Pengelompokan Artefak Dokumen Perangkat Lunak Open Source Dengan Vektor Paragraf

Guntur Budi Herwanto(1),
(1) Department of Computer Science, Faculty of Mathematics and Natural Science, Universitas Gadjah mada, Indonesia

Abstract


Dalam beberapa tahun belakangan, perangkat lunak open source semakin bertumbuh. Tidak hanya perangkat lunak dalam bentuk final, namun komponen dan library perangkat lunak semakin berkembang setiap tahunnya. Github merupakan salah satu lokasi populer dalam mempublikasikan project open source. Ketersediaan dataset yang besar ini merupakan peluang bagi peneliti di bidang perangkat lunak development dalam mengembangkan risetnya. Perkembangan variasi artefak perangkat lunak membuat metode yang bersifat supervised menjadi sulit. Penilitian ini mencoba untuk melakukan pengelompokkan secara unsupervised dengan teknik clustering K-Means dan representasi paragraph vector. Langkah ini merupakan awalan dalam pembentukan model klasifikasi yang membutuhkan supervisi dalam pelabelan dokumennya. Hasil clustering menunjukkan dokumen dapat dapat di kelompokkan menjadi beberapa cluster dan hasil yang terbaik dilihat pada cluster dengan k berjumlah 6.

Kata Kunci: document clustering, doc2vec, k-means clustering, artefak perangkat lunak.

References


N. Munaiah, S. Kroh, C. Cabrey, and M. Nagappan, “Curating GitHub for engineered software projects,” Empir. Softw. Eng., vol. 22, no. 6, pp. 3219–3253, 2017.

Y. Ma, S. Fakhoury, M. Christensen, and V. Arnaoudova, “Automatic Classification of Software Artifacts in Open-Source Applications,” in The Mining Software Repositories (MSR), 2018.

T. Bi, P. Liang, A. Tang, and C. Yang, “A systematic mapping study on text analysis techniques in software architecture,” J. Syst. Softw., vol. 144, no. May, pp. 533–558, 2018.

M. Soliman, M. Galster, and M. Riebisch, “Developing an Ontology for Architecture Knowledge from Developer Communities,” Proc. - 2017 IEEE Int. Conf. Softw. Archit. ICSA 2017, pp. 89–92, 2017.

W. Ding, P. Liang, A. Tang, H. Van Vliet, and M. Shahin, “How do open source communities document software architecture: An exploratory survey,” Proc. IEEE Int. Conf. Eng. Complex Comput. Syst. ICECCS, pp. 136–145, 2014.

G. Robles, J. M. Gonzalez-barahona, J. L. Prieto, U. Rey, and J. Carlos, “Assessing and Evaluating Documentation in Libre Software Projects ?,” Hum. Factors, no. 004337, 2006.

G. Gousios, “The {GHT}orrent dataset and tool suite,” in Proceedings of the 10th Working Conference on Mining Software Repositories, 2013, pp. 233–236.

D. Blei, L. Carin, and D. Dunson, “Probabilistic topic models,” IEEE Signal Process. Mag., vol. 27, no. 6, pp. 55–65, 2010.

T. Mikolov, I. Sutskever, K. Chen, G. Corrado, and J. Dean, “Distributed Representations of Words and Phrases and Their Compositionality,” in Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 2, 2013, pp. 3111–3119.

Q. Le, T. Mikolov, and T. G. Com, “Distributed Representations of Sentences and Documents,” vol. 32, 2014.

J. MacQueen, “Some methods for classification and analysis of multivariate observations,” in Proc. Fifth Berkeley Symp. Math. Stat. Probab. Vol. 1 Stat., 1967, pp. 281–297.

N. X. Vinh, “Information Theoretic Measures for Clusterings Comparison : Variants , Properties , Normalization and Correction for Chance,” vol. 11, pp. 2837–2854, 2010.

A. Rosenberg and J. Hirschberg, “{V}-Measure: A Conditional Entropy-Based External Cluster Evaluation Measure,” in Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning ({EMNLP}-{C}o{NLL}), 2007, pp. 410–420.




DOI: https://doi.org/10.33369/pseudocode.6.2.182%20–%20186

Article Metrics

 Abstract Views : 0 times
 PDF (Bahasa Indonesia) Downloaded : 0 times

Refbacks

  • There are currently no refbacks.


Copyright (c) 2019 Guntur Budi Herwanto

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Jurnal Pseudocode terindeks

Jurnal Pseudocode
Program Studi Informatika, Fakultas Teknik, Universitas Bengkulu
Jl. W.R. Supratman, Kandang Limun, Bengkulu 38371
Telepon (0736) 344087 Faksimile (0736) 349134
Email: pseudocode@unib.ac.id

Counter Homepage kostenlos

 

Location