Replication package for identifying four types of SATD from four different sources

This dataset includes pre-trained word embeddings and the weighted file for identifying four types (i.e., code/design, requirement, documentation, and test debt) of SATD (self-admitted technical debt) from four different sources (i.e., code comments, issue tracking systems, commit messages, and pull requests).本数据集包含预训练词嵌入，以及用于从四种不同来源（代码注释、问题跟踪系统、提交消息与拉取请求（pull requests））中识别四类SATD（self-admitted technical debt，即自我承认的技术债务）的加权文件，该四类SATD分别为代码/设计债务、需求债务、文档债务与测试债务。