Determination of Implicit Aspects with Rule Based Knowledge Extraction in Indonesian Reviews
Abstract
Determination of implicit aspects is one of the important things in opinion sentences. This study proposes a new approach for developing rule-based knowledge by forming a relation between opinion words with aspect categories. The relationship is obtained from the combination of rules, based on Opinion Word Similarity (OWS). Evaluation for rule-based knowledge extraction is in the form of threshold values of frequency and confidence to produce the best precision, recall, and f-measure values. The knowledge extraction consists of two phases: training phase and testing phase. The training phase is described as the process to extract rule-based knowledge. The testing phase is described as the process to obtain the implicit aspects of opinion sentences by referring to rule-based knowledge. To extract rule-based knowledge on user reviews, it is necessary to identify opinion sentences with explicit aspects and get pairs of aspects and words of opinion with rules generated from regular expressions. The evaluation result of rule-based knowledge with confidence using OWS showed better results compared to rule-based knowledge without using OWS. By using OWS, precision value increased by 0.25%, recall value increased by 1.15%, and precision value increased by 0.83%.
References
N. Akhtar, N. Zubair, A. Kumar, dan T. Ahmad, “Aspect based Sentiment Oriented Summarization of Hotel Reviews,” Procedia Comput. Sci., Vol. 115, hal. 563–571, 2017.
Y. Setiowati dan F. Setyorini, “Service Extraction and Sentiment Analysis to Indicate Hotel Service Quality in Yogyakarta based on User Opinion,” International Seminar on Research of Information Technology and Intelligent Systems, 2018, hal. 427–432.
D. Ekawati dan M.L. Khodra, “Aspect-based Sentiment Analysis for Indonesian Restaurant Reviews,” Proc. - 2017 Int. Conf. Adv. Informatics Concepts, Theory Appl. ICAICTA 2017, 2017, hal. 1-6.
L. Zhang, B. Liu, S.H. Lim, dan E. O’Brien-Strain, “Extracting and Ranking Product Features in Opinion Documents,” The 23rd International Conference on Computational Linguistics: Posters, 2009, hal. 1462–1470.
D.H. Sasmita, A.F. Wicaksono, S. Louvan, dan M. Adriani, “Unsupervised Aspect-based Sentiment Analysis on Indonesian Restaurant Reviews,” Proc. 2017 Int. Conf. Asian Lang. Process. IALP 2017, 2017, hal. 383–386.
S. Gojali dan M.L. Khodra, “Aspect Based Sentiment Analysis for Review Rating Prediction,” Int. Conf. Adv. Informatics Concepts, Theory Appl. ICAICTA 2016, 2016, hal. 1-6.
Y. Kang dan L. Zhou, “RubE: Rule-based Methods for Extracting Product Features from Online Consumer Reviews,” Inf. Manag., Vol. 54, No. 2, hal. 166–176, 2017.
E. Marrese-Taylor, J.D. Velásquez, dan F. Bravo-Marquez, “A Novel Deterministic Approach for Aspect-based Opinion Mining in Tourism Products Reviews,” Expert Syst. Appl., Vol. 41, No. 17, hal. 7764–7775, 2017.
T.A. Rana dan Y.N. Cheah, “A Two-fold Rule-based Model for Aspect Extraction,” Expert Syst. Appl., Vol. 89, hal. 273–285, 2017.
F. Lazhar dan T.G. Yamina, “Mining Explicit and Implicit Opinions from Reviews,” Int. J. Data Mining, Model. Manag., Vol. 8, No. 1, hal.
K. Schouten dan F. Frasincar, “Implicit Feature Extraction for Sentiment Analysis in Consumer Reviews,” Int. Conf. on Appl. of Natural Language to Data Bases/Information Systems, 2014, hal. 228–231.
K. Schouten., F. Frasincar, dan Erasmus, “Finding Implicit Features in Consumer Reviews for Sentiment Analysis,” Int. Conf. Web Eng. ICWE 2014 Web Eng., 2014, hal. 130–144.
Z. Hai, K. Chang, dan J.J. Kim, “Implicit Feature Identification via Cooccurrence Association Rule Mining,” in Int. Conf. on Intelligent Text Processing and Computational Linguistics, 2011, hal. 393–404.
P. Prameswari, I. Surjandari, dan E. Laoh, “Opinion Mining from Online Reviews in Bali Tourist Area,” Proc. - 2017 3rd Int. Conf. Sci. Inf. Technol. Theory Appl. IT Educ. Ind. Soc. Big Data Era, ICSITech 2017, 2017, hal. 226–230.
© Jurnal Nasional Teknik Elektro dan Teknologi Informasi, under the terms of the Creative Commons Attribution-ShareAlike 4.0 International License.
1.png)
