Abstract
Social media has recently become a basic source for news consumption and sharing among millions of users. Social media platforms enable users to publish and share their own generated content with little or no restrictions. However, this gives an opportunity for the spread of inaccurate or misleading content, which can badly affect users' beliefs and decisions. This is why credibility assessment of social media content has recently received tremendous attention. The majority of the studies in the literature focused on identifying features that provide a high predictive power when fed to data mining models and select the model with the highest predictive performance given those features. Results of these studies are conflicting regarding the best model. Additionally, they disregarded the fact that real-time credibility assessment is needed and thus time and resources consumption is crucial for model selection. This study tries to fill this gap by investigating the performance of different data mining techniques for credibility assessments in terms of both functional and operational characteristics for a balanced evaluation that considers both model performance and interoperability.