Abstract Background Diabetic retinopathy (DR) is a leading cause of blindness in American adults. If detected, DR can be treated to prevent further damage causing blindness. There is an increasing interest in developing artificial intelligence (AI) technologies to help detect DR using electronic health records. The lesion-related information documented in fundus image reports is a valuable resource that could help diagnoses of DR in clinical decision support systems. However, most studies for AI-based DR diagnoses are mainly based on medical images; there is limited studies to explore the lesion-related information captured in the free text image reports. Methods In this study, we examined two state-of-the-art transformer-based natural language processing (NLP) models, including BERT and RoBERTa, compared them with a recurrent neural network implemented using Long short-term memory (LSTM) to extract DR-related concepts from clinical narratives. We identified four different categories of DR-related clinical concepts including lesions, eye parts, laterality, and severity, developed annotation guidelines, annotated a DR-corpus of 536 image reports, and developed transformer-based NLP models for clinical concept extraction and relation extraction. We also examined the relation extraction under two settings including ‘gold-standard’ setting—where gold-standard concepts were used–and end-to-end setting. Results For concept extraction, the BERT model pretrained with the MIMIC III dataset achieve the best performance (0.9503 and 0.9645 for strict/lenient evaluation). For relation extraction, BERT model pretrained using general English text achieved the best strict/lenient F1-score of 0.9316. The end-to-end system, BERT_general_e2e, achieved the best strict/lenient F1-score of 0.8578 and 0.8881, respectively. Another end-to-end system based on the RoBERTa architecture, RoBERTa_general_e2e, also achieved the same performance as BERT_general_e2e in strict scores. Conclusions This study demonstrated the efficiency of transformer-based NLP models for clinical concept extraction and relation extraction. Our results show that it’s necessary to pretrain transformer models using clinical text to optimize the performance for clinical concept extraction. Whereas, for relation extraction, transformers pretrained using general English text perform better.
more »
« less
A Comparison Study for Disaster Tweet Classification Using Deep Learning Models
Effectively filtering and categorizing the large volume of user-generated content on social media during disaster events can help emergency management and disaster response prioritize their resources. Deep learning approaches, including recurrent neural networks and transformer-based models, have been previously used for this purpose. Capsule Neural Networks (CapsNets), initially proposed for image classification, have been proven to be useful for text analysis as well. However, to the best of our knowledge, CapsNets have not been used for classifying crisis-related messages, and have not been extensively compared with state-of-the-art transformer-based models, such as BERT. Therefore, in this study, we performed a thorough comparison between CapsNet models, state-of-the-art BERT models and two popular recurrent neural network models that have been successfully used for tweet classification, specifically, LSTM and Bi-LSTM models, on the task of classifying crisis tweets both in terms of their informativeness (binary classification), as well as their humanitarian content (multi-class classification). For this purpose, we used several benchmark datasets for crisis tweet classification, namely CrisisBench, CrisisNLP and CrisisLex. Experimental results show that the performance of the CapsNet models is on a par with that of LSTM and Bi-LSTM models for all metrics considered, while the performance obtained with BERT models have surpassed the performance of the other three models across different datasets and classes for both classification tasks, and thus BERT could be considered the best overall model for classifying crisis tweets.
more »
« less
- Award ID(s):
- 1741345
- NSF-PAR ID:
- 10472648
- Publisher / Repository:
- SCITEPRESS - Science and Technology Publications
- Date Published:
- Journal Name:
- Proceedings of the 12th International Conference on Data Science, Technology and Applications DATA
- Volume:
- 1
- Page Range / eLocation ID:
- 152 to 163
- Subject(s) / Keyword(s):
- ["Tweet Classification, Capsule Neural Networks, BERT, LSTM, Bi-LSTM."]
- Format(s):
- Medium: X
- Location:
- Rome, Italy
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Social media platforms are playing increasingly critical roles in disaster response and rescue operations. During emergencies, users can post rescue requests along with their addresses on social media, while volunteers can search for those messages and send help. However, efficiently leveraging social media in rescue operations remains challenging because of the lack of tools to identify rescue request messages on social media automatically and rapidly. Analyzing social media data, such as Twitter data, relies heavily on Natural Language Processing (NLP) algorithms to extract information from texts. The introduction of bidirectional transformers models, such as the Bidirectional Encoder Representations from Transformers (BERT) model, has significantly outperformed previous NLP models in numerous text analysis tasks, providing new opportunities to precisely understand and classify social media data for diverse applications. This study developed and compared ten VictimFinder models for identifying rescue request tweets, three based on milestone NLP algorithms and seven BERT-based. A total of 3191 manually labeled disaster-related tweets posted during 2017 Hurricane Harvey were used as the training and testing datasets. We evaluated the performance of each model by classification accuracy, computation cost, and model stability. Experiment results show that all BERT-based models have significantly increased the accuracy of categorizing rescue-related tweets. The best model for identifying rescue request tweets is a customized BERT-based model with a Convolutional Neural Network (CNN) classifier. Its F1-score is 0.919, which outperforms the baseline model by 10.6%. The developed models can promote social media use for rescue operations in future disaster events.more » « less
-
Social media cyberbullying has a detrimental effect on human life. As online social networking grows daily, the amount of hate speech also increases. Such terrible content can cause depression and actions related to suicide. This paper proposes a trustable LSTM Autoencoder Network for cyberbullying detection on social media using synthetic data. We have demonstrated a cutting-edge method to address data availability difficulties by producing machine-translated data. However, several languages such as Hindi and Bangla still lack adequate investigations due to a lack of datasets. We carried out experimental identification of aggressive comments on Hindi, Bangla, and English datasets using the proposed model and traditional models, including Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (BiLSTM), LSTM-Autoencoder, Word2vec, Bidirectional Encoder Representations from Transformers (BERT), and Generative Pre-trained Transformer 2 (GPT-2) models. We employed evaluation metrics such as f1-score, accuracy, precision, and recall to assess the models’ performance. Our proposed model outperformed all the models on all datasets, achieving the highest accuracy of 95%. Our model achieves state-of-the-art results among all the previous works on the dataset we used in this paper.more » « less
-
Abstract Purpose Social media users share their ideas, thoughts, and emotions with other users. However, it is not clear how online users would respond to new research outcomes. This study aims to predict the nature of the emotions expressed by Twitter users toward scientific publications. Additionally, we investigate what features of the research articles help in such prediction. Identifying the sentiments of research articles on social media will help scientists gauge a new societal impact of their research articles. Design/methodology/approach Several tools are used for sentiment analysis, so we applied five sentiment analysis tools to check which are suitable for capturing a tweet's sentiment value and decided to use NLTK VADER and TextBlob. We segregated the sentiment value into negative, positive, and neutral. We measure the mean and median of tweets’ sentiment value for research articles with more than one tweet. We next built machine learning models to predict the sentiments of tweets related to scientific publications and investigated the essential features that controlled the prediction models. Findings We found that the most important feature in all the models was the sentiment of the research article title followed by the author count. We observed that the tree-based models performed better than other classification models, with Random Forest achieving 89% accuracy for binary classification and 73% accuracy for three-label classification. Research limitations In this research, we used state-of-the-art sentiment analysis libraries. However, these libraries might vary at times in their sentiment prediction behavior. Tweet sentiment may be influenced by a multitude of circumstances and is not always immediately tied to the paper's details. In the future, we intend to broaden the scope of our research by employing word2vec models. Practical implications Many studies have focused on understanding the impact of science on scientists or how science communicators can improve their outcomes. Research in this area has relied on fewer and more limited measures, such as citations and user studies with small datasets. There is currently a critical need to find novel methods to quantify and evaluate the broader impact of research. This study will help scientists better comprehend the emotional impact of their work. Additionally, the value of understanding the public's interest and reactions helps science communicators identify effective ways to engage with the public and build positive connections between scientific communities and the public. Originality/value This study will extend work on public engagement with science, sociology of science, and computational social science. It will enable researchers to identify areas in which there is a gap between public and expert understanding and provide strategies by which this gap can be bridged.more » « less
-
The automatic classification of electrocardiogram (ECG) signals has played an important role in cardiovascular diseases diagnosis and prediction. Deep neural networks (DNNs), particularly Convolutional Neural Networks (CNNs), have excelled in a variety of intelligent tasks including biomedical and health informatics. Most the existing approaches either partition the ECG time series into a set of segments and apply 1D-CNNs or divide the ECG signal into a set of spectrogram images and apply 2D-CNNs. These studies, however, suffer from the limitation that temporal dependencies between 1D segments or 2D spectrograms are not considered during network construction. Furthermore, meta-data including gender and age has not been well studied in these researches. To address those limitations, we propose a multi-module Recurrent Convolutional Neural Networks (RCNNs) consisting of both CNNs to learn spatial representation and Recurrent Neural Networks (RNNs) to model the temporal relationship. Our multi-module RCNNs architecture is designed as an end-to-end deep framework with four modules: (i) timeseries module by 1D RCNNs which extracts spatio-temporal information of ECG time series; (ii) spectrogram module by 2D RCNNs which learns visual-temporal representation of ECG spectrogram ; (iii) metadata module which vectorizes age and gender information; (iv) fusion module which semantically fuses the information from three above modules by a transformer encoder. Ten-fold cross validation was used to evaluate the approach on the MIT-BIH arrhythmia database (MIT-BIH) under different network configurations. The experimental results have proved that our proposed multi-module RCNNs with transformer encoder achieves the state-of-the-art with 99.14% F1 score and 98.29% accuracy.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.5220/0012129300003541
