Using latent semantic analysis to identify similarities in source code to support program understanding

JI Maletic, A Marcus - … on tools with artificial intelligence. ICTAI …, 2000 - ieeexplore.ieee.org
… By applying LSA to source code and its associated … similarity measures. A number of
metrics are defined based on these similarity measures to help support program understanding. …

An empirical study of the textual similarity between source code and source code summaries

PW McBurney, C McMillan - Empirical Software Engineering, 2016 - Springer
… the similarity of those summaries to source code. This study found that the similarity to a
method’s source code … to better understand the relationships that exist between source code and …

Deep learning similarities from different representations of source code

M Tufano, C Watson, G Bavota, M Di Penta… - … on mining software …, 2018 - dl.acm.org
… The goal of this study is to investigate whether source code similarity can be learned from
different kinds of program representations, with the purpose of understanding whether one can …

Explanation in code similarity investigation

O Karnalim - IEEE Access, 2021 - ieeexplore.ieee.org
… An obvious example of this in programming is source code comments, which are generally
easier to understand than the code itself. In light of this benefit, several studies automatically …

A study of the uniqueness of source code

M Gabel, Z Su - … international symposium on Foundations of software …, 2010 - dl.acm.org
… to study the intuitive idea of incidental similarity in source code. In addition to the information
… We do not have a complete explanation for these phenomena, but we hypothesize that they …

Source-code similarity detection and detection tools used in academia: a systematic review

M Novak, M Joy, D Kermek - ACM Transactions on Computing Education …, 2019 - dl.acm.org
… transformations” [160] and “A plagiarized program can be defined as a program that has
been produced from another program without a detailed understanding of the source code” [98]. …

Towards learning (dis)-similarity of source code from program contrasts

Y Ding, L Buratti, S Pujar, A Morari, B Ray… - arXiv preprint arXiv …, 2021 - arxiv.org
Understanding the functional (dis)-similarity of source code is significant for code modeling
tasks such as software vulnerability and code … We present DISCO (DISsimilarity of COde), a …

A comparison of code similarity analysers

C Ragkhitwetsagul, J Krinke, D Clark - Empirical Software Engineering, 2018 - Springer
… In this paper, we fill the gap by presenting the largest extant study on source code similarity
that covers the … from reverse engineering by making it difficult or impossible to understand. …

Semantic clustering: Identifying topics in source code

A Kuhn, S Ducasse, T Gîrba - Information and software technology, 2007 - Elsevier
… of source code are overlooked. To understand software as a whole, we need to enrich software
analysis with the … We use this similarity measurement to identify topics in the source code. …

Semantic similarity metrics for evaluating source code summarization

S Haque, Z Eberhart, A Bansal… - … Conference on Program …, 2022 - dl.acm.org
… a brief description of a section of source code that helps programmers understand what the
… to determine the level of semantic similarity between source code summaries, and the level …