SavedAdd your journal

Journals / The International Journal of Energy and Engineering Sciences / 2024 / Volume: 9 Issue: 2

DETECTION OF DEPRESSION STATUS FROM TEXT USING NLP APPROACH: COMPARATIVE PERFORMANCE OF DIFFERENT ENSEMBLE ALGORITHMS

Zülfikar Aslan(Gaziantep Üniversitesi)0000-0002-2706-5715
Pages
—
Publication Date
2024-12-31
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The findings may contribute to the development of technology-supported approaches for early diagnosis and intervention in the field of mental health.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:This study aims to compare the performance of different ensemble learning algorithms using Natural Language Processing (NLP) approach for the detection of depression status from text.
📊
Key Findings & Data:A dataset consisting of 124,017 tweets collected between 2019-2020 was used in the study.
💡
Conclusion & Impact:The findings may contribute to the development of technology-supported approaches for early diagnosis and intervention in the field of mental health.
🔬Design:Modeling & Simulation
📍Scope:2019-2020 Verileri
⚙️Variables:Depression Detection · Natural Language Processing (NLP) · Ensemble Learning Algorithms

Abstract

This study aims to compare the performance of different ensemble learning algorithms using Natural Language Processing (NLP) approach for the detection of depression status from text. Depression is a common mental health problem worldwide and early diagnosis and intervention are of critical importance. A dataset consisting of 124,017 tweets collected between 2019-2020 was used in the study. These tweets were classified according to their depressive and non-depressive content. Five different ensemble learning algorithms, namely Random Forest, AdaBoost, Gradient Boosting, XGBoost and Voting Classifier, were applied in the study. The performance of the models was evaluated using various metrics such as accuracy, precision, recall and F1-score. In addition, ROC curves and learning curves were analyzed. The results revealed that all ensemble learning algorithms showed high performance, but Random Forest gave the best results in all metrics. Voting Classifier performed the second best, while Gradient Boosting performed relatively poorly. This study shows that ensemble learning algorithms are effective in detecting depression from text, and Random Forest in particular can be used as a potential screening tool in this area. The findings may contribute to the development of technology-supported approaches for early diagnosis and intervention in the field of mental health.

🔖

Cite This Article

Aslan, Z. (2024). DETECTION OF DEPRESSION STATUS FROM TEXT USING NLP APPROACH: COMPARATIVE PERFORMANCE OF DIFFERENT ENSEMBLE ALGORITHMS. The International Journal of Energy and Engineering Sciences, Volume: 9 Issue: 2. https://ajindex.com/articles/1551691

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (21)

  1. Depression, W. H. O. (2017). Other common mental disorders: global health estimates. Geneva: World Health Organization, 24(1).
  2. Calvo, R., Milne, D., Hussain, M. S., & Christensen, H. (2017). Natural language processing in mental health applications using non-clinical texts. Natural Language Engineering, 23(5), 649–685. https://doi.org/10.1017/S1351324916000383
  3. Polikar, R. (2006). Ensemble based systems in decision making. IEEE Circuits and systems magazine, 6(3), 21-45. https://doi.org/10.1109/MCAS.2006.1688199
  4. Zhou, Z. H. (2012). Ensemble methods: foundations and algorithms. CRC press. https://doi.org/10.1201/b12207
  5. Dietterich, T. G. (2000, June). Ensemble methods in machine learning. In International workshop on multiple classifier systems (pp. 1-15). Berlin, Heidelberg: Springer Berlin Heidelberg. https://doi.org/10.1007/3-540-45014-9_1
  6. Lakshminarayanan, B., Pritzel, A., & Blundell, C. (2017). Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in neural information processing systems, 30.
  7. De Choudhury, M., Gamon, M., Counts, S., & Horvitz, E. (2013). Predicting depression via social media. In Proceedings of the international AAAI conference on web and social media (Vol. 7, No. 1, pp. 128-137).
  8. Eichstaedt, J. C., Smith, R. J., Merchant, R. M., Ungar, L. H., Crutchley, P., Preoţiuc-Pietro, D.,. & Schwartz, H. A. (2018). Facebook language predicts depression in medical records. Proceedings of the National Academy of Sciences, 115(44), 11203-11208. https://doi.org/10.1073/pnas.1802331115
  9. Sagi, O., & Rokach, L. (2018). Ensemble learning: A survey. Wiley interdisciplinary reviews: data mining and knowledge discovery, 8(4), e1249. https://doi.org/10.1002/widm.1249
  10. Trotzek, M., Koitka, S., & Friedrich, C. M. (2018). Utilizing neural networks and linguistic metadata for early detection of depression indications in text sequences. IEEE Transactions on Knowledge and Data Engineering, 32(3), 588-601. https://doi.org/10.1109/TKDE.2018.2885515
  11. Sau, A., & Bhakta, I. (2017). Predicting anxiety and depression in elderly patients using machine learning technology. Healthcare Technology Letters, 4(6), 238-243. https://doi.org/10.1049/htl.2017.0066
  12. Orabi, A. H., Buddhitha, P., Orabi, M. H., & Inkpen, D. (2018, June). Deep learning for depression detection of twitter users. In Proceedings of the fifth workshop on computational linguistics and clinical psychology: from keyboard to clinic (pp. 88-97). https://doi.org/10.18653/v1/W18-0609
  13. Burdisso, S. G., Errecalde, M., & Montes-y-Gómez, M. (2019). A text classification framework for simple and effective early depression detection over social media streams. Expert Systems with Applications, 133, 182-197. https://doi.org/10.1016/j.eswa.2019.05.023
  14. S., M. (2021). Depressive/Non-Depressive Tweets between Dec'19 to Dec'20. https://doi.org/10.21227/9phc-ya88
  15. Dietterich, T. G. (2000, June). Ensemble methods in machine learning. In International workshop on multiple classifier systems (pp. 1-15). Berlin, Heidelberg: Springer Berlin Heidelberg. https://doi.org/10.1007/3-540-45014-9_1
  16. Rokach, L. (2010). Ensemble-based classifiers. Artificial intelligence review, 33, 1-39. https://doi.org/10.1007/s10462-009-9124-7
  17. Breiman, L. (2001). Random forests. Machine learning, 45, 5-32. https://doi.org/10.1023/A:1010933404324
  18. Freund, Y., & Schapire, R. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of computer and system sciences, 55(1), 119-139. https://doi.org/10.1006/jcss.1997.1504
  19. Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of statistics, 1189-1232. https://doi.org/10.1214/aos/1013203451
  20. Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794). https://doi.org/10.1145/2939672.2939785
  21. Eichstaedt, J. C., Smith, R. J., Merchant, R. M., Ungar, L. H., Crutchley, P., Preoţiuc-Pietro, D.,. & Schwartz, H. A. (2018). Facebook language predicts depression in medical records. Proceedings of the National Academy of Sciences, 115(44), 11203-11208. https://doi.org/10.1073/pnas.1802331115