{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:41:19Z","timestamp":1777891279180,"version":"3.51.4"},"reference-count":38,"publisher":"MDPI AG","issue":"24","license":[{"start":{"date-parts":[[2022,12,13]],"date-time":"2022-12-13T00:00:00Z","timestamp":1670889600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Korean Government (MSIT)","award":["2022-0-01200"],"award-info":[{"award-number":["2022-0-01200"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In today\u2019s world, mental health diseases have become highly prevalent, and depression is one of the mental health problems that has become widespread. According to WHO reports, depression is the second-leading cause of the global burden of diseases. In the proliferation of such issues, social media has proven to be a great platform for people to express themselves. Thus, a user\u2019s social media can speak a great deal about his\/her emotional state and mental health. Considering the high pervasiveness of the disease, this paper presents a novel framework for depression detection from textual data, employing Natural Language Processing and deep learning techniques. For this purpose, a dataset consisting of tweets was created, which were then manually annotated by the domain experts to capture the implicit and explicit depression context. Two variations of the dataset were created, on having binary and one ternary labels, respectively. Ultimately, a deep-learning-based hybrid Sequence, Semantic, Context Learning (SSCL) classification framework with a self-attention mechanism is proposed that utilizes GloVe (pre-trained word embeddings) for feature extraction; LSTM and CNN were used to capture the sequence and semantics of tweets; finally, the GRUs and self-attention mechanism were used, which focus on contextual and implicit information in the tweets. The framework outperformed the existing techniques in detecting the explicit and implicit context, with an accuracy of 97.4 for binary labeled data and 82.9 for ternary labeled data. We further tested our proposed SSCL framework on unseen data (random tweets), for which an F1-score of 94.4 was achieved. Furthermore, in order to showcase the strengths of the proposed framework, we validated it on the \u201cNews Headline Data set\u201d for sarcasm detection, considering a dataset from a different domain. It also outmatched the performance of existing techniques in cross-domain validation.<\/jats:p>","DOI":"10.3390\/s22249775","type":"journal-article","created":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T03:21:52Z","timestamp":1670988112000},"page":"9775","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":67,"title":["Depression Detection Based on Hybrid Deep Learning SSCL Framework Using Self-Attention Mechanism: An Application to Social Networking Data"],"prefix":"10.3390","volume":"22","author":[{"given":"Aleena","family":"Nadeem","sequence":"first","affiliation":[{"name":"Department of Computer Software Engineering, National University of Sciences and Technology, Islamabad 44000, Pakistan"}]},{"given":"Muhammad","family":"Naveed","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Shaheed Zulfikar Ali Bhutto Institute of Science and Technology, Islamabad 44000, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4845-4808","authenticated-orcid":false,"given":"Muhammad","family":"Islam Satti","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Faculty of Computing, Riphah International University, Islamabad 46000, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9583-5585","authenticated-orcid":false,"given":"Hammad","family":"Afzal","sequence":"additional","affiliation":[{"name":"Department of Computer Software Engineering, National University of Sciences and Technology, Islamabad 44000, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0594-652X","authenticated-orcid":false,"given":"Tanveer","family":"Ahmad","sequence":"additional","affiliation":[{"name":"Innovation Education and Research Center for On-Device AI Software (Bk21), Department of Computer Science and Engineering, Chungnam National University, Daejeon 34134, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8366-3533","authenticated-orcid":false,"given":"Ki-Il","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Chungnam National University, Daejeon 34134, Republic of Korea"}]}],"member":"1968","published-online":{"date-parts":[[2022,12,13]]},"reference":[{"key":"ref_1","unstructured":"World Health Organization (2021, November 15). Depression. Available online: https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/depression."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Serrat, O. (2017). Social Network Analysis in Knowledge Solutions, Springer.","DOI":"10.1007\/978-981-10-0983-9"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1146\/annurev-publhealth-031912-114409","article-title":"The epidemiology of depression across cultures","volume":"34","author":"Kessler","year":"2013","journal-title":"Annu. Rev. Public Health"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1308","DOI":"10.1017\/S0033291717002781","article-title":"Trends in depression prevalence in the USA from 2005 to 2015: Widening disparities in vulnerable groups","volume":"48","author":"Weinberger","year":"2017","journal-title":"Psychol. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1109\/MCI.2014.2307227","article-title":"Jumping NLP curves: A review of natural language processing research","volume":"9","author":"Cambria","year":"2014","journal-title":"IEEE Comput. Intell. Mag."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"513","DOI":"10.3389\/fpsyg.2019.00513","article-title":"Text-Based Detection of the Risk of Depression","volume":"10","author":"Jana","year":"2019","journal-title":"Front. Psychol"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.eswa.2019.05.023","article-title":"A text classification framework for simple and effective early depression detection over social media streams","volume":"133","author":"Burdisso","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1177\/0165551519860469","article-title":"Exploring the dominant features of social media for depression detection","volume":"46","author":"Hussain","year":"2020","journal-title":"J. Inf. Sci."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1007\/s00521-021-06426-4","article-title":"Deep learning for prediction of depressive symptoms in a large textual dataset","volume":"34","author":"Uddin","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"23649","DOI":"10.1007\/s11042-022-12648-y","article-title":"An hybrid deep learning approach for depression prediction from user tweets using feature-rich CNN and bi-directional LSTM","volume":"81","author":"Kour","year":"2022","journal-title":"Multimed. Tools Appl."},{"key":"ref_11","first-page":"4395358","article-title":"Psychological Analysis for Depression Detection from Social Networking Sites","volume":"2022","author":"Gupta","year":"2022","journal-title":"Ment. Illn. Detect. Anal. Soc. Media"},{"key":"ref_12","first-page":"281","article-title":"Explainable depression detection with multi-aspect features using a hybrid deep learning model on social media","volume":"25","author":"Wang","year":"2022","journal-title":"Spec. Top. Issues Comput. Sci."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Stankevich, M., Isakov, V., Devyatkin, D., and Smirnov, I. (2018, January 16\u201318). Feature Engineering for Depression Detection in Social Media. Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods, Madeira, Portugal.","DOI":"10.5220\/0006598604260431"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1007\/s10844-020-00599-5","article-title":"Multimodal depression detection on instagram considering time interval of posts","volume":"56","author":"Chiu","year":"2021","journal-title":"J. Intell. Inf. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s13755-018-0046-0","article-title":"Depression detection from social network data using machine learning techniques","volume":"6","author":"Islam","year":"2018","journal-title":"Health Inf. Sci. Syst."},{"key":"ref_16","unstructured":"Md Zia Uddin, K.K.D., F\u00f8lstad, A., and Brandtzaeg, P. (2022). Automatic depression recognition by intelligent speech signal processing: A systematic survey. CAAI Transactions on Intelligence Technology, Wiley Online Library."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Solieman, H., and Pustozerov, E.A. (2021, January 26\u201329). The Detection of Depression Using Multimodal Models Based on Text and Voice Quality Features. Proceedings of the 2021 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (ElConRus), Moscow, Russia.","DOI":"10.1109\/ElConRus51938.2021.9396540"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s13721-020-0226-0","article-title":"Multi-modal social and psycho-linguistic embedding via recurrent neural networks to identify depressed users in online forums","volume":"9","author":"Shrestha","year":"2020","journal-title":"Netw. Model. Anal. Health Inform. Bioinform."},{"key":"ref_19","unstructured":"Dinkeland, H., Wu, M., and Yu, K. (2019). Text-based depression detection on sparse data. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Yang, L. (2019, January 3\u20136). Multi-Modal Depression Detection and Estimation. Proceedings of the 2019 8th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW), Cambridge, UK.","DOI":"10.1109\/ACIIW.2019.8925288"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"103427","DOI":"10.1016\/j.jbi.2020.103427","article-title":"Multi-modal interactive fusion method for detecting teenagers\u2019 psychological stress","volume":"106","author":"Zhanga","year":"2020","journal-title":"J. Biomed. Inform."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Huang, Z., Epps, J., and Joachim, D. (2020, January 4\u20138). Exploiting vocal tract coordination using dilated cnns for depression detection in naturalistic environments. Proceedings of the ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain.","DOI":"10.1109\/ICASSP40776.2020.9054323"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1109\/TAFFC.2018.2870398","article-title":"Integrating deep and shallow models for multi-modal depression analysis\u2014Hybrid architectures","volume":"12","author":"Yang","year":"2018","journal-title":"IEEE Trans. Affect. Comput."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1093\/jamia\/ocz221","article-title":"Depression screening using mobile phone usage metadata: A machine learning approach","volume":"27","author":"Razavi","year":"2020","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"16381","DOI":"10.1038\/s41598-020-72289-9","article-title":"Using machine learning-based analysis for behavioral differentiation between anxiety and depression","volume":"10","author":"Richter","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1258","DOI":"10.1016\/j.procs.2020.03.442","article-title":"Predicting anxiety, depression and stress in modern life using machine learning algorithms","volume":"167","author":"Priya","year":"2020","journal-title":"Procedia Comput. Sci."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1989","DOI":"10.1016\/j.procs.2020.04.213","article-title":"Assessment of anxiety, depression and stress using machine learning models","volume":"171","author":"Kumar","year":"2020","journal-title":"Procedia Comput. Sci."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Lam, G., Dongyan, H., and Lin, W. (2019, January 12\u201317). Context-aware deep learning for multi-modal depression detection. Proceedings of the ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK.","DOI":"10.1109\/ICASSP.2019.8683027"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zheng, W., Yan, L., Gou, C., and Wang, F.Y. (2020, January 6\u201310). Graph attention model embedded with multi-modal knowledge for depression detection. Proceedings of the 2020 IEEE International Conference on Multimedia and Expo (ICME), London, UK.","DOI":"10.1109\/ICME46284.2020.9102872"},{"key":"ref_30","unstructured":"Shalu, H., CN, H.S., Das, A., Majumder, S., Datar, A., MS, S.M., Das, A., and Kadiwala, J. (2020). Depression Status Estimation by Deep Learning based Hybrid Multi-Modal Fusion Model. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"101696","DOI":"10.1016\/j.artmed.2019.07.004","article-title":"Depression recognition using machine learning methods with different feature generation strategies","volume":"99","author":"LI","year":"2019","journal-title":"Artif. Intell. Med."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10916-019-1345-y","article-title":"Automated Depression Detection Using Deep Representation and Sequence Learning with EEG Signals","volume":"43","author":"Ay","year":"2019","journal-title":"J. Med. Syst."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1007\/s11571-020-09581-x","article-title":"The successful discrimination of depression from EEG could be attributed to proper feature extraction and not to a particular classification method","volume":"14","author":"Pokrajac","year":"2020","journal-title":"Cogn. Neurodynamics"},{"key":"ref_34","unstructured":"(2021, October 15). Depression Tweets Kaggle. Available online: https:\/\/www.kaggle.com\/datasets\/samrats\/depressiontweets?select=train2Data.csv."},{"key":"ref_35","unstructured":"(2022, May 11). Sarvcasm Detection Dataset Kaggle. Available online: https:\/\/www.kaggle.com\/saurabhbagchi\/sarcasm-detectio-through-nlp."},{"key":"ref_36","first-page":"8887","article-title":"Optimal feature extraction based machine learning approach for sarcasm type detection in news headlines","volume":"975","author":"Jariwala","year":"2020","journal-title":"Int. J. Comput. Appl."},{"key":"ref_37","first-page":"56","article-title":"Identification of Sarcasm in Textual Data: A Comparative Study","volume":"4","author":"Mehndiratta","year":"2019","journal-title":"Int. J. Comput. Appl."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Mandal, P.K., and Mahto, R. (2019). Deep CNN-LSTM with word embeddings for news headline sarcasm detection. 16th International Conference on Information Technology-New Generations (ITNG 2019), Springer.","DOI":"10.1007\/978-3-030-14070-0_69"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/24\/9775\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:40:27Z","timestamp":1760146827000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/24\/9775"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,13]]},"references-count":38,"journal-issue":{"issue":"24","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["s22249775"],"URL":"https:\/\/doi.org\/10.3390\/s22249775","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,13]]}}}