View article

Current research in software engineering has mostly focused on the retrieval accuracy aspect but little on the presentation aspect of code examples, e.g., how code examples are presented in a result page. We investigate the feasibility of summarizing code examples for better presenting a code example. Our algorithm based on machine learning could approximate summaries in an oracle manually generated by humans with a precision of 0.71. This result is promising as summaries with this level of precision achieved the same level of agreement as human annotators with each other.