Abstract
Recently, the swift increase of social media platforms has provided a rich source for studying several users’ psychological phenomena. For instance, stress identification in text content can lead to knowing some insights about social media users’ mental health. Actually, chronic stress has a huge negative impact that requires the development of different methods for early detection and diagnosis. In this paper, we propose a deep learning approach and a Natural Language Processing (NLP) method to reveal self-reported chronic stress from tweets. In effect, we have implemented distinct pre-trained BERT (Bi-directional Encoder Representations from Transformers) embedding models, along with a BiLSTM (Bidirectional Long Short-Term Memory) classifier. Actually, we fine-tuned the pre-trained BERT models by leveraging their powerful contextual representation. Next, the output of the embedding is fed into a BiLSTM model which further refines the stress classification by capturing the sequential dependencies in the tweet text. Experiments disclosed that BERT with Talking-Heads Attention architecture is the best model for such text classification tasks. Moreover, our suggested model has achieved good performance and surpassed the baseline architectures for chronic stress detection in Twitter data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Pozos-Radillo, B.E., Preciado-Serrano, M.D.L., Acosta-Fernández, M., et al.: Academic stress as a predictor of chronic stress in university students. Psicol. Educ. 20, 47–52 (2014). https://doi.org/10.1016/j.pse.2014.05.006
Marin, M.F., Lord, C., Andrews, J., et al.: Chronic stress, cognitive functioning and mental health. Neurobiol. Learn. Mem. 96, 583–595 (2011). https://doi.org/10.1016/j.nlm.2011.02.016
Dai, S., Mo, Y., Wang, Y., et al.: Chronic stress promotes cancer development. Front. Oncol. 10, 1492 (2020). https://doi.org/10.3389/fonc.2020.01492
Girardi, D., Lanubile, F., Novielli, N.: Emotion detection using noninvasive low cost sensors. In: 2017 7th International Conference on Affective Computing and Intelligent Interaction, ACII 2017, pp. 125–130 (2018)
Tariq, S., Akhtar, N., Afzal, H., et al.: A novel co-training-based approach for the classification of mental illnesses using social media posts. IEEE Access 7, 166165–166172 (2019). https://doi.org/10.1109/ACCESS.2019.2953087
Lin, T., Chen, C., Tzeng, Y., Lee, L.: NCUEE-NLP@SMM4H’22: Classification of Self-reported Chronic Stress on Twitter Using Ensemble Pre-trained Transformer Models. In: Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task, Gyeongju, Republic of Korea, Association for Computational Linguistics, pp. 62–64 (2022)
Thammasan, N., Moriyama, K., Fukui, K., Numao, M.: Familiarity effects in EEG-based emotion recognition. Brain Inf. 4, 39–50 (2017). https://doi.org/10.1007/s40708-016-0051-5
Gaikwad, G., Joshi, D.J.: Multiclass Mood classification on twitter using lexicon dictionary and machine learning algorithms. Proc. Int. Conf. Inven. Comput. Technol. ICICT 2016, 1–6 (2016). https://doi.org/10.1109/INVENTIVE.2016.7823247
Yang, D., Li, W., Zhang, J., et al.: A neuropathological hub identification for Alzheimer’s disease via joint analysis of topological structure and neuropathological burden. In: Proceeding of the International Symposium on Biomedical Imaging, pp. 1–4, Mar 2022. https://doi.org/10.1109/ISBI52829.2022.9761444
Katchapakirin, K., Wongpatikaseree, K., Yomaboot, P., Kaewpitakkun, Y.: Facebook social media for depression detection in the Thai community. In: Proceeding of 2018 15th International Joint Conference on Computer Science and Software Engineering, JCSSE 2018, pp. 1–6 (2018). https://doi.org/10.1109/JCSSE.2018.8457362
Zanwar, S., Wiechmann, D., Qiao, Y., Kerz, E.: MANTIS at SMM4H’2022: pre-trained language models meet a suite of psycholinguistic features for the detection of self-reported chronic stress. In: Proceedings of the Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task, pp. 16–18 (2022)
Brain, G.: TensorFlow Hub. In: TensorFlow. https://tfhub.dev/s?module-type=text-embedding (2021). Accessed 26 May 2023
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019, vol. 1, pp. 4171–4186 (2019)
Wikimedia Foundation: Wikipedia Dataset (2018). https://dumps.wikimedia.org/. Accessed 30 June 2023
BooksCorpus Dataset. https://yknzhu.wixsite.com/mbweb. Accessed 30 May 2023
Turc, I., Chang, M.-W., Lee, K., Toutanova, K.: Well-read students learn better: on the importance of pre-training compact models (2019). https://doi.org/10.48550/arXiv.1908.08962. Accessed 30 May 2023
Lan, Z., Chen, M., Goodman, S., et al.: ALBERT: A Lite BERT for Self-supervised Learning of Language Representations (2019). https://doi.org/10.48550/arXiv.1909.11942. Accessed 30 May 2023
Clark, K., Luong, M.T., Le, Q.V., Manning, C.D.: Electra: pre-training text encoders as discriminators rather than generators. In: 8th International Conference on Learning Representations, ICLR 2020, pp. 1–18 (2020). https://doi.org/10.48550/arXiv.2003.10555. Accessed 30 May 2023
MEDLINE/PubMed Dataset. https://www.nlm.nih.gov/databases/download/pubmed_medline.html. Accessed 30 May 2023
Shazeer, N., Lan, Z., Cheng, Y., Nan Ding, L.H.: Talking-Heads Attention (2020). https://doi.org/10.48550/arXiv.2003.02436. Accessed 30 May 2023
Shazeer, N.: GLU Variants Improve Transformer (2020). https://doi.org/10.48550/arXiv.2002.05202. Accessed 30 May 2023
Weissenbacher, D., Klein, A.Z., Gascó, L., et al.: Overview of the seventh social media mining for health applications #SMM4H shared tasks at COLING 2022. In: Proceedings of the Seventh Social Media Mining for Health (#SMM4H) Workshop and Shared Task, pp. 221–241 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Qorich, M., Ouazzani, R.E. (2024). BERT-Based Models with BiLSTM for Self-chronic Stress Detection in Tweets. In: Farhaoui, Y., Hussain, A., Saba, T., Taherdoost, H., Verma, A. (eds) Artificial Intelligence, Data Science and Applications. ICAISE 2023. Lecture Notes in Networks and Systems, vol 838. Springer, Cham. https://doi.org/10.1007/978-3-031-48573-2_54
Download citation
DOI: https://doi.org/10.1007/978-3-031-48573-2_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48572-5
Online ISBN: 978-3-031-48573-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)