Detection of source code in internet texts using automatically generated machine learning models

• Autorzy: Badurowicz Marcin

Identyfikatory

DOI

10.35784/acs-2022-7

• Języki publikacji: EN

Abstrakty

EN

In the paper, the authors are presenting the outcome of web scraping software allowing for the automated classification of source code. The software system was prepared for a discussion forum for software developers to find fragments of source code that were published without marking them as code snippets. The analyzer software is using a Machine Learning binary classification model for differentiating between a programming language source code and highly technical text about software. The analyzer model was prepared using the AutoML subsystem without human intervention and fine-tuning and its accuracy in a described problem exceeds 95%. The analyzer based on the automatically generated model has been deployed and after the first year of continuous operation, its False Positive Rate is less than 3%. The similar process may be introduced in document management in software development process, where automatic tagging and search for code or pseudo-code may be useful for archiving purposes.

Słowa kluczowe

EN

source code; binary classification; text classification; AutoML

• Wydawca: Polskie Towarzystwo Promocji Wiedzy ; Lublin University of Technology
• Czasopismo: Applied Computer Science
• Rocznik: 2022
• Tom: Vol. 18, no 1
• Strony: 89--98
• Opis fizyczny: Bibliogr. 22 poz., fig., tab.

Twórcy

autor

Badurowicz Marcin

• Lublin University of Technology, Faculty of Electrical Engineering and Computer Science, Department of Computer Science, Poland

• https://orcid.org/0000-0003-2249-4219

Bibliografia

• [1] 4programmers.net. (2000). Forum dyskusyjne dla programistów. https://4programmers.net
• [2] Ahmed, Z., Amizadeh, S., Bilenko, M., Carr, R., Chin, W.-S., Dekel, Y., Dupre, X., Eksarevskiy, V., Filipi, S., Finley, T., Goswami, A., Hoover, M., Inglis, S., Interlandi, M., Kazmi, N., Krivosheev, G., Luferenko, P., Matantsev, I., Matusevych, S., Moradi, S., Nazirov, G., Ormont, J., Oshri, G., Pagnoni, A., Parmar, J., Roy, P., Siddiqui, M. Z., Weimer, M., Zahirazami, S., and Zhu, Y. (2019). Machine Learning at Microsoft with ML.NET. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 2448–2458). Association for Computing Machinery. https://doi.org/10.1145/3292500.3330667
• [3] Alreshedy, K., Dharmaretnam, D., German, D. M., Srinivasan, V., & Gulliver, T. A. (2018). SCC: Automatic Classification of Code Snippets. arXiv:1809.07945. https://doi.org/10.48550/arXiv.1809.07945
• [4] Badurowicz, M. (2020). ktos/Eleia: 4programmers.net bot for nagging users when their code in post is not marked as code. http://github.com/ktos/eleia
• [5] Van Dam, J. K., & Zaytsev, V. (2016). Software Language Identification with Natural Language Classifiers. 2016 IEEE 23rd International Conference on Software Analysis, Evolution, and Reengineering (SANER) (pp. 624–628). IEEE. https://doi.org/10.1109/SANER.2016.92
• [6] Gilda, S. (2017). Source code classification using Neural Networks. 2017 14th International Joint Conference on Computer Science and Software Engineering (JCSSE) (1–6). IEEE. https://doi.org/10.1109/JCSSE.2017.8025917
• [7] GitHub Copilot – Your AI pair programmer. (n.d.). Retrieved January 22, 2021 from https://copilot.github.com
• [8] He, X., Zhao, K., & Chu, X. (2021). AutoML: A survey of the state-of-the-art. Knowledge-Based Systems, 212, 106622. https://doi.org/https://doi.org/10.1016/j.knosys.2020.106622
• [9] Khasnabish, J. N., Sodhi, M., Deshmukh, J., & Srinivasaraghavan, G. (2014). Detecting Programming Language from Source Code Using Bayesian Learning Techniques. In P. Perner (Ed.), Machine Learning and Data Mining in Pattern Recognition (pp. 513–522). Springer International Publishing.
• [10] Kłosowski, G., Kulisz, M., Lipski, J., Maj, M., & Bialek, R. (2021). The Use of Transfer Learning with Very Deep Convolutional Neural Network in Quality Management. European Research Studies Journal, XXIV(Special Issue 2), 253–263. https://doi.org/10.35808/ersj/2222
• [11] Kulisz, M., Kujawska, J., Przysucha, B., & Cel, W. (2021). Forecasting Water Quality Index in Groundwater Using Artificial Neural Network. Energies, 14(18), 5875. https://doi.org/10.3390/en14185875
• [12] LeClair, A., Eberhart, Z., & McMillan, C. (2018). Adapting Neural Text Classification for Improved Software Categorization. 2018 IEEE International Conference on Software Maintenance and Evolution (ICSME) (461–472). IEEE. https://doi.org/10.1109/ICSME.2018.00056
• [13] Linguist. (n.d.). Retrieved January 22, 2022 from https://github.com/github/linguist
• [14] Machrowska, A., Szabelski, J., Karpiński, R., Krakowski, P., Jonak, J., & Jonak, K. (2020). Use of Deep Learning Networks and Statistical Modeling to Predict Changes in Mechanical Parameters of Contaminated Bone Cements. Materials, 13(23), 5419. https://doi.org/10.3390/ma13235419
• [15] Madani, N., Guerrouj, L., Di Penta, M., Gueheneuc, Y.-G., & Antoniol, G. (2010). Recognizing Words from Source Code Identifiers Using Speech Recognition Techniques. 2010 14th European Conference on Software Maintenance and Reengineering (pp. 68–77). IEEE. https://doi.org/10.1109/CSMR.2010.31
• [16] Ohashi, H., & Watanobe, Y. (2019). Convolutional Neural Network for Classification of Source Codes. 2019 IEEE 13th International Symposium on Embedded Multicore/Many-Core Systems-on-Chip (MCSoC) (pp. 194–200). IEEE. https://doi.org/10.1109/MCSoC.2019.00035
• [17] Pygments - Python syntax highlighter. (n.d.). Retrieved January 22, 2021 from https://pygments.org
• [18] Sobaszek, Ł., Gola, A., & Kozłowski, E. (2020). Predictive Scheduling with Markov Chains and ARIMA Models. Applied Sciences, 10(17), 6121. https://doi.org/10.3390/app10176121
• [19] Szabelski, J., Karpiński, R., & Machrowska, A. (2022). Application of an Artificial Neural Network in the Modelling of Heat Curing Effects on the Strength of Adhesive Joints at Elevated Temperature with Imprecise Adhesive Mix Ratios. Materials, 15(3), 721. https://doi.org/10.3390/ma15030721
• [20] Ugurel, S., Krovetz, R., & Giles, C. L. (2002). What’s the Code? Automatic Classification of Source Code Archives. Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 632–638). ACM Digital Library. https://doi.org/10.1145/775047.775141
• [21] Wever, M., Tornede, A., Mohr, F., & Hullermeier, E. (2021). AutoML for Multi-Label Classification: Overview and Empirical Evaluation. IEEE Transactions on Pattern Analysis & Machine Intelligence, 43(09), 3037–3054. https://doi.org/10.1109/TPAMI.2021.3051276
• [22] Yin, P., Deng, B., Chen, E., Vasilescu, B., & Neubig, G. (2018). Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow. International Conference on Mining Software Repositories (pp. 476–486). ACM Digital Library. https://doi.org/10.1145/3196398.3196408