Algoritma Ekstraksi Informasi Berbasis Aturan

  • Agny Ismaya Badan Pemeriksa Keuangan RI Perwakilan Provinsi NTB
Keywords: LHP LKPD, ekstraksi informasi, klasifikasi, POS Tagging, rule-based classification

Abstract

The information in in the audit report of local government financial statement (LHP LKPD) was not managed digitally. The information in LHP from 33 provinces has just accumulate in a place without next process to take its main information. The absence of information searching application inhibit the learning process of the existing reports in advance. Therefore, an application can extract information from a set of LHP documents are needed to get main information, called criteria, consequence, cause, response, and audit advice.
This research creates a tool to extract the information in the audit report of local government financial statement (LHP LKPD). Information extraction method that used in this research is rule-based classification and pre-processing method that used is POS Tagging. The objective of information extraction in this research finds some sections in audit finding (Temuan Pemeriksaan-TP) that are criteria, consequence, cause, response, and audit advice.
The accuracy of training and test data are 98,27% and 89,77%. Decrease accuracy caused by usage of pdf2text that do not give a convertible identical between the input and output data, and usage of wordmatch method for classification.

References

Chandrawati, T. 2008. Pengembangan Part of Speech Tagger untuk Bahasa Indoensia Berdasarkan Metode Conditional Random Fields dan Transformation Based Learning. Universitas Indonesia.

Wicaksono, A. F., and A. Purwarianti. 2010. HMM Based Part-of-Speech Tagger for Bahasa Indonesia. Institut Teknologi Bandung.

Jiang, J. 2012. Information Extraction from Text. In Mining Text Data, edited by C. C. Aggarwal and C. Zhai: Springer, 11-41.

Feldman, R., and J. Sanger. 2006. The Text Mining Handbook, Advances Approaches in Analyzing Unstructured Data. Cambridge: Cambridge University Press.

Firdaniza, N. Gusriani, and Akmal. Hidden Markov Model. Bandung: Universitas Padjadjaran.

Palanisamy, S. K. 2006. Association Rule Based Classification, COmputer Science, Worcester Polytechnic Institute.

Chaudhary, U. K., I. Papapanagiotou, and M. Devetsikiotis. Flow Classification Using Clustering and Association Rule Mining. North Carolina State University.

How to Cite
Agny Ismaya. (1). Algoritma Ekstraksi Informasi Berbasis Aturan. Jurnal Nasional Teknik Elektro Dan Teknologi Informasi, 3(4), 242-247. Retrieved from https://dev.journal.ugm.ac.id/v3/JNTETI/article/view/3042
Section
Articles