Cockroach Optimized Progressive Laplace Extreme Learning Machine for Depression Prediction in Social Media Text

R.Geetha; D.Vimal Kumar

doi:https://doi.org/10.14445/22315381/IJETT-V74I4P110

Research Article | Open Access | Download PDF

Volume 74 | Issue 4 | Year 2026 | Article Id. IJETT-V74I4P110 | DOI : https://doi.org/10.14445/22315381/IJETT-V74I4P110

Cockroach Optimized Progressive Laplace Extreme Learning Machine for Depression Prediction in Social Media Text

R.Geetha, D.Vimal Kumar

Received	Revised	Accepted	Published
17 Nov 2025	11 Feb 2026	19 Feb 2026	29 Apr 2026

Citation :

R.Geetha, D.Vimal Kumar, "Cockroach Optimized Progressive Laplace Extreme Learning Machine for Depression Prediction in Social Media Text," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 4, pp. 132-143, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I4P110

Abstract

Early detection of depression is crucial for timely intervention and effective treatment. Social media platforms play a significant role in sharing individual thoughts and opinions through textual posts. Conventional deep learning models in depression face challenges in improving the accuracy of depression detection with minimal time consumption. To improve the accuracy, a novel model, Cockroach Optimized Progressive Laplace Extreme Learning Machine (COPLELM), is proposed for sentiment analysis of Twitter social media text with minimal time consumption. The data acquisition is to collect text data from the Twitter Dataset. Progressive Laplace Kernelized Extreme Learning Machine is employed for depression prediction with several layers. First, a number of Twitter text data are given to the input layer. Texts are transferred to a hidden layer for performing pre-processing, which involves tasks such as tokenization, stop-word removal, and word stemming. A censored regressive cockroach swarm optimization algorithm is employed in the subsequent hidden layers to extract optimal keywords. Finally, the prediction is performed in the next hidden layer using Gestalt pattern matching. Depression and non-depression Twitter texts are accurately detected in the output layer with minimal time. Experimental evaluations are conducted using various performance metrics, including prediction accuracy, precision, recall, F1-score, specificity, error rate, and depression prediction time, confusion matrix, and ROC. The results demonstrate that the proposed COPLELM model achieves higher accuracy in depression prediction, with reduced time and error rates compared to existing methods.

Keywords

Depression detection, Social Media Text, Progressive Extreme Learning Machine, Laplace Kernel, censored regressive cockroach swarm optimization algorithm, Gestalt pattern matching.

References

[1] Joel Philip Thekkekara, Sira Yongchareon, and Veronica Liesaputra, “An Attention-based CNN-BiLSTM Model for Depression Detection on Social Media Text,” Expert Systems with Applications, vol. 249, pp. 1-9, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Nawshad Farruque et al., “Deep Temporal Modelling of Clinical Depression through Social Media Text,” Natural Language Processing Journal, vol. 6, pp. 1-14, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Amna Qasim et al., “Detection of Depression Severity in Social Media Text using Transformer-based Models,” Information, vol. 16, no. 2, pp. 1-23, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Eunchae Lim et al., “A Lightweight Approach based on Cross-Modality for Depression Detection,” Computers in Biology and Medicine, vol. 186, pp. 1-14, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Nawshad Farruque et al., “Depression Symptoms Modelling from Social Media Text: An LLM Driven Semi-Supervised Learning Approach,” Language Resources and Evaluation, vol. 58, no. 3, pp. 1013-1041, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Muhammad Asad Abbas et al., “Novel Transformer based Contextualized Embedding and Probabilistic Features for Depression Detection from Social Media,” IEEE Access, vol. 12, pp. 54087-54100, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Shakir Khan, and Salihah Alqahtani, “Hybrid Machine Learning Models to Detect Signs of Depression,” Multimedia Tools and Applications, vol. 83, no. 13, pp. 38819-38837, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Filza Rehmani et al., “Depression Detection with Machine Learning of Structural and Non-Structural Dual Languages,” Healthcare Technology Letters, vol. 11, no. 4, pp. 218-226, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Bayode Ogunleye, Hemlata Sharma, and Olamilekan Shobayo, “Sentiment Informed Sentence BERT-Ensemble Algorithm for Depression Detection,” Big Data and Cognitive Computing, vol. 8, no. 9, pp. 1-16, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Umesh Kumar Lilhore et al., “Prevalence and Risk Factors Analysis of Postpartum Depression at Early Stage using Hybrid Deep Learning Model,” Scientific Reports, vol. 14, no. 1, pp. 1-24, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Ngumimi Karen Iyortsuun et al., “Additive Cross-Modal Attention Network (ACMA) for Depression Detection based on Audio and Textual Features,” IEEE Access, vol. 12, pp. 20479-20489, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Yongfeng Tao et al., “DepMSTAT: Multimodal Spatio-Temporal Attentional Transformer for Depression Detection,” IEEE Transactions on Knowledge and Data Engineering, vol. 36, no. 7, pp. 2956-2966, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Wenli Zhang et al., “Depression Detection using Digital Traces on Social Media: A Knowledge-Aware Deep Learning Approach,” Journal of Management Information Systems, vol. 41, no. 2, pp. 546-580, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Cao Xin, and Lailatul Qadri Zakaria, “Integrating Bert with CNN and BiLSTM for Explainable Detection of Depression in Social Media Contents,” IEEE Access, vol. 12, pp. 161203-161212, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[15] M. Kiran Myee et al., “Detection of Depression in Social Media Posts using Emotional Intensity Analysis,” Engineering, Technology & Applied Science Research, vol. 14, no. 5, pp. 16207-16211, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Vandana, Nikhil Marriwala, and Deepti Chaudhary, “A Hybrid Model for Depression Detection using Deep Learning,” Measurement: Sensors, vol. 25, pp. 1-10, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[17] İsmail Baydili, Burak Tasci, and Gülay Tasci, “Deep Learning-based Detection of Depression and Suicidal Tendencies in Social Media Data with Feature Selection,” Behavioural Sciences, vol. 15, no. 3, pp. 1-28, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[18] T. Srajan Kumar, M. Narayanan, and Harikrishna Kamatham, “A Deep Learning Framework with a Hybrid Model for Automatic Depression Detection in Social Media Posts,” International Journal of Intelligent Systems and Applications in Engineering, vol. 12, no. 4, pp. 3217-3231, 2024.
[Publisher Link]

[19] Eliseo Bao, Anxo Pérez, and Javier Parapar, “Explainable Depression Symptom Detection in Social Media,” Health Information Science and Systems, vol. 12, no. 1, pp. 1-18, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Muhammad Rizwan et al., “Depression Intensity Classification from Tweets using Fast Text based Weighted Soft Voting Ensemble,” Computers, Materials and Continua, vol. 78, no. 2, pp. 2047-2066, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Loukas Ilias, Spiros Mouzakitis, and Dimitris Askounis, “Calibration of Transformer-based Models for Identifying Stress and Depression in Social Media,” IEEE Transactions on Computational Social Systems, vol. 11, no. 2, pp. 1979-1990, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Shiwen Zhou, and Masnizah Mohd, “Mental Health Safety and Depression Detection in Social Media Text Data: A Classification Approach based on a Deep Learning Model,” IEEE Access, vol. 13, pp. 63284-63297, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[23] Biodoumoye George Bokolo, and Qingzhong Liu, “Advanced Comparative Analysis of Machine Learning and Transformer Models for Depression and Suicide Detection in Social Media Texts,” Electronics, vol. 13, no. 20, pp. 1-22, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[24] Xiaolong Li et al., “Hypergraph Neural Network for Multimodal Depression Recognition,” Electronics, vol. 13, no. 22, pp. 1-20, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[25] Dip Kumar Saha et al., “Ensemble of Hybrid Model based Technique for Early Detecting of Depression based on SVM and Neural Networks,” Scientific Reports, vol. 14, no. 1, pp. 1-18, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Tumpa Rani Shaha et al., “Feature Group Partitioning: An Approach for Depression Severity Prediction with Class Balancing using Machine Learning Algorithms,” BMC Medical Research Methodology, vol. 24, no. 1, pp. 1-18, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[27] Ziling Ruan et al., “Automatic Depression Detection among Higher Education Students based on DeepFM,” IEEE Transactions on Instrumentation and Measurement, vol. 73, pp. 1-10, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[28] Shahid Munir Shah et al., “Advancing Depression Detection on Social Media Platforms through Fine-Tuned Large Language Models,” Online Social Networks and Media, vol. 46, pp. 1-16, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[29] Esteban A. Ríssola et al., “On the Incidence of Depression Symptoms on Social Media,” Journal of Computational Social Science, vol. 8, no. 2, pp. 1-30, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[30] Robinson Narvaez Burbano, Oscar Mauricio Caicedo Rendon, and Carlos. A. Astudillo, “An Encoder-Only Transformer Model for Depression Detection from Social Network Data: The DEENT Approach,” Applied Sciences, vol. 15, no. 6, pp. 1-17, 2025.
[CrossRef] [Google Scholar] [Publisher Link]