고객 감성 분석을 위한 학습 기반 토크나이저 비교 연구
Comparative Study of Tokenizer Based on Learning for Sentiment Analysis
0
조회
0
다운로드
6
인용
0
참고문헌
키워드
초록
Purpose: The purpose of this study is to compare and analyze the tokenizer in natural language processing for customer satisfaction in sentiment analysis. Methods: In this study, a supervised learning-based tokenizer Mecab-Ko and an unsupervised learning-based tokenizer SentencePiece were used for comparison. Three algorithms: Naïve Bayes, k-Nearest Neighbor, and Decision Tree were selected to compare the performance of each tokenizer. For performance comparison, three metrics: accuracy, precision, and recall were used in the study. Results: The results of this study are as follows; Through performance evaluation and verification, it was confirmed that SentencePiece shows better classification performance than Mecab-Ko. In order to confirm the robustness of the derived results, independent t-tests were conducted on the evaluation results for the two types of the tokenizer. As a result of the study, it was confirmed that the classification performance of the SentencePiece tokenizer was high in the k-Nearest Neighbor and Decision Tree algorithms. In addition, the Decision Tree showed slightly higher accuracy among the three classification algorithms. Conclusion: The SentencePiece tokenizer can be used to classify and interpret customer sentiment based on online reviews in Korean more accurately. In addition, it seems that it is possible to give a specific meaning to a short word or a jargon, which is often used by users when evaluating products but is not defined in advance.
Abstract
Purpose: The purpose of this study is to compare and analyze the tokenizer in natural language processing for customer satisfaction in sentiment analysis. Methods: In this study, a supervised learning-based tokenizer Mecab-Ko and an unsupervised learning-based tokenizer SentencePiece were used for comparison. Three algorithms: Naïve Bayes, k-Nearest Neighbor, and Decision Tree were selected to compare the performance of each tokenizer. For performance comparison, three metrics: accuracy, precision, and recall were used in the study. Results: The results of this study are as follows; Through performance evaluation and verification, it was confirmed that SentencePiece shows better classification performance than Mecab-Ko. In order to confirm the robustness of the derived results, independent t-tests were conducted on the evaluation results for the two types of the tokenizer. As a result of the study, it was confirmed that the classification performance of the SentencePiece tokenizer was high in the k-Nearest Neighbor and Decision Tree algorithms. In addition, the Decision Tree showed slightly higher accuracy among the three classification algorithms. Conclusion: The SentencePiece tokenizer can be used to classify and interpret customer sentiment based on online reviews in Korean more accurately. In addition, it seems that it is possible to give a specific meaning to a short word or a jargon, which is often used by users when evaluating products but is not defined in advance.
참고문헌 (24)
- Balbi, S., "Combining Different Evaluation Systems on Social Media for Measuring User Satisfaction", Information Processing & Management, 54(4), pp.674~685 (2018)
- Bataa, E., "An Investigation of Transfer Learning-based Sentiment Analysis in Japanese", arXiv Preprint arXiv:1905.09642, ~ (2019)
- Bérard, A., "Machine Translation of Restaurant Reviews : New Corpus for Domain Adaptation and Robustness", arXiv Preprint arXiv:1910.14589, 14589~ (2019)
- Collobert, R., "Natural Language Processing(almost)from Scratch", Journal of Machine Llearning Research, 12, pp.2493~2537 (2011)
- Decker, R., "Estimating Aggregate Consumer Preferences from Online Product Reviews", International Journal of Research in Marketing, 27(4), pp.293~307 (2010)
- Fang, X., "Sentiment Analysis Using Product Review Data", Journal of Big Data, 2(1), pp.5~ (2015)
- Gruen, T. W., "eWOM : The Impact of Customer-to-customer Online Know-how Exchange on Customer Value and Loyalty", Journal of Business Research, 59(4), pp.449~456 (2006)
- Henson, B., "Affective Consumer Requirements: A Case Study of Moisturizer Packaging", Concurrent Engineering, 14(3), pp.187~196 (2006)
- Jiang, S., "Cognitive Detection of Multiple Discrete Emotions from Chinese Oonline Reviews", 2016 IEEE First International Conference on Data Science in Cyberspace (DSC), pp.137~142 (2016)
- Kamiński, B., "A Framework for Sensitivity Analysis of Decision Trees", Central European Journal of Operations Research, 26(1), pp.135~159 (2018)
- 김주연, "커피전문점 서비스 요소가 고객의 감정 및 충성도에 미치는 영향", Culinary Science & Hospitality Research, 15(1), pp.271~286 (2009), (사)한국조리학회[DOI]
- Kudo, T., "Sentencepiece : A Simple and Language Independent Subword Tokenizer and Detokenizer for Neural Text Processing", arXiv Preprint arXiv:1808.06226, ~ (2018)
- Kuwano, S., "Subjective Impression of Copy Machine Noises: An Examination of Physical Metrics for the Evaluation of Sound quality", Proc. Inter-Noise 2009 (2009)
- 임좌상, "한국어 트위터의 감정 분류를 위한 기계학습의 실증적 비교", 멀티미디어학회논문지, 17(2), pp.232~239 (2014), 한국멀티미디어학회[DOI]
- Litvin, S. W., "Electronic Word-of-mouth in Hospitality and Tourism Management", Tourism Management, 29(3), pp.458~468 (2008)
- Liu, B., "Sentiment Analysis and Opinion Mining", Synthesis Lectures on Human Language Technologies, 5(1), pp.1~167 (2012)
- Liu, H., "Combining User Preferences and User Opinions for Accurate Recommendation", Electronic Commerce Research and Applications, 12(1), pp.14~23 (2013)
- Liu, Y., "Identifying Helpful Online Reviews: a Product Designer’s Perspective", Computer-Aided Design, 45(2), pp.180~194 (2013)
- Montefinese, M., "The Adaptation of the Affective Norms for English Words(ANEW)for Italian", Behavior Research Methods, 46(3), pp.887~903 (2014)
- Rose, S., "Online Customer Experience: A Review of the Bbusiness‐to‐consumer Oonline Purchase Context", International Journal of Management Reviews, 13(1), pp.24~39 (2011)
- Su, J., "Enhancing Aspect-Based Sentiment Analysis With Capsule Network", IEEE ACCESS, 8, pp.100551~100561 (2020)
- Taniguchi, Y., "Examining Language-agnostic Methods of Automatic Coding in the Community of Inquiry Framework", 16th International Conference on Cognition and Exploratory Learning in Digital Age IADIS Press, pp.19~26 (2019)
- Wang, H., "Latent Aspect Rating Analysis on Review Text Data: a Rating Regression Approach", Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp.783~792 (2010)
- Yang, L., "Sentiment Analysis for E-commerce Product Reviews in Chinese Based on Sentiment Lexicon and Deep Learning", IEEE Access, 8, pp.23522~23530 (2020)