# A PubMedBERT-based Classifier with Data Augmentation Strategy for Detecting Medication Mentions in Tweets

arXiv: https://arxiv.org/abs/2112.02998 · HTML: https://mlsanity.com/paper/2112.02998/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 19 references that are in the map.
- First posted on arXiv 3 Nov 2021.

## Builds on (most cited first, 4 of 4)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [Deep Neural Networks Ensemble for Detecting Medication Mentions in Tweets](https://mlsanity.com/paper/1904.05308/) (2019)

## Built on by (most cited first, 3 of 3)

- [Reasoning LLMs in the Medical Domain: A Literature Survey](https://mlsanity.com/paper/2508.19097/) (2025)
- [Eir: Thai Medical Large Language Models](https://mlsanity.com/paper/2409.08523/) (2024)
- [ProtRLSearch: A Multi-Round Multimodal Protein Search Agent with Large Language Models Trained via Reinforcement Learning](https://mlsanity.com/paper/2603.01464/) (2026)

## Abstract (arXiv)

As a major social media platform, Twitter publishes a large number of user-generated text (tweets) on a daily basis. Mining such data can be used to address important social, public health, and emergency management issues that are infeasible through other means. An essential step in many text mining pipelines is named entity recognition (NER), which presents some special challenges for tweet data. Among them are nonstandard expressions, extreme imbalanced classes, and lack of context information, etc. The track 3 of BioCreative challenge VII (BC7) was organized to evaluate methods for detecting medication mentions in tweets. In this paper, we report our work on BC7 track 3, where we explored a PubMedBERT-based classifier trained with a combination of multiple data augmentation approaches. Our method achieved an F1 score of 0.762, which is substantially higher than the mean of all submissions (0.696).