Can Tweets Predict Citations? Metrics of Social Impact Based on Twitter and Correlation with Traditional Metrics of Scientific Impact
Bibliographic record
Abstract
BACKGROUND: Citations in peer-reviewed articles and the impact factor are generally accepted measures of scientific impact. Web 2.0 tools such as Twitter, blogs or social bookmarking tools provide the possibility to construct innovative article-level or journal-level metrics to gauge impact and influence. However, the relationship of the these new metrics to traditional metrics such as citations is not known. OBJECTIVE: (1) To explore the feasibility of measuring social impact of and public attention to scholarly articles by analyzing buzz in social media, (2) to explore the dynamics, content, and timing of tweets relative to the publication of a scholarly article, and (3) to explore whether these metrics are sensitive and specific enough to predict highly cited articles. METHODS: Between July 2008 and November 2011, all tweets containing links to articles in the Journal of Medical Internet Research (JMIR) were mined. For a subset of 1573 tweets about 55 articles published between issues 3/2009 and 2/2010, different metrics of social media impact were calculated and compared against subsequent citation data from Scopus and Google Scholar 17 to 29 months later. A heuristic to predict the top-cited articles in each issue through tweet metrics was validated. RESULTS: A total of 4208 tweets cited 286 distinct JMIR articles. The distribution of tweets over the first 30 days after article publication followed a power law (Zipf, Bradford, or Pareto distribution), with most tweets sent on the day when an article was published (1458/3318, 43.94% of all tweets in a 60-day period) or on the following day (528/3318, 15.9%), followed by a rapid decay. The Pearson correlations between tweetations and citations were moderate and statistically significant, with correlation coefficients ranging from .42 to .72 for the log-transformed Google Scholar citations, but were less clear for Scopus citations and rank correlations. A linear multivariate model with time and tweets as significant predictors (P < .001) could explain 27% of the variation of citations. Highly tweeted articles were 11 times more likely to be highly cited than less-tweeted articles (9/12 or 75% of highly tweeted article were highly cited, while only 3/43 or 7% of less-tweeted articles were highly cited; rate ratio 0.75/0.07 = 10.75, 95% confidence interval, 3.4-33.6). Top-cited articles can be predicted from top-tweeted articles with 93% specificity and 75% sensitivity. CONCLUSIONS: Tweets can predict highly cited articles within the first 3 days of article publication. Social media activity either increases citations or reflects the underlying qualities of the article that also predict citations, but the true use of these metrics is to measure the distinct concept of social impact. Social impact measures based on tweets are proposed to complement traditional citation metrics. The proposed twimpact factor may be a useful and timely metric to measure uptake of research findings and to filter research findings resonating with the public in real time.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.032 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.006 | 0.007 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".