Today’s collaborative platforms, such as GitHub and Slack, are essential parts of the daily routine of anyone who works in IT. Data aggregated by these platforms has significant value for socio-technical assistance algorithms designed to improve the working conditions for employees. However, the way this data is distributed across various platforms makes it very time-consuming to collect and combine. As a result, the existing algorithms for socio-technical assistance (such as recommendation systems for channels in messengers) are based only on data directly related to the purpose of the algorithms.

In this project, we collected a dataset that comprises data on channel activity, technical repositories (including commit history), and organization structure. We built several types of Space channel recommendation systems based on different combinations of data types. The best of the constructed models were then fused into a multimodal channel recommendation system.