Analysis of written interactions in open-source communities using RCNN

Abstract

Open-source software has proved to be a key pillar in modern-day software development. The growing size of the open-source communities has significantly increased the throughput of these projects. However, larger communities tend to lead to difficulties in communication and openness for newer members. In this paper, we try to analyze the interactions on Github for some of the popular open-source projects. We have created a database of 2500 filtered comments classified into five classes of emotion. We have also proposed a novel RCNN based architecture to detect the sentiment of the comments and perform multiclass text classification. Furthermore, we have discussed possible model integrations with existing open-source platforms and the challenges associated with the implementation. © 2021 IEEE.