PROJECT TITLE :

An Eye-Tracking Study of Java Programmers and Application to Source Code Summarization

ABSTRACT:

Source Code Summarization is an emerging technology for automatically generating temporary descriptions of code. Current summarization techniques work by choosing a subset of the statements and keywords from the code, and then together with information from those statements and keywords in the outline. The standard of the outline depends heavily on the process of choosing the subset: a high-quality choice would contain the same statements and keywords that a programmer would choose. Unfortunately, little evidence exists about the statements and keywords that programmers read as important when they summarize supply code. In this paper, we tend to gift an eye-tracking study of ten professional Java programmers in that the programmers scan Java methods and wrote English summaries of these methods. We have a tendency to apply the findings to create a completely unique summarization tool. Then, we have a tendency to evaluate this tool. Finally, we any analyze the programmers’ methodology summaries to explore specific keyword usage and provide proof to support the event of supply code summarization systems.