e.g. mhealth
Search Results (1 to 10 of 49 Results)
Download search results: CSV END BibTex RIS
Skip search results from other journals and go to results- 22 Journal of Medical Internet Research
- 7 JMIR Infodemiology
- 5 JMIR Formative Research
- 5 JMIR Public Health and Surveillance
- 3 JMIR Medical Informatics
- 2 JMIR Cancer
- 1 JMIR AI
- 1 JMIR Aging
- 1 JMIR Dermatology
- 1 JMIR Human Factors
- 1 JMIR Research Protocols
- 0 Medicine 2.0
- 0 Interactive Journal of Medical Research
- 0 iProceedings
- 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 Challenges
- 0 JMIR Diabetes
- 0 JMIR Biomedical Engineering
- 0 JMIR Data
- 0 JMIR Cardio
- 0 Journal of Participatory Medicine
- 0 JMIR Pediatrics and Parenting
- 0 JMIR Perioperative Medicine
- 0 JMIR Nursing
- 0 JMIRx Med
- 0 JMIRx Bio
- 0 Transfer Hub (manuscript eXchange)
- 0 JMIR Neurotechnology
- 0 Asian/Pacific Island Nursing Journal
- 0 Online Journal of Public Health Informatics
- 0 JMIR XR and Spatial Computing (JMXR)
In past sentiment analyses of large-scale social media content data, human evaluators often examined a subset of the dataset rather than analyzing the entire dataset. The subset was then used as a representative sample to inform the sentiment of the whole dataset [8,9] or as a reference for machine learning classifiers tasked with analyzing the entire dataset [14].
J Med Internet Res 2025;27:e63631
Download Citation: END BibTex RIS
Moreover, sentiment analysis is another NLP technique that enables the analysis of sentiment being expressed in online news to address RQ2 [53,54]. VADER is a lexicon-based sentiment analysis tool that is included in the NLTK and shows high accuracy in news sentiment analysis [55].
J Med Internet Res 2025;27:e66696
Download Citation: END BibTex RIS
A Bag-of-Words representation was derived to enable both word frequency visualization and sentiment evaluation. Word clouds were generated to visually represent the most frequently occurring words for each LLM-generated text. The size and prominence of the words in the cloud reflected their frequency, offering an intuitive summary of the dominant themes and linguistic patterns specific to each model. To assess the emotional tone and polarity of the texts, sentiment analysis was performed using the TDM.
JMIR Form Res 2025;9:e56126
Download Citation: END BibTex RIS
These factors may result in varying word choices and sentiment, even when discussing similar topics. For example, geographic differences can affect how happiness is expressed on the web [32], while daily routines and spatiotemporal context can shape sentiments related to specific locations or events [33,34]. It is important to acknowledge these biases because such factors could influence the patterns observed in our analysis.
J Med Internet Res 2025;27:e58656
Download Citation: END BibTex RIS
To mitigate measurement bias that can result from applying off-the-shelf models to our dataset, we applied 2 popular sentiment analysis tools, specifically, Valence Aware Dictionary for Sentiment Reasoning (VADER) [22] and Linguistic Inquiry and Word Count (LIWC) [23], to calculate the sentiment scores of web-based communications to quantify the overall sentiment expressed. These tools were chosen for their ability to consistently analyze large volumes of text data, making them suitable for our study.
JMIR Aging 2024;7:e60050
Download Citation: END BibTex RIS
We conducted spatiotemporal analysis of the volume, sentiment, and topic of patient experience–related posts on the Weibo platform. Figure 1 shows an overview of this study, which included three distinct stages: (1) data collection and cleaning, (2) data selection and coding, and (3) data analysis and interpretation.
Study design.
JMIR Med Inform 2024;12:e59249
Download Citation: END BibTex RIS
The commercial social media aggregator, Brandwatch was leveraged to gather X/Twitter data and perform sentiment analysis [15,16]. Brandwatch is an official partner of X/Twitter allowing better access to X/Twitter data [17]. The accuracy of Brandwatch’s sentiment analysis is around 75%, which is comparable to other sentiment analysis tools [18-20]. In the tool, a query for the drug “hydroxychloroquine” and “Plaquenil” was added, and the date range was set from November 30, 2019, to January 29, 2021.
JMIR Infodemiology 2024;4:e56675
Download Citation: END BibTex RIS
Advanced analytical techniques, such as sentiment analysis and topic modeling, can be used to explore the complex landscape of opinions and emotions surrounding obesity on social media platforms [14]. Sentiment analysis allows for the systematic identification and categorization of subjective information in textual data, providing insights into the prevailing emotions and opinions expressed in social media posts [15].
J Med Internet Res 2024;26:e52142
Download Citation: END BibTex RIS
Sentiment and emotion analysis are natural language processing (NLP) techniques for the identification of sentiment and emotion from speech or voice data, images, or text data [11-13]. In sentiment analysis, the overall polarity of a text is identified—whether it is positive, negative, or neutral. Emotion analysis involves the identification of specific emotions expressed in a text.
J Med Internet Res 2024;26:e55151
Download Citation: END BibTex RIS
These corpora were then used to train NLP algorithms to automatically extract vaccine sentiment and hesitancy content. Finally, we developed an online dashboard to provide real-time insights into vaccine sentiment and hesitancy trends. Our study focuses on evaluating the vaccine sentiment and hesitancy of human papillomavirus (HPV), MMR, and general or unspecified vaccines.
JMIR Med Inform 2024;12:e57164
Download Citation: END BibTex RIS