Duplicate Detection Models for Bug Reports of Software Triage Systems: A Survey

Abstract

Duplicate bug report detection (DBRD) is one of the significant problems of software triage systems, which receive end-user bug reports. DBRD needs automation using artificial intelligence techniques like information retrieval, natural language processing, text and data mining, and machine learning. There are two models of duplicate detection as follows: The first model uses machine learning techniques to learn the features of duplication between pairs of bug reports. The second model called IR-based that use a similarity metric like REP or BM25F to rank top-k bug reports that are similar to a target bug report. The IR-based approach has identical behavior like the k-nearest neighborhood algorithm of machine learning. This study reviews a decade of duplicate detection techniques and their pros and cons. Besides, the metrics of their validation performance will be studied.