Cosine Similarity through Control Flow Graphs for Secure Software Engineering

Astrit Desku, Bujar Raufi, Artan Luma, Besnik Selimi

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

As the recommender systems need data to generate a recommendation, the dataset is intended as a standardized input for research on recommendation systems for software engineering but is also useful in many other areas that analyze source code. In this paper, we present a collection of 557-cryptography C# solutions, which includes 19590 classes. From these repositories of classes are generated two datasets with 19, 590 lines of code, respectively 1, 191, 340 lines of code using control flow graph rules. For two datasets are calculated TF-IDF and Cosine Similarity.

Original languageEnglish
Title of host publication7th International Conference on Engineering and Emerging Technologies, ICEET 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages4
ISBN (Electronic)9781665427142
DOIs
Publication statusPublished - 2021
Externally publishedYes
Event7th International Conference on Engineering and Emerging Technologies, ICEET 2021 - Istanbul, Turkey
Duration: 27 Oct 202128 Oct 2021

Publication series

Name7th International Conference on Engineering and Emerging Technologies, ICEET 2021

Conference

Conference7th International Conference on Engineering and Emerging Technologies, ICEET 2021
Country/TerritoryTurkey
CityIstanbul
Period27/10/2128/10/21

Keywords

  • Control Flow Graph
  • Cosine Similarity
  • Machine Learning
  • Recommender Systems
  • TF-IDF

Fingerprint

Dive into the research topics of 'Cosine Similarity through Control Flow Graphs for Secure Software Engineering'. Together they form a unique fingerprint.

Cite this