Social Media Discussions About Robotic Total Knee Arthroplasty: Cross-Sectional Analysis
Bibliographic record
Abstract
Background: The advent of robotic total knee arthroplasty (TKA) in the field of orthopedics has caused much discussion on social media. As social media grows, its platforms are becoming an increasingly popular medium for health care-related discussions. Objective: This study aimed to better understand the current public discussion about robotic TKA on social media. We aimed to characterize these discussions by analyzing their contributors, the general sentiment, the temporal trends, and the content. Methods: A comprehensive search of the Twitter database for academic research was performed from inception (March 2006) to April 1, 2023, to identify all tweets related to robotic TKA. General data regarding the tweets and the accounts were retrieved. ChatGPT-4o (OpenAI) was used to categorize the post's content and the accounts into different categories developed via iterative testing. The content was categorized using a rule-based classification algorithm developed using Python to assign categories based on keyword presence, phrase matching, and syntactic patterns. Regarding the accounts, an automated keyword-based rule engine was implemented in Python to classify accounts based on the account's name and description. We used a lexicon-based natural language processing Python library, via ChatGPT-4o, to assign a sentiment to the tweets and conducted subgroup sentiment analysis. Results: A total of 2000 tweets were retrieved for analysis. Account analysis revealed that the most prevalent account categories were "medical professionals" (619/2000, 31.0%), "patients and community" (274/2000, 13.7%), and "media and publications" (268/2000, 13.4%). Content analysis revealed that the most prevalent tweet themes were "technology and innovation" (550/2000, 27.5%), "advertising and promotion" (176/2000, 8.8%), and "research and data" (172/2000, 8.6%). Sentiment analysis showed that 61.6% (1231/2000) of the tweets had a positive sentiment, while 9.2% (183/2000) were neutral, and 29.3% (586/2000) had a negative sentiment. Accounts categorized as "institutions" had the highest prevalence of positive sentiment (165/229, 72.1%), while accounts categorized as "media and publications" had the highest prevalence of negative sentiment (88/268, 32.8%). The number of tweets relating to robotic TKA has been steadily rising since 2016, with a peak incidence of 402 (20.1%) tweets published in 2022. Conclusions: The increased number of tweets with a positive sentiment suggests a positive outlook toward robotic TKA. Institutions had the highest prevalence of positive sentiment, suggesting a possible bias toward positive reporting of robotic TKA, likely for commercial reasons. Media and publications had the highest prevalence of negative sentiment, which may represent skepticism and bias toward negative reporting on robotic technologies in health care. Medical professionals contributed significantly to the discussion about robotic TKA, while patient involvement was relatively small. The number of tweets relating to robotic TKA has been steadily growing since 2016, which indicates that robotic TKA has been gaining in popularity over recent years.
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.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.009 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".