Detecting Adverse Drug Reactions from User-Generated Twitter Data: A Case Study
Bibliographic record
Abstract
Adverse Drug Reactions (ADRs) are defined as unwanted drug effects that cause induced mortality and morbidity in health-care. Health-related subjects can be discussed throughout the broad span of social media conversations. Plethora of information available in social media and health-related forums, as well as the rich expression of public opinion, has recently piqued the public health community’s interest in using these sources for pharmacovigilance. We investigate the role of sentiment analysis characteristics in detecting ADR mentions based on user generated dataset obtained from Twitter online streaming API. Our proposed model uses BERT-CNN model with final layer of Support vector machine (SVM) to classify the ADRs mentions. In our study, we extracted tweets from tweeter using Tweepy API and performed data pre-processing, data annotation and data augmentation to create a strong corpus. For data augmentation, we used Marian MT model for to increase the number of tweets with the help of back translation. We passed this corpus to BERT-Base model to get word embeddings and then used CNN model to get important features from data. To get the better efficiency, we used SVM which classifies a tweet. The evaluation study reveals that our proposed model achieved 92% accuracy and 78% F1score. Data augmentation and BERT pre-trained model are the main keys of our proposed model which help us to achieve better result than other machine learning models.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".