EP.TU.157Can Twitter Attention Predict Citation Metrics? A Machine Learning Aided Analysis

Abstract Aims Surgical journals have developed social media profiles to increase engagement though it remains unclear as whether attention indices for publications act a surrogate or predictor of traditional citation metrics. This study used machine learning determine if there is relationship between Twitter mentions and number citations surgical publications. Methods We identified all original research review papers published in Annals Surgery, BJS JAMA Surgery 2019. Citations data were retrieved the Spearman rank coefficient was degree correlation two variables. An unsupervised machine-learning hierarchical clustering algorithm define clusters outlying papers. Quantitative qualitative analysis completed. Results 413 selected. Median 7 (IQR 3-14), median 40 15-79). No observed (Spearman’s rho 0.076 p-value 0.124). Cluster one large (cluster 2, 367/413 papers) six small clusters. Analysis cluster 2 revealed weak but significant 0.107 0.041). The remaining characterised by an out proportion compared vice versa. Conclusions should not be In our database skewed