Understanding LDA in source code analysis

Abstract

Latent Dirichlet Allocation (LDA) has seen increasing use in the understanding of source code and its related artifacts in part because of its impressive modeling power. However, this expressive power comes at a cost: the technique includes several tuning parameters whose impact on the resulting LDA model must be carefully considered. An obvious example is the burn-in period; too short a burn-in period leaves excessive echoes of the initial uniform distribution. The aim of this work is to provide insights into the tuning parameter's impact. Doing so improves the comprehension of both, 1) researchers who look to exploit the power of LDA in their research and 2) those who interpret the output of LDA-using tools. It is important to recognize that the goal of this work is not to establish values for the tuning parameters because there is no universal best setting. Rather, appropriate settings depend on the problem being solved, the input corpus (in this case, typically words from the source code and its supporting artifacts), and the needs of the engineer performing the analysis. This work's primary goal is to aid software engineers in their understanding of the LDA tuning parameters by demonstrating numerically and graphically the relationship between the tuning parameters and the LDA output. A secondary goal is to enable more informed setting of the parameters. Results obtained using both production source code and a synthetic corpus underscore the need for a solid understanding of how to configure LDA's tuning parameters.

Clustering Classes in Packages for Program Comprehension

“…In this article, to effectively use LDA, we apply it in a package-level corpus rather than each class to extract the latent topics to simulate the functional features or concerns for a package since small (class-level) corpus is too small to generate good topics [19][20][21][22][23]. Then, we cluster the classes according to these topics and assign different classes to their corresponding topics [23].…”

“…Program comprehension is one of the most important activities in software maintenance and reverse engineering [8,10,23,44,45]. Clustering techniques are commonly used to decompose a software system into small units for easier comprehension.…”

Using Hierarchical Latent Dirichlet Allocation to Construct Feature Tree for Program Comprehension

“…There are a number of studies focusing on this area [10,[34][35][36][37][38]. Program clustering is one of the effective ways for program comprehension.…”

ITMViz: Interactive Topic Modeling for Source Code Analysis

“…The collapsed Gibbs sampler also has to be configured with a number of parameters including the number of burn-in iterations, the number of samples, and the sampling interval. These parameters have a significant impact on the resulting topic model in LDA and are subject of studies [11], [12] to help researchers configure LDA when used in the context of source code analysis. Interactive topic modeling has another parameter η which can be used to control the strength of domain knowledge on the inferred topic models, allowing for overriding the user-specified constraints if the underlying data strongly suggests otherwise.…”