Using word embedding and convolution neural network for bug triaging by considering design flaws

Resolving bugs in the maintenance phase of software is a complicated task. Bug assignment one main tasks for resolving bugs. Some Bugs cannot be fixed properly without making design decisions and have to assigned designers, rather than programmers, avoid emerging bad smells that may cause subsequent bug reports. Hence, it important refer some designer check possible flaws. Based on our best knowledge, there are few works considered referring designers. this issue work. In paper, dataset created, CNN-based model proposed predict need assigning by learning peculiarities reports effective creating code. The features each extracted from CNN based its textual features, such as summary description. number samples added fixing process using PMD tool determines tag. description new given predicts designer. accuracy 75% (or more) was achieved datasets with sufficient deep learning-based training. A referrals efficiency predicting at time receiving report demonstrated testing 10 projects.