeling: Building Empathy in a Tech-Obsessed World,” Little A, 2021.
4. [4] Y. Wongpiriyansant, “Build mindfulness, heal the mind, fight COVID-19,” Nanmeebooks, 2020.
5. [5] Y.-H. Lin and L. Pai, “When depressy strikes, hold it tight,” Eurasian, 2017.
6. [6] K. Khamkliang, “Feeling down? You can get through it,” Nation Books, 2020.
7. [7] B. Yalamanchili, N. S. Kota, M. S. Abbaraju, V. S. S. Nadella, and S. V. Alluri, “Real-time Acoustic based Depression Detection using Machine Learning Techniques,” 2020 Int. Conf. on Emerging Trends in Information Technology and Engineering (ic-ETITE), 2020. https://doi.org/10.1109/ic-ETITE47903.2020.394
8. [8] S. T. Sadasivuni and Y. Zhang, “A New Method for Discovering Daily Depression from Tweets to Monitor People’s Depression Status,” 2020 IEEE Int. Conf. on Humanized Computing and Communication with Artificial Intelligence (HCCAI), pp. 47-50, 2020. https://doi.org/10.1109/HCCAI49649.2020.00013
9. [9] X. Chen, “Research on Depression Recognition Based on University Students’ Facial Expressions and Actions with the Assistance of Artificial Intelligence,” J. Adv. Comput. Intell. Intell. Inform., Vol.28, No.5, pp. 1126-1131, 2024. https://doi.org/10.20965/jaciii.2024.p1126
10. [10] A. A. Jo, E. D. Raj, A. S. Vino, and P. K. Menon, “Exploring Explainable AI for Enhanced Depression Prediction in Mental Health,” 2024 First Int. Conf. on Innovations in Communications, Electrical and Computer Engineering (ICICEC), 2024. https://doi.org/10.1109/icicec62498.2024.10808414
11. [11] N. R. Kanchapogu and S. N. Mohanty, “Enhancing Depression Predictive Models: A Comparative Study of Hybrid AI, Machine Learning and Deep Learning Techniques,” Research Square, 2024. https://doi.org/10.21203/rs.3.rs-3992742/v1
12. [12] V. Nuipain, K. Plangklang, and S. Hanumas, “Depression risk prediction system using text mining techniques,” Proc. of the 20th National Conf. on Computing and Information Technology, pp. 42-47, 2024.
13. [13] K. Fuangngam, N. Bhumpenpein, and S. Nuchitprasitchai, “A sentiment analysis model for double negative in Thai language,” Proc. of the 20th National Conf. on Computing and Information Technology, pp. 48-53, 2024.
14. [14] P. Naphakorn, A. Bunteong, K. Sattratham, and K. Leknawa, “Development of a visual novel game prototype to enhance communication skills with individuals experiencing depression,” Proc. of the 21st National Conf. on Computing and Information Technology, 2025.
15. [15] L. Mookdasanit, “Natural Language Processing,” Triple Group, 2022.
16. [16] S. Rattanapojanart, “In 2024, 17.20% of Thai people are at risk of depression, and 15.48% experience high stress; highlighting the case of a “pharmacist” facing pressure,” 2024. https://www.hfocus.org/content/2024/11/32116 [Accessed May 20, 2025]
17. [17] R. Kumar and D. Singh, “Effects of Social Media on Mental Health: A Review,” J. of Survey in Fisheries Sciences, Vol.10, Issue 1, pp. 3717-3721, 2023. https://doi.org/10.53555//sfs.v10i1.1658
18. [18] B. Ridout and A. Campbell, “The Use of Social Networking Sites in Mental Health Interventions for Young People: Systematic Review,” J. of Medical Internet Research, Vol.20, No.12, Article No.12244, 2018. https://doi.org/10.2196/12244
19. [19] P. Apakhajorn, “The reality of the online world: A truth that the government must pay attention to,” 2016 (in Thai). https://www.isranews.org/isranews/49987-a_49987.html [Accessed February 11, 2021]
20. [20] O. Ulvi, A. Karamehic-Muratovic, M. Baghbanzadeh, A. Bashir, J. Smith, and U. Haque, “Social Media Use and Mental Health: A Global Analysis,” Epidemiologia, Vol.3, Issue 1, pp. 11-25, 2022. https://doi.org/10.3390/epidemiologia3010002
21. [21] T. Ikbal, “A Comprehensive Evaluation of the Impact of Social Media on Mental Health Reveals Noteworthy Effects,” Praxis Int. J. of Social Science and Literature, Vol.6, Issue 8, pp. 64-72, 2023. https://doi.org/10.51879/pijssl/060807
22. [22] A. Aldkheel and L. Zhou, “Depression Detection on Social Media: A Classification Framework and Research Challenges and Opportunities,” J. of Healthcare Informatics Research, Vol.8, pp. 88-120, 2024. https://doi.org/10.1007/s41666-023-00152-3
23. [23] SAS Software, “Natural Language Processing: Definition and Importance,” 2021 (in Thai). https://www.sas.com/th_th/insights/analytics/what-is-natural-language-processing-nlp.html [Accessed November 16, 2021]
24. [24] Y. Zhou, “Depression Prediction Model Based on NLP,” Applied and Computational Engineering, Vol.109, No.1, pp. 109-112, 2024. https://doi.org/10.54254/2755-2721/109/20241284
25. [25] P. Nakwijit, “Understanding transformer [Part III],” 2020 (in Thai). https://medium.com/@chameleontk/-transformer-part-iii-2f36fb256f0c [Accessed September 10, 2024]
26. [26] Quora, “Which are the weaknesses of transformers in deep learning?,” 2024. https://www.quora.com/Which-are-the-weaknesses-of-transformers-in-deep-learning [Accessed September 10, 2024]
27. [27] A. Vaswani et al., “Attention is all you need,” Proc. of the 31st Int. Conf. on Neural Information Processing Systems (NIPS’17), pp. 6000-6010, 2017.
28. [28] J. Zhang et al., “Data augmentation for transformer-based neural networks in speech translation,” IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), pp. 6309-6331, 2020.
29. [29] J. Ardharn, “Text-based depression detection on social media using deep learning,” A Master’s Project for Master of Science, Faculty of Science, Srinakharinwirot University, 2023.
30. [30] D. Duernrubroem, C. Charoenphol, and J. Jiranukul, “A comparison of data mining structure efficiency for classifying depression from Twitter posting behavior,” Mahasarakham University J. of Science and Technology, Vol.39, No.3, pp. 331-343, 2016.
31. [31] I. C. Obagbuwa, S. Danster, and O. C. Chibaya, “Supervised machine learning models for depression sentiment analysis,” Frontiers in Artificial Intelligence, Vol.6, 2023. https://doi.org/10.3389/frai.2023.1230649
32. [32] L. P. Hung and S. Alias, “Beyond Sentiment Analysis: A Review of Recent Trends in Text Based Sentiment Analysis and Emotion Detection,” J. Adv. Comput. Intell. Intell. Inform., Vol.27, No.1, pp. 84-95, 2023. https://doi.org/10.20965/jaciii.2023.p0084
33. [33] N. V. Babu and E. G. M. Kanaga, “Sentiment Analysis in Social Media Data for Depression Detection Using Artificial Intelligence: A Review,” SN Computer Science, Vol.3, Article No.74, 2022. https://doi.org/10.1007/s42979-021-00958-1
34. [34] W. Phatthiyaphaibun, “Thai Sentiment Text,” 2017. https://github.com/pythainlp/lexicon-thai/tree/master/ข้อความ [Accessed March 1, 2022]
35. [35] S. R. Kamite and V. B. Kamble, “Detection of Depression in Social Media via Twitter Using Machine learning Approach,” 2020 Int. Conf. on Smart Innovations in Design, Environment, Management, Planning and Computing (ICSIDEMPC), pp. 122-125, 2020. https://doi.org/10.1109/ICSIDEMPC49020.2020.9299641
36. [36] J. Jingjit and V. Asawaranun, “Learning data science principles with Python (1st ed.),” Core Function, 2020.
37. [37] B. Pasilatetsang, “Creating learning for AI with Python machine learning,” SE-ED Education, 2021.
38. [38] N. Charoenkiattiboon, “Using data mining techniques to assist in academic advising for higher education,” Master’s thesis of Computer Sciences, Silpakorn University, 2007.
39. [39] T. Wannaprapha, “Using data mining techniques for screening people successfully in undergraduate studies of educational technology,” Master’s thesis of Engineering, College of Innovation Technology and Engineering, Dhurakij Pundit University, 2021.
40. [40] M. Keerthiga et al., “Machine Learning-based Depression Prediction using Social Media Feeds,” 2023 Int. Conf. on Inventive Computation Technologies (ICICT), pp. 863-869, 2023. https://doi.org/10.1109/ICICT57646.2023.10134427
41. [41] Y. He, L. Ji, R. Qian, and W. Gu, “A Text-Based Suicide Detection Model Using Hybrid Prompt Tuning in Few-Shot Scenarios,” J. Adv. Comput. Intell. Intell. Inform., Vol.29, No.3, pp. 649-658, 2025. https://doi.org/10.20965/jaciii.2025.p0649
42. [42] M. Hämäläinen, P. Patpong, K. Alnajjar, N. Partanen, and J. Rueter, “Detecting Depression in Thai Blog Posts: A Dataset and a Baseline,” Proc. of the 7th Workshop on Noisy User-generated Text (W-NUT 2021), pp. 20-25, 2021. https://doi.org/10.18653/v1/2021.wnut-1.3
43. [43] S. Mahasiriakalayot, T. Senivongse, and N. Taephant, “Predicting Signs of Depression from Twitter Messages,” 2022 19th Int. Joint Conf. on Computer Science and Software Engineering (JCSSE), 2022. https://doi.org/10.1109/JCSSE54890.2022.9836287
44. [44] S. Fara, O. Hickey, A. L. Georgescu, S. Goria, E. Molimpakis, and N. Cummins, “Bayesian networks for the robust and unbiased prediction of depression and its symptoms utilizing speech and multimodal data,” 2022.
45. [45] B. Ojeme and A. Mbogho, “Predictive Strength of Bayesian Networks for Diagnosis of Depressive Disorders,” I. Czarnowski et al. (Eds.), “Intelligent Decision Technologies 2016,” Smart Innovation, Systems and Technologies (SIST), Vol.56, pp. 373-382, Springer, 2016. https://doi.org/10.1007/978-3-319-39630-9_31
46. [46] M. F. Guiñazú, M. González, R. B. Ruiz, V. Hernández, S. B. Diez, and J. D. Velásquez, “A novel depression risk prediction model based on data fusion from Chilean National Health Surveys to diagnose risk depression among patients with mood disorders,” Information Fusion, Vol.100, Article No.101960, 2023. https://doi.org/10.1016/j.inffus.2023.101960
47. [47] V. A. S. Putri, A. V. Vitianingsih, R. Hamidan, A. L. Maukar, and N. T. Pratitis, “Sentiment Analysis on Social Media Instagram of Depression Issues Using Naïve Bayes Method,” J. Inovtek Polbeng Seri Informatika, Vol.9, No.2, pp. 802-813, 2024. https://doi.org/10.35314/spchsk42
48. [48] P. Panluck and P. Boonrawd, “Sentiment analysis for monkeypox outbreak using BERT model,” Proc. of the 20th National Conf. on Computing and Information Technology, pp. 78-83, 2024.
49. [49] C. Wongsin, N. Srikarnjanaperd, and J. Polpinij, “Automatic feeling analysis from opinion text,” Proc. of the 11th National Conf. on Computing and Information Technology, 2015.
50. [50] W. Thurachon, W. Sumethawatthanaphong, and N. Songsook, “Classification system para rubber varieties using Naïve Bayes,” Proc. of the 10th National Conf. on Computing and Information Technology, 2014.
51. [51] Facebook1, “Depression,” 2022. https://www.facebook.com/search/pages?q=ซึมเศร้า [Accessed February 15, 2022]
52. [52] Facebook2, “Depression,” 2022. https://www.facebook.com/search/groups?q=ซึมเศร้า [Accessed February 15, 2022]
53. [53] Instagram, “#Depression,” 2022. https://www.instagram.com/explore/tags/โรคซึมเศร้า/ [Accessed February 15, 2022]
54. [54] M. Q. Patton, “How to Use Qualitative Methods in Evaluation,” Sage Publications, 1987.
55. [55] C. Photisita, “The art and science of qualitative research (4th ed.),” Institute for Population and Social Research, Mahidol University, 2009.
56. [56] MedPark Hospital, “Depression Test,” 2025 (in Thai). https://www.medparkhospital.com/disease-and-treatment/depression-tests [Accessed May 20, 2025]
57. [57] Department of Mental Health, Ministry of Public Health, “Guidelines for provincial monitoring and surveillance of depression (3rd Revised Edition, 2014),” 2014. https://vjlh.go.th/booking/upload_file2/2450661385f86a43f9e92d.pdf [Accessed May 20, 2025]
58. [58] P. Pasunon, “Validity of questionnaire for social science research,” J. of Social Sciences Srinakarinwirot University, Vol.18, pp. 375-396, 2015.
59. [59] S. Piboon, “Development of rating scale tools in research,” 2009 (in Thai). https://www.gotoknow.org/posts/238980 [Accessed December 28, 2021]
60. [60] J. W. Best, “Research in Education (3rd ed.),” Prentice-Hall, Inc., 1977.
61. [61] P. Sirisuwan, “The effect of health promotion program for preventing new diabetes cases in Singhok Subdistrict, Kaset Wisai District, Roi Et Province,” Boromarajonani College of Nursing Surin, Vol.8, No.1, pp. 45-58, 2018.
62. [62] T. K. Koo and M. Y. Li, “A Guideline of Selecting and Reporting Intraclass Correlation Coefficients for Reliability Research,” J. of Chiropractic Medicine, Vol.15, Issue 2, pp. 155-163, 2016. https://doi.org/10.1016/j.jcm.2016.02.012
63. [63] J. M. Fisher, “First grader’s perception of their learning: A qualitative study of motivation for literacy,” Dissertation Abstract International, Vol.59, No.6, Article No.1903-A, 1998.
64. [64] S. Jalukar, A. Ratnaparkhi, P. Shinde, S. Kunkulol, and V. Kulkarni, “Sentiment Analysis for Depression Detection,” Int. J. of Trendy Research in Engineering and Technology, Vol.6, Issue 3, pp. 17-22, 2022. https://doi.org/10.54473/IJTRET.2022.6305
65. [65] M. Deshpande and V. Rao, “Depression detection using emotion artificial intelligence,” 2017 Int. Conf. on Intelligent Sustainable Systems (ICISS), pp. 858-862, 2017. https://doi.org/10.1109/ISS1.2017.8389299
66. [66] P. M. Jadhav, Sonia, and A. N. Kulkarni, “Depression Predicting Model For Social Media User’s Emotions Using Deep Learning Methods,” Mathematics and Applied Sciences, Vol.44, No.S8, pp. 194-201, 2023. https://doi.org/10.53555/jaz.v44iS8.3538
67. [67] G. Zhu, L. Li, Y. Zheng, X. Zhang, and H. Zou, “Forecasting Influenza Based on Autoregressive Moving Average and Holt-Winters Exponential Smoothing Models,” J. Adv. Comput. Intell. Intell. Inform., Vol.25, No.1, pp. 138-144, 2021. https://doi.org/10.20965/jaciii.2021.p0138
68. [68] M. Usman, S. Haris, and A. C. M. Fong, “Prediction of Depression Using Machine Learning Techniques: A Review of Existing Literature,” 2020 IEEE 2nd Int. Workshop on System Biology and Biomedical Systems (SBBS), 2020. https://doi.org/10.1109/SBBS50483.2020.9314940
69. [69] I. N. Joharee, N. N. W. N. Hashim, and N. S. M. Shah, “Sentiment Analysis and Text Classification for Depression Detection,” J. of Integrated and Advanced Engineering, Vol.3, No.1, pp. 65-78, 2023. https://doi.org/10.51662/jiae.v3i1.86