e.g. mhealth
Search Results (1 to 3 of 3 Results)
Download search results: CSV END BibTex RIS
Skip search results from other journals and go to results- 1 JMIR Formative Research
- 1 JMIR Medical Informatics
- 1 JMIR Public Health and Surveillance
- 0 Journal of Medical Internet Research
- 0 Medicine 2.0
- 0 Interactive Journal of Medical Research
- 0 iProceedings
- 0 JMIR Research Protocols
- 0 JMIR Human Factors
- 0 JMIR mHealth and uHealth
- 0 JMIR Serious Games
- 0 JMIR Mental Health
- 0 JMIR Rehabilitation and Assistive Technologies
- 0 JMIR Preprints
- 0 JMIR Bioinformatics and Biotechnology
- 0 JMIR Medical Education
- 0 JMIR Cancer
- 0 JMIR Challenges
- 0 JMIR Diabetes
- 0 JMIR Biomedical Engineering
- 0 JMIR Data
- 0 JMIR Cardio
- 0 Journal of Participatory Medicine
- 0 JMIR Dermatology
- 0 JMIR Pediatrics and Parenting
- 0 JMIR Aging
- 0 JMIR Perioperative Medicine
- 0 JMIR Nursing
- 0 JMIRx Med
- 0 JMIRx Bio
- 0 JMIR Infodemiology
- 0 Transfer Hub (manuscript eXchange)
- 0 JMIR AI
- 0 JMIR Neurotechnology
- 0 Asian/Pacific Island Nursing Journal
- 0 Online Journal of Public Health Informatics
- 0 JMIR XR and Spatial Computing (JMXR)
After manually analyzing and annotating users’ reviews, we employed both classical (ie, multinomial Naïve Bayes [MNB], support vector machine [SVM], random forest [RF]) and deep learning (ie, neural networks [11], fast Text [12], and different transformers [13]) methods for classification experiments. This resulted in 8 different classification models.
JMIR Form Res 2022;6(5):e36238
Download Citation: END BibTex RIS
We applied 2 unsupervised word embedding models (Word2 Vec [11] and Fast Text [12]) to the Korean medical word pair sets, and the results were compared with those of the human evaluation. A Korean medicine–focused corpus with 129 million words (aforementioned) was used for model training. The preprocessing of the obtained corpus was twofold. First, the entire corpus data were segmented using the Korean Sentence Splitter (KSS) 2.2.0.2.
JMIR Med Inform 2021;9(6):e29667
Download Citation: END BibTex RIS
In this study, we demonstrate that using Fast Text (FT) can enhance the efficiency of Twitter-based flu outbreak prediction models. Originally, FT became an efficient text classifier that was proposed by Facebook. FT performs more quickly than deep learning classifiers for training and testing procedures and produces comparably accurate results. The FT classifier can train more than a billion words in about 10 min and then predict multiple classes within half a million sentences in less than a minute [16].
JMIR Public Health Surveill 2019;5(2):e12383
Download Citation: END BibTex RIS