SISTEM DETEKSI KERUSAKAN PADA SISTEM OPERASI MENGGUNAKAN METODE TF-IDF DAN COSINE SIMILARITY

  • Aa Zezen Zaenal Abidin stmik subang
  • Andi Sukmadinata

Abstract

System damage to the operating system, errors in the operating system, with damage to software and hardware. The detection system is expected to be more flexible than an ordinary expert system, because in an ordinary expert system the consultation is guided while in the detection system using the text similarity method, the user can express the consultation using free expressions on the user consultation menu by using the user consultation text. The system uses the Term Frequency-Inverse Document Frequency method. Once the operating system malfunction query is filled in to the system, the query preprocessing is carried out and the text document is in the database, dedicating the weight of the relationship of a word to the document. After doing the word weighting process, then do the document crunching against the query using the Cosine Similarity method. A collection of text that has been classified in the database which is used as the basis of knowledge and the text consulted as a query, obtained the operating system damage detection system with two categories, namely software and hardware damage. The system is able to create consulted crashes by checking the similarity of the query text and knowledge base. The results of the evaluation using a matrix that shows an accuracy value of 70 percent, the next research in error detection using text similarity is expected to increase the reliability of the system with even greater assessments.

References

[1] R. Ju, P. Zhou, C. H. Li, and L. Liu, “An Efficient Method for Document Categorization Based on Word2vec and Latent Semantic Analysis,” 2015.
[2] B. Kuyumcu, B. BULUZ, and Y. KOMECOGLU, “Ridge Regresyon Analizi ile Türkçe Dokümanlarda Yazar Tanıma Author Identification in Turkish Documents with Ridge Regression Analysis,” pp. 0–3, 2019.
[3] A. Mishra and S. Vishwakarma, “Analysis of TF-IDF Model and its Variant for Document Retrieval,” pp. 772–776, 2015.
[4] H. Ma, Y. Zhang, and Z. Du, “Cross-language Sentiment Classification Based on Support Vector Machine *,” pp. 507–513, 2015.
[5] Nurdin and A. Munthoha, “SISTEM PENDETEKSIAN KEMIRIPAN JUDUL SKRIPSI MENGGUNAKAN,” J. Nas. dan Teknol. Jar., vol. 2, pp. 90–97, 2017.
[6] O. R. Sulaeman, W. Gata, M. Wahyudi, R. Subandi, R. Setiyawan, and B. Pratama, “Information Retrieval System to Find Articles and Clauses in UUD 1945 Using Vector Space Model Method Information Retrieval System to Find Articles and Clauses in UUD 1945 Using Vector Space Model Method,” J. Phys. Conf. Ser., 2020.
[7] R. R. A. Siregar, F. A. Sinaga, R. Arianto, P. Studi, S. Teknik, and K. Kunci, “APLIKASI PENENTUAN DOSEN PENGUJI SKRIPSI MENGGUNAKAN METODE TF-IDF DAN VECTOR SPACE MODEL,” J. Comput. Sci. Inf. Syst., vol. 2, pp. 171–186, 2017.
[8] F. Wiranto, A. Maududie, and T. Dharmawan, “Time Frame Detection Based on Online News Documents Using Vector Space Model,” 2019 Int. Conf. Comput. Sci. Inf. Technol. Electr. Eng., vol. 1, no. 1, pp. 19–23, 2019.
[9] S. Arts, B. Cassiman, and J. C. Gomez, “Text matching to measure patent similarity,” Strateg. Manag. J., vol. 39, no. 1, pp. 62–84, 2018.
[10] M. Laburu, A. Perez, A. Casillas, I. Goenaga, and M. Oronoz, “Can i find information about rare diseases in some other language?,” Proc. - 2018 IEEE Int. Conf. Bioinforma. Biomed. BIBM 2018, pp. 2102–2108, 2019.
[11] P. A. Hummel, F. Jakel, S. Lange, and R. Mertelsmann, “Case-based Reasoning Reaseach and Development,” vol. 11156, pp. 264–280, 2018.
[12] M. H. Hoffmann, “TEXT MINING OF EXPERT KNOWLEDGE FOR THE CONSTRUCTION OF A GLOBAL HABITAT SPACE OF MICRANTHES AND SAXIFRAGA REVEALS MULTIPLE AVENUES OF ARCTIC BIOME ASSEMBLY,” vol. 180, no. 3, 2019.
[13] E. Da Costa, H. Tjandrasa, and S. Djanali, “Text mining for pest and disease identification on rice farming with interactive text messaging,” Int. J. Electr. Comput. Eng., vol. 8, no. 3, pp. 1671–1683, 2018.
[14] G. Sogancıoglu, H. Oztu, and A. Ozgu, “BIOSSES : a semantic sentence similarity estimation system for the biomedical domain,” no. March, 2018.
[15] M. Mustaqhfiri, Z. Abidin, and R. Kusumawati, “Peringkasan Teks Otomatis Berita Berbahasa Indonesia Menggunakan Metode Maximum Marginal Relevance,” Matics, no. March 2012, 2012.
[16] S. Jabri, A. DAHBI, and T. GADI, “Ranking of Text Documents using TF-IDF Weighting and Association Rules mining,” 2018.
[17] M. Deshpande and V. Rao, “Depression detection using emotion artificial intelligence,” Proc. Int. Conf. Intell. Sustain. Syst. ICISS 2017, no. Iciss, pp. 858–862, 2018.
[18] C. J. Rameshbhai and J. Paulose, “Opinion mining on newspaper headlines using SVM and NLP,” Int. J. Electr. Comput. Eng., vol. 9, no. 3, pp. 2152–2163, 2019
Published
2020-09-26
How to Cite
ABIDIN, Aa Zezen Zaenal; SUKMADINATA, Andi. SISTEM DETEKSI KERUSAKAN PADA SISTEM OPERASI MENGGUNAKAN METODE TF-IDF DAN COSINE SIMILARITY. JURNAL ILMIAH INFORMATIKA, [S.l.], v. 8, n. 02, p. 107-112, sep. 2020. ISSN 2615-1049. Available at: <http://ejournal.upbatam.ac.id/index.php/jif/article/view/1968>. Date accessed: 26 feb. 2021. doi: https://doi.org/10.33884/jif.v8i02.1968.