English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

In recent work, we identified and studied a small cohort of Twitter userswhose pregnancies with birth defect outcomes could be observed via theirpublicly available tweets. Exploiting social media's large-scale potential tocomplement the limited methods for studying birth defects, the leading cause ofinfant mortality, depends on the further development of automatic methods. Theprimary objective of this study was to take the first step towards scaling theuse of social media for observing pregnancies with birth defect outcomes,namely, developing methods for automatically detecting tweets by usersreporting their birth defect outcomes. We annotated and pre-processedapproximately 23,000 tweets that mention birth defects in order to train andevaluate supervised machine learning algorithms, including feature-engineeredand deep learning-based classifiers. We also experimented with variousunder-sampling and over-sampling approaches to address the class imbalance. ASupport Vector Machine (SVM) classifier trained on the original, imbalanceddata set, with n-grams, word clusters, and structural features, achieved thebest baseline performance for the positive classes: an F1-score of 0.65 for the"defect" class and 0.51 for the "possible defect" class. Our contributionsinclude (i) natural language processing (NLP) and supervised machine learningmethods for automatically detecting tweets by users reporting their birthdefect outcomes, (ii) a comparison of feature-engineered and deeplearning-based classifiers trained on imbalanced, under-sampled, andover-sampled data, and (iii) an error analysis that could inform classificationimprovements using our publicly available corpus. Future work will focus onautomating user-level analyses for cohort inclusion.

Automatically Detecting Self-Reported Birth Defect Outcomes on Twitter for Large-scale Epidemiological Research