Deep gramulator: Improving precision in the classification of personal health-experience tweets with deep learning

Calix, Ricardo A.; Gupta, Ravish; Gupta, Matrika; Jiang, Keyuan

doi:10.1109/bibm.2017.8217820

Cited by 16 publications

(17 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A set of 22 engineered features based upon both textual content and metadata of tweets was proposed in constructing a corpus of personal experience tweets (Jiang et al, 2016). Subsequently, Calix and colleagues introduced the concept of deep gramulator to include a textual feature that contains expressions in one class but not in the opposite class, to improve the discriminatory ability of the classification (Calix et al, 2017). Advancement in neural embedding, which demonstrated state-of-art results in many classification tasks on textual data, motivated the development of a new approach of combining word embedding (word2vec) and a recurrent neural network which demonstrated a significant improvement of classification performance (p < 0.05) (Jiang et al, 2018).…”

Section: Related Workmentioning

confidence: 99%

Identifying Personal Experience Tweets of Medication Effects Using Pre-trained RoBERTa Language Model and Its Updating

Zhu¹,

Song²,

Jin

et al. 2020

Proceedings of the 11th International Workshop on Health Text Mining and Information Analysis

Self Cite

View full text Add to dashboard Cite

Post-market surveillance, the practice of monitoring the safe use of pharmaceutical drugs is an important part of pharmacovigilance. Being able to collect personal experience related to pharmaceutical product use could help us gain insight into how the human body reacts to different medications. Twitter, a popular social media service, is being considered as an important alternative data source for collecting personal experience information with medications. Identifying personal experience tweets is a challenging classification task in natural language processing. In this study, we utilized three methods based on Facebook's Robustly Optimized BERT Pretraining Approach (RoBERTa) to predict personal experience tweets related to medication use: the first one combines the pre-trained RoBERTa model with a classifier, the second combines the updated pre-trained RoBERTa model using a corpus of unlabeled tweets with a classifier, and the third combines the RoBERTa model that was trained with our unlabeled tweets from scratch with the classifier too. Our results show that all of these approaches outperform the published methods (Word Embedding + LSTM) in classification performance (p < 0.05), and updating the pre-trained language model with tweets related to medications could even improve the performance further.

show abstract

Section: Related Workmentioning

confidence: 99%

Identifying Personal Experience Tweets of Medication Effects Using Pre-trained RoBERTa Language Model and Its Updating

Zhu¹,

Song²,

Jin

et al. 2020

Proceedings of the 11th International Workshop on Health Text Mining and Information Analysis

Self Cite

View full text Add to dashboard Cite

show abstract

“…Calix et al [18] proposed a deep-learning-based medication-use safety scheme called the Deep Gramulator, which tracks and monitors the use of medication by medical personnel to facilitate medication-use safety. The Deep Gramulator can automatically extract tweets to obtain relevant personal health experiences from social media.…”

Section: Related Workmentioning

confidence: 99%

MedGlasses: A Wearable Smart-Glasses-Based Drug Pill Recognition System Using Deep Learning for Visually Impaired Chronic Patients

et al. 2020

View full text Add to dashboard Cite

Today, with the arrival of an aging society, the average age of the population is rising. It is known that the physiology of a person degrades with age. There are approximately 285 million visually impaired people in the world, of whom 140 million are elderly people over the age of 50, and 110 million of these visually impaired elderly people suffer from multiple chronic diseases. In the case of multiple medication usage, these 110 million vulnerable people will be more likely to take the wrong medicines or forget to take their medication. To solve this problem, this paper proposes a wearable smart-glassesbased drug pill recognition system using deep learning, named MedGlasses, for visually impaired people to improve their medication-use safety. The proposed MedGlasses system consists of a pair of wearable smart glasses, an artificial intelligence (AI)-based intelligent drug pill recognition box, a mobile device app, and a cloud-based information management platform. Experimental results show that a recognition accuracy of up to 95.1% can be achieved. Therefore, the proposed MedGlasses system can effectively mitigate the problem of drug interactions caused by taking incorrect drugs, thereby reducing the cost of medical treatment and providing visually impaired chronic patients with a safe medication environment. INDEX TERMS Artificial intelligence over the Internet of Things (AIoT), deep learning, drug pill recognition, image sensor, image processing, medication-use safety, visually impaired, wearable devices.

show abstract

“…Text classification with deep learning is considered better than machine learning [12] on the same object. A previous study [13] showed that the results of deep learning accuracy were better than machine learning in the classification of health tweets. The superior performance of deep learning than machine learning underlies this research using deep learning as a classification method.…”

Section: Introductionmentioning

confidence: 97%

Identifying Degree-of-Concern on COVID-19 topics with text classification of Twitters

Hasanah

Suciati

Purwitasari

2021

regist. j. ilm. teknol. sist. inf.

View full text Add to dashboard Cite

The COVID-19 pandemic has various impacts on changing people’s behavior socially and individually. This study identifies the Degree-of-Concern topic of COVID-19 through citizen conversations on Twitter. It aims to help related parties make policies for developing appropriate emergency response strategies in dealing with changes in people’s behavior due to the pandemic. The object of research is 12,000 data from verified Twitter accounts in Surabaya. The varied nature of Twitter needs to be classified to address specific COVID-19 topics. The first stage of classification is to separate Twitter data into COVID-19 and non-COVID-19. The second stage is to classify the COVID-19 data into seven classes: warnings and suggestions, notification of information, donations, emotional support, seeking help, criticism, and hoaxes. Classification is carried out using a combination of word embedding (Word2Vec and fastText) and deep learning methods (CNN, RNN, and LSTM). The trial was carried out with three scenarios with different numbers of train data for each scenario. The classification results show the highest accuracy is 97.3% and 99.4% for the first and second stage classification obtained from the combination of fastText and LSTM. The results show that the classification of the COVID-19 topic can be used to identify Degree-of-Concern properly. The results of the Degree-of-Concern identification based on the classification can be used as a basis for related parties in making policies to formulate appropriate emergency response strategies in dealing with changes in public behavior due to a pandemic.

show abstract

Deep gramulator: Improving precision in the classification of personal health-experience tweets with deep learning

Cited by 16 publications

References 7 publications

Identifying Personal Experience Tweets of Medication Effects Using Pre-trained RoBERTa Language Model and Its Updating

Identifying Personal Experience Tweets of Medication Effects Using Pre-trained RoBERTa Language Model and Its Updating

MedGlasses: A Wearable Smart-Glasses-Based Drug Pill Recognition System Using Deep Learning for Visually Impaired Chronic Patients

Identifying Degree-of-Concern on COVID-19 topics with text classification of Twitters

Contact Info

Product

Resources

About