MétaCan
Menu
Back to cohort
Record W2800727526 · doi:10.2196/publichealth.5789

Sentiment Analysis of Health Care Tweets: Review of the Methods Used

2018· review· en· W2800727526 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

venuePublished in a venue whose home country is Canada.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueJMIR Public Health and Surveillance · 2018
Typereview
Languageen
FieldSocial Sciences
TopicSocial Media in Health Education
Canadian institutionsnot available
FundersNational Institute for Health and Care Research
KeywordsHealth careSentiment analysisData scienceComputer scienceInformation retrievalPolitical scienceNatural language processing

Abstract

fetched live from OpenAlex

BACKGROUND: Twitter is a microblogging service where users can send and read short 140-character messages called "tweets." There are several unstructured, free-text tweets relating to health care being shared on Twitter, which is becoming a popular area for health care research. Sentiment is a metric commonly used to investigate the positive or negative opinion within these messages. Exploring the methods used for sentiment analysis in Twitter health care research may allow us to better understand the options available for future research in this growing field. OBJECTIVE: The first objective of this study was to understand which tools would be available for sentiment analysis of Twitter health care research, by reviewing existing studies in this area and the methods they used. The second objective was to determine which method would work best in the health care settings, by analyzing how the methods were used to answer specific health care questions, their production, and how their accuracy was analyzed. METHODS: A review of the literature was conducted pertaining to Twitter and health care research, which used a quantitative method of sentiment analysis for the free-text messages (tweets). The study compared the types of tools used in each case and examined methods for tool production, tool training, and analysis of accuracy. RESULTS: A total of 12 papers studying the quantitative measurement of sentiment in the health care setting were found. More than half of these studies produced tools specifically for their research, 4 used open source tools available freely, and 2 used commercially available software. Moreover, 4 out of the 12 tools were trained using a smaller sample of the study's final data. The sentiment method was trained against, on an average, 0.45% (2816/627,024) of the total sample data. One of the 12 papers commented on the analysis of accuracy of the tool used. CONCLUSIONS: Multiple methods are used for sentiment analysis of tweets in the health care setting. These range from self-produced basic categorizations to more complex and expensive commercial software. The open source and commercial methods are developed on product reviews and generic social media messages. None of these methods have been extensively tested against a corpus of health care messages to check their accuracy. This study suggests that there is a need for an accurate and tested tool for sentiment analysis of tweets trained using a health care setting-specific corpus of manually annotated tweets first.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.019
metaresearch head score (Gemma)0.007
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Review · Consensus signal: Review
Teacher disagreement score0.984
Threshold uncertainty score0.985

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0190.007
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0040.001
Bibliometrics0.0000.005
Science and technology studies0.0010.001
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.251
GPT teacher head0.556
Teacher spread0.305 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it