Pelican Optimization-Assisted Deep Learning Framework for Adverse Drug Reaction Detection from Twitter Data

International Journal of Computer Science and Engineering

© 2025 by SSRG - IJCSE Journal

Volume 12 Issue 5

Year of Publication : 2025

Authors : R. Deepalakshmi, P. Manikandan

10.14445/23488387/IJCSE-V12I5P106

How to Cite?

R. Deepalakshmi, P. Manikandan, "Pelican Optimization-Assisted Deep Learning Framework for Adverse Drug Reaction Detection from Twitter Data," SSRG International Journal of Computer Science and Engineering , vol. 12,  no. 5, pp. 42-55, 2025. Crossref, https://doi.org/10.14445/23488387/IJCSE-V12I5P106

Abstract:

Adverse Drug Reactions (ADRs) lead to significant patient safety hurdles, necessitating timely and accurate detection to support pharmacovigilance efforts. Traditional ADR reporting systems suffer from underreporting and delays, prompting the need for alternative data sources such as social media. However, extracting meaningful insights from unstructured and noisy social media text presents substantial challenges. This research introduces a novel Deep Convolutional Recurrent Semantic Similarity Model (DCR-SSM), which integrates convolutional and recurrent layers with a semantic similarity mechanism and attention module to enhance ADR detection from Twitter data. The framework incorporates a robust preprocessing pipeline tailored to social media text and a novel Decision Tree-based Pelican Optimization Algorithm (DT-POA) for feature selection and Bag-of-Words encoding to capture relevant linguistic and semantic features. Simulation of the proposed framework is assessed on the SMM4H dataset, indicating the superior performance of the proposed Model over state-of-the-art ADR detection methods. The DCR-SSM accomplished an accuracy of 75%, 72%, recall of 72%, and an F1-score of 73%, outperforming traditional machine learning (SVM) and deep learning models (LSTM, Bi-LSTM, CNN). Compared to best-performing existing models, the proposed framework improves precision by up to 5.2% and maintains a balanced trade-off between recall and F1-score, ensuring better generalization in real-world applications. These findings highlight the potential of leveraging NLP and deep learning for mining patient-reported ADRs from social media, offering a scalable and cost-effective alternative to conventional pharmacovigilance methods. Future research can further explore multi-lingual ADR detection and domain-specific embeddings to enhance detection accuracy and adaptability across diverse healthcare settings.

Keywords:

Adverse Drug Reactions, Deep Learning, Natural Language Processing, Pharmacovigilance, Twitter data.

References:

[1] Sarvnaz Karimi et al., “Text and Data Mining Techniques in Adverse Drug Reaction Detection,” ACM Computing Surveys, vol. 47, no. 4, pp. 1-39, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[2] I-Jen P. Castle et al., “Emergency Department Visits for Adverse Drug Reactions Involving Alcohol: United States, 2005 to 2011,” Alcoholism: Clinical and Experimental Research, vol. 40, no. 9, pp. 1913-1925, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[3] R. Bordet et al., “Analysis of the Direct Cost of Adverse Drug Reactions in Hospitalised Patients,” European Journal of Clinical Pharmacology, vol. 56, pp. 935-941, 2001.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Toshiyuki Sakaeda et al., “Data Mining of the Public Version of the FDA Adverse event Reporting System,” International Journal of Medical Sciences, vol. 10, no. 7, pp. 796-803, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Muaed Alomar et al., “Post Marketing Surveillance of Suspected Adverse Drug Reactions through Spontaneous Reporting: Current Status, Challenges and The Future,” Therapeutic Advances in Drug Safety, vol. 11, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Brett R. South et al., “Evaluating the Effects of Machine Pre-annotation and An Interactive Annotation Interface on Manual De-identification of Clinical Text,” Journal of Biomedical Informatics, vol. 50, pp. 162-172, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Wei-San Lin et al., “Utilizing Different Word Representation Methods for Twitter Data in Adverse Drug Reactions Extraction,” 2015 Conference on Technologies and Applications of Artificial Intelligence (TAAI), 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Weiai Xu et al., “Twitter Hashtags for Health: Applying Network and Content Analyses to Understand the Health Knowledge Sharing in a Twitter-based Community of Practice,” Quality & Quantity, vol. 49, pp. 1361-1380, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Ioannis Korkontzelos et al., “Analysis of the Effect of Sentiment Analysis on Extracting Adverse Drug Reactions from Tweets and Forum Posts,” Journal of Biomedical Informatics, vol. 62, pp. 148-158, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Trung Huynh et al., “Adverse Drug Reaction Classification with Deep Neural Networks,” Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pp. 877-887, 2016.
[Google Scholar] [Publisher Link]
[11] Chih-Hsuan Wei et al., “Assessing the State of the Art in Biomedical Relation Extraction: Overview of the BioCreative V Chemical-Disease Relation (CDR) Task,” Database, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Guillaume Lample et al., “Neural Architectures for Named Entity Recognition,” arXiv preprint arXiv:1603.01360, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Zichao Yang et al., “Hierarchical Attention Networks for Document Classification,” Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1480-1489, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Yuan Luo, Ozlem Uzuner, and Peter Szolovits, “Bridging Semantics and Syntax with Graph Algorithms—State-of-the-art of Extracting Biomedical Relations,” Briefings in Bioinformatics, vol. 18, no. 1, pp. 160-178, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Abeed Sarker, and Graciela Gonzalez, “Portable Automatic Text Classification for Adverse Drug Reaction Detection Via Multi-corpus Training,” Journal of Biomedical Informatics, vol. 53, pp. 196-207, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Azadeh Nikfarjam et al., “Pharmacovigilance from Social Media: Mining Adverse Drug Reaction Mentions using Sequence Labeling with Word Embedding Cluster Features,” Journal of the American Medical Informatics Association, vol. 22, no. 3, pp. 671-681, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[17] G. Gonzalez-Hernandez et al., “Capturing the Patient's Perspective: A Review of Advances in Natural Language Processing of Health-related Text,” Yearbook of Medical Informatics, vol. 26, no. 1, pp. 214-227, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Anne Cocos, Alexander G. Fiks, and Aaron J. Masino, “Deep Learning for Pharmacovigilance: Recurrent Neural Network Architectures for Labeling Adverse Drug Reactions in Twitter Posts,” Journal of the American Medical Informatics Association, vol. 24, no. 4, pp. 813-821, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Jae-Young Lee et al., “The Use of Social Media in Detecting Drug Safety-related New Black Box Warnings, Labelling Changes, or Withdrawals: Scoping Review,” JMIR Public Health and Surveillance, vol. 7, no. 6, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[20] John M. Giorgi, and Gary D. Bader, “Transfer Learning for Biomedical Named Entity Recognition with Neural Networks,” Bioinformatics, vol. 34, no. 23, pp. 4087-4094, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Davy Weissenbacher et al., “Overview of the Fourth Social Media Mining for Health (SMM4H) Shared Tasks at ACL 2019,” Proceedings of the Fourth Social Media Mining for Health Applications (# SMM4H) Workshop & Shared Task, pp. 21-30, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Pavel Trojovský, and Mohammad Dehghani, “Pelican Optimization Algorithm: A Novel Nature-inspired Algorithm for Engineering Applications,” Sensors, vol. 22, no. 3, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Arjun Magge et al., “Overview of the Sixth Social Media Mining for Health Applications (# SMM4H) Shared Tasks at NAACL 2021,” Proceedings of the Sixth Social Media Mining for Health (# SMM4H) Workshop and Shared Task, pp. 21-32, 2021. [CrossRef] [Google Scholar] [Publisher Link]
[24] Davy Weissenbacher et al., “Overview of the Seventh Social Media Mining for Health Applications (# SMM4H) Shared Tasks at COLING 2022,” Proceedings of the Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task, pp. 221-241, 2022.
[Google Scholar] [Publisher Link]
[25] Andrey Sakhovskiy, Zulfat Miftahutdinov, and Elena Tutubalina, “KFU NLP Team at SMM4H 2021 Tasks: Cross-lingual and Cross-modal BERT-based Models for Adverse Drug Effects,” Proceedings of the Sixth Social Media Mining for Health (# SMM4H) Workshop and Shared Task, pp. 39-43, 2021.
[CrossRef] [Google Scholar] [Publisher Link]