Replication of the Reliability Prediction for Health-Related Content A Replicability Study
Mirjana Sadikovikj, TOBIAS ABRAHAM HAIDER, WANJIA TANG, ANUM HAFEEZ · Zenodo (CERN European Organization for Nuclear Research) · 2023
This study aims to replicate the work of Sondhi and his colleagues, who proposed a method for determining the reliability of online health-related content using support vector machines based on a set of linguistic and web-specific features extracted from web sites. Our replication study made use of the code provided by the authors and aimed to make it more reproducible by updating outdated libraries and replacing custom implementations with standard ones. We were able to obtain results that were consistent with the original study, and our replication effort has resulted in a refactored version of the original code that is now also available to the research community. Our replication effort confirmed the conclusions of the original study and highlighted some challenges involved in replication of research