Data from communication platforms such as instant messaging, email or social media is considered highly sensitive data. As a consequence, it is difficult for researchers to get access to representative data when evaluating communication platforms. This lack of available public data causes two main problems. 1. Research findings may not reflect the real use case, which means the solution either might not work in practice, or the solution’s performance may differ vastly in a real setting. 2. It becomes difficult to compare different research findings if they’re tested on different data. Ideally, researchers would have access to a benchmarking tool that makes the evaluation straightforward, and makes results easy to compare.In this project, we will investigate how communication platform data can be generated and used to build a benchmarking suite.