Eye movements of developers are used to speculate the mental cognition model (i.e., bottom-up or top-down) applied during program comprehension tasks. The cognition models examine how programmers understand source code by describing the temporary information structures in the programmer's short term memory. The two types of models that we are interested in are top-down and bottom-up. The top-down model is normally applied as-needed (i.e., the domain of the system is familiar). The bottom-up model is typically applied when a developer is not familiar with the domain or the source code. An eye-tracking study of 18 developers reading and summarizing Java methods is used as our dataset for analyzing the mental cognition model. The developers provide a written summary for methods assigned to them. In total, 63 methods are used from five different systems. The results indicate that on average, experts and novices read the methods more closely (using the bottom-up mental model) than bouncing around (using top-down). However, on average novices spend longer gaze time performing bottom-up (66s.) compared to experts (43s.)

The paper partially replicates and extends a previous study by Busjahn et al. [4] on the factors influencing dwell time during source code reading, where source code element type and frequency of gaze visits are studied as factors. Unlike the previous study, this study focuses on analyzing eye movement data in large open source Java projects. Five experts and thirteen novices participated in the study where the main task is to summarize methods. The results examine semantic line-level information that developers view during summarization. We find no correlation between the line length and the total duration of time spent looking on the line even though it exists between a token's length and the total fixation time on the token reported in prior work. The first fixations inside a method are more likely to be on a method's signature, a variable declaration, or an assignment compared to the other fixations inside a method. In addition, it is found that smaller methods tend to have shorter overall fixation duration for the entire method, but have significantly longer duration per line in the method. The analysis provides insights into how source code's unique characteristics can help in building more robust methods for analyzing eye movements in source code and overall in building theories to support program comprehension on realistic tasks.

An eye-tracking study of 18 developers reading and summarizing Java methods is presented. The developers provide a written summary for methods assigned to them. In total, 63 methods are used from five different systems. Previous studies on this topic use only short methods presented in isolation usually as images. In contrast, this work presents the study in the Eclipse IDE allowing access to all the source code in the system. The developer can navigate via scrolling and switching files while writing the summary. New eye-tracking infrastructure allows for this improvement in the study environment. Data collected includes eye gazes on source code, written summaries, and time to complete each summary. Unlike prior work that concluded developers focus on the signature the most, these results indicate that they tend to focus on the method body more than the signature. Moreover, both experts and novices tend to revisit control flow terms rather than reading them for a long period. They also spend a significant amount of gaze time and have higher gaze visits when they read call terms. Experts tend to revisit the body of the method significantly more frequently than its signature as the size of the method increases. Moreover, experts tend to write their summaries from source code lines that they read the most.

Two studies are conducted to evaluate an approach to automatically generate natural language documentation summaries for C++ methods. The documentation approach relies on a method's stereotype information. First, each method is automatically assigned a stereotype(s) based on static analysis and a set of heuristics. Then, the approach uses the stereotype information, static analysis, and predefined templates to generate a natural-language summary/documentation for each method. This documentation is automatically added to the code base as a comment for each method. The result of the first study reveals that the generated documentation is accurate, does not include unnecessary information, and does a reasonable job describing what the method does. Based on statistical analysis of the second study, the most important part of the documentation is the short description as it describes the intended behavior of a method.

An approach to automatically generate natural language documentation summaries for C++ methods is presented. The approach uses prior work by the authors on stereotyping methods along with the source code analysis framework srcML. First, each method is automatically assigned a stereotype(s) based on static analysis and a set of heuristics. Then, the approach uses the stereotype information, static analysis, and predefined templates to generate a natural-language summary for each method. This summary is automatically added to the code base as a comment for each method. The predefined templates are designed to produce a generic summary for specific method stereotypes. Static analysis is used to extract internal details about the method (e.g., parameters, local variables, calls, etc.). This information is used to specialize the generated summaries.