Human-like summaries from heterogeneous and time-windowed software development artefacts

• Main Authors: ALGHAMDI, Mahfouth, TREUDE, Christoph, WAGNER, Markus
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2020
• Subjects: Extractive summarisation; Heuristic optimisation; Software development; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/8949; https://ink.library.smu.edu.sg/context/sis_research/article/9952/viewcontent/ppsn20.pdf
• Institution: Singapore Management University

Automatic text summarisation has drawn considerable interest in the area of software engineering. It is challenging to summarise the activities related to a software project, (1) because of the volume and heterogeneity of involved software artefacts, and (2) because it is unclear what information a developer seeks in such a multi-document summary. We present the first framework for summarising multi-document software artefacts containing heterogeneous data within a given time frame. To produce human-like summaries, we employ a range of iterative heuristics to minimise the cosine-similarity between texts and high-dimensional feature vectors. A first study shows that users find the automatically generated summaries the most useful when they are generated using word similarity and based on the eight most relevant software artefacts.