Filters








135 Hits in 7.7 sec

Deep Learning for Relevance Filtering in Syndromic Surveillance: A Case Study in Asthma/Difficulty Breathing

Oduwa Edo-Osagie, Beatriz De La Iglesia, Iain Lake, Obaghe Edeghere
2019 Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods  
Finally, the deep learning methods enabled us to gather context and word similarity information which we can use to fine tune the vocabulary we employ to extract relevant Tweets in the first place.  ...  In this paper, we investigate deep learning methods that may extract some word context for Twitter mining for syndromic surveillance.  ...  Beatriz De La Iglesia and Iain Lake receive support from the National Institute for Health Research Health Protection Research Unit (NIHR HPRU) in Emergency Preparedness and Response.  ... 
doi:10.5220/0007366904910500 dblp:conf/icpram/Edo-OsagieILE19 fatcat:np22lrd7ofgenilgdebt7qpp6u

Public Perception Analysis of Tweets During the 2015 Measles Outbreak: Comparative Study Using Convolutional Neural Network Models

Jingcheng Du, Lu Tang, Yang Xiang, Degui Zhi, Jun Xu, Hsing-Yi Song, Cui Tao
2018 Journal of Medical Internet Research  
We compared the performance of the CNN models to those of 4 conventional machine learning models and another neural network model.  ...  neural network (CNN) models (compared with conventional machine learning methods) on measles outbreak-related tweets classification tasks with a relatively small and highly unbalanced gold standard training  ...  Diseases of the National Institutes of Health under award number R01AI130460, and the UTHealth Innovation for Cancer Prevention Research Training Program Pre-Doctoral Fellowship (Cancer Prevention and  ... 
doi:10.2196/jmir.9413 pmid:29986843 pmcid:PMC6056740 fatcat:fd6aznkjarbhbpolfaas4gwo6y

Recent Advances in Using Natural Language Processing to Address Public Health Research Questions Using Social Media and ConsumerGenerated Data

Mike Conway, Mengke Hu, Wendy W. Chapman
2019 IMIA Yearbook of Medical Informatics  
Finally, we found that in the period under review "modern" machine learning methods (i.e. deep neural-network-based methods), while increasing in popularity, remain less widely used than "classical" machine  ...  However, mental health and substance use and abuse (including the use of tobacco, alcohol, marijuana, and opioids) have been the subject of an increasing volume of research in the 2016 - 2018 period.  ...  The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.  ... 
doi:10.1055/s-0039-1677918 pmid:31419834 pmcid:PMC6697505 fatcat:r5ubjbhoszh47flxg6tf7n5eku

Twitter mining using semi-supervised classification for relevance filtering in syndromic surveillance

Oduwa Edo-Osagie, Gillian Smith, Iain Lake, Obaghe Edeghere, Beatriz De La Iglesia, Olalekan Uthman
2019 PLoS ONE  
We investigate the use of Twitter data to deliver signals for syndromic surveillance in order to assess its ability to augment existing syndromic surveillance efforts and give a better understanding of  ...  Additionally, we highlight the use of emojis and other special features capturing the tweet's tone to improve the classification performance.  ...  Acknowledgments We acknowledge support from NHS 111 and NHS Digital for their assistance with the NHS 111 system; Out-of-Hours providers submitting data to the GPOOH syndromic surveillance and Advanced  ... 
doi:10.1371/journal.pone.0210689 pmid:31318885 pmcid:PMC6638773 fatcat:2kqtjnjrjvcdxcfqaur6765imu

Ontology-driven aspect-based sentiment analysis classification: An infodemiological case study regarding infectious diseases in Latin America

José Antonio García-Díaz, Mar Cánovas-García, Rafael Valencia-García
2020 Future generations computer systems  
This new information is subsequently applied in order to build an aspect-based sentiment analysis model based on statistical and linguistic features. This is done by applying deep-learning models.  ...  The appearance of this new data source, which was previously unimaginable, has opened up a new way in which to improve public health systems, resulting in better communication policies and better detection  ...  Acknowledgements This work has been supported by the Spanish National Research Agency (AEI) and the European Regional Development Fund (FEDER/ERDF) through projects KBS4FIA (TIN2016-76323-R) and LaTe4PSP  ... 
doi:10.1016/j.future.2020.06.019 pmid:32572291 pmcid:PMC7301140 fatcat:xxt6mfojevf3zhpu4fchr3lzuq

Text Classification Models for the Automatic Detection of Nonmedical Prescription Medication Use from Social Media [article]

Mohammed Ali Al-Garadi, Yuan-Chi Yang, Haitao Cai, Yucheng Ruan, Karen O'Connor, Graciela Gonzalez-Hernandez, Jeanmarie Perrone, Abeed Sarker
2020 medRxiv   pre-print
We experimented with state-of-the-art bi-directional transformer-based language models, which utilize tweet-level representations that enable transfer learning (e.g., BERT, RoBERTa, XLNet, AlBERT, and  ...  In this paper, we describe the development and evaluation of automatic text classification models for detecting self-reports of PM abuse from Twitter.  ...  The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIH.  ... 
doi:10.1101/2020.04.13.20064089 fatcat:iei7ywd3lzc3dejklcyhfrvoty

Detecting Dengue/Flu Infections based on Tweets using LSTM and Word Embedding

Samina Amin, M. Irfan Uddin, M. Ali Zeb, Ala Abdulsalam Alarood, Marwan Mahmoud, Monagi H. Alkinani
2020 IEEE Access  
Zhang et al. developed [33] a model where they focused on syntactic and semantic information of tweets, using a hybrid of Gated Recurrent Unit (GRU) and Artificial Neural Network (ANN).  ...  as Recurrent Neural Networks (RNNs) with LSTM and Word2Vec approaches. 1) LITERATURE ON DISEASE DETECTION IN SOCIAL MEDIA The related work conducted on flu and dengue outbreaks using OSNSs data as follows  ...  He currently serves as coordinator of the R&D program for the Ministry of Education.  ... 
doi:10.1109/access.2020.3031174 fatcat:hosbf5toujdtzepprtptrbh3me

Mining social media for prescription medication abuse monitoring: a review and proposal for a data-centric framework

2019 JAMIA Journal of the American Medical Informatics Association  
There is a paucity of standardized, data-centric frameworks for curating social media data for task-specific analyses and near real-time surveillance of nonmedical PM use.  ...  Prescription medication (PM) misuse and abuse is a major health problem globally, and a number of recent studies have focused on exploring social media as a resource for monitoring nonmedical PM use.  ...  Both traditional and neural network-based classifiers were experimented with.  ... 
doi:10.1093/jamia/ocz162 pmid:31584645 pmcid:PMC7025330 fatcat:ilk34pcwkjdgvectwvz26hheoq

Multi-Label Classification of Microblogging Texts using Convolution Neural Network

Md. Aslam Parwez, Muhammad Abulaish, Jahiruddin Jahiruddin
2019 IEEE Access  
Nowadays, the use of feature vectors, such as word embeddings, as an input to neural networks for text classification and clustering has shown a remarkable performance gain.  ...  Traditional machine learning approaches mainly use a bag of words or n-gram techniques to generate feature vectors as text representation to train classifiers and perform considerably well for many text  ...  Recurrent neural networks are the most widely used neural networks by machine learning professionals.  ... 
doi:10.1109/access.2019.2919494 fatcat:ruebxamsxfdjzoxnqrwonovnyu

Evolutionary clustering and community detection algorithms for social media health surveillance

Heba Elgazzar, Kyle Spurlock, Tanner Bogart
2021 Machine Learning with Applications  
This research proposes a new potential surveillance avenue through unsupervised machine learning using dynamic, evolutionary variants of clustering algorithms DBSCAN and the Louvain method to allow for  ...  community detection in temporal networks.  ...  Both fields of supervised and unsupervised machine learning have been commonly proposed for applications of health surveillance.  ... 
doi:10.1016/j.mlwa.2021.100084 pmid:34939040 pmcid:PMC8470901 fatcat:744dqfrk7rdibazqf7mv4oglou

Multi-Task Pharmacovigilance Mining from Social Media Posts

Shaika Chowdhury, Chenwei Zhang, Philip S. Yu
2018 Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18  
Aiming to effectively monitor various aspects of Adverse Drug Reactions (ADRs) from diversely expressed social medical posts, we propose a multi-task neural network framework that learns several tasks  ...  Besides being able to correctly classify ADR posts and accurately extract ADR mentions from online posts, the proposed framework is also able to further understand reasons for which the drug is being taken  ...  . • CRNN: State-of-the-art model for doing ADR Classification task. CRNN [13] is a convolutional neural network concatenated with a recurrent neural network.  ... 
doi:10.1145/3178876.3186053 dblp:conf/www/ChowdhuryZY18 fatcat:v5swpkoqpbbqtjigydzeyy3hre

Text classification models for the automatic detection of nonmedical prescription medication use from social media

Mohammed Ali Al-Garadi, Yuan-Chi Yang, Haitao Cai, Yucheng Ruan, Karen O'Connor, Gonzalez-Hernandez Graciela, Jeanmarie Perrone, Abeed Sarker
2021 BMC Medical Informatics and Decision Making  
In this paper, we describe the development and evaluation of automatic text classification models for detecting self-reports of PM abuse from Twitter.  ...  Methods We experimented with state-of-the-art bi-directional transformer-based language models, which utilize tweet-level representations that enable transfer learning (e.g., BERT, RoBERTa, XLNet, AlBERT  ...  of the dominant NN architectures for text classification is the recurrent neural network (RNN) [47, 48] .  ... 
doi:10.1186/s12911-021-01394-0 pmid:33499852 fatcat:peoffb3hojbi5chkzkvt2klcjy

Towards Deep Learning Prospects: Insights for Social Media Analytics

Malik Khizar Hayat, Ali Daud, Abdulrahman A. Alshdadi, Ameen Banjar, Rabeeh Ayaz Abbasi, Yukun Bao, Hussain Dawood
2019 IEEE Access  
INDEX TERMS Social media data, dynamic network, deep learning, feature learning. 36958 He has published about 70 papers in reputed international Impact Factor journals and conferences.  ...  In order to the exponential development and widespread availability of digital social media (SM), analyzing these data using traditional tools and technologies is tough or even intractable.  ...  In terms of DL, the authors fused two NN models; one is CNN used for feature extraction from tweets, and Gates Recurrent Neural Network GRNN that uses sequential data where input are dependent upon the  ... 
doi:10.1109/access.2019.2905101 fatcat:65mxyey3frdrfngvbfnfss3gpa

Detecting and Explaining Crisis

Rohan Kshirsagar, Robert Morris, Samuel Bowman
2017 Proceedings of the Fourth Workshop on Computational Linguistics and Clinical Psychology –- From Linguistic Signal to Clinical Reality  
We explore several methods to detect and explain crisis using a combination of neural and non-neural techniques.  ...  Our best technique significantly outperforms the baseline for detection and explanation.  ...  Bowman acknowledges support from a Google Faculty Research Award and gifts from Tencent Holdings and NVIDIA Corporation. We thank Koko for contributing a unique dataset for this research.  ... 
doi:10.18653/v1/w17-3108 dblp:conf/acl-clpsych/KshirsagarMB17 fatcat:7u6cxeifpfebthw5o4s6wgf6y4

Detecting and Explaining Crisis [article]

Rohan Kshirsagar, Robert Morris, Sam Bowman
2017 arXiv   pre-print
We explore several methods to detect and explain crisis using a combination of neural and non-neural techniques.  ...  Our best technique significantly outperforms the baseline for detection and explanation.  ...  Bowman acknowledges support from a Google Faculty Research Award and gifts from Tencent Holdings and NVIDIA Corporation. We thank Koko for contributing a unique dataset for this research.  ... 
arXiv:1705.09585v1 fatcat:yjvk7ejngnabnjarkvngfc5x34
« Previous Showing results 1 — 15 out of 135 results