A Cloud-Based Platform for Democratizing and Socializing the Benchmarking Process

Performances evaluation, benchmarking and reproducibility represent significant aspects for evaluating the practical impact of scientific research outcomes in the Computer Science field. In spite of all the benefits (e.g., increasing visibility, boosting impact, improving the research quality) which can be obtained from conducting comprehensive and extensive experimental evaluations or providing reproducible software artifacts and detailed description of experimental setup, the required effort for achieving these goals remains prohibitive. In this article, we present the design and the implementation details of the Liquid Benchmarking platform as a social and cloud-based platform for democratizing and socializing the software benchmarking processes. Particularly, the platform facilitates the process of sharing the experimental artifacts (computing resources, datasets, software implementations, benchmarking tasks) as services where the end users can easily design, mashup, execute the experiments and visualize the experimental results with zero installation or configuration efforts. Moreover, the social features of the platform enable the users to share and provide feedback on the results of the executed experiments in a form that can guarantee a transparent scientific crediting process. Finally, we present four benchmarking case studies that have been realized via the Liquid Benchmarking platform in the following domains: XML compression techniques, graph indexing and querying techniques, string similarity join algorithms and reverse K nearest neighbors algorithms. Keywords—Cloud Computing; Benchmarking; Software-as-aService, Social Computing