LSTM 알고리즘을 활용한 전기 수요고객의 온라인 질문에 대한 토픽분류

다국어 초록 (Multilingual Abstract)

In response to questions or complaints posted by customers on the company"s homepage, the response time is an important measure of customer satisfaction. However, the time it takes for a customer to receive an answer includes a time for the article to be selected by the person in charge of the reply, which limits the shortening. In this study, we developed a model in which a machine, not a person, reads the article, classifies the topic, and delivers it to each person in charge of the article. The article posted on the KEPCO homepage used in this study is a short sentence consisting of an average of 49 words. Due to the scarcity of multi-frequency words, it was found that there is a limit in securing a certain level of topic modeling accuracy in unsupervised machine learning like LDA. To overcome this, we labeled topics and let the machine conduct supervised learning. Although there are limitations in improving accuracy because there are articles containing more than two topics in one article, the classification accuracy is secured up to 84% by using LSTM and Baysian Optimization. The result of this study suggests that topic classification is possible for short-term customer questions in specific fields such as the electric power industry. In addition, it is expected that a model will be developed that can provide optimal reference answers for newly received questions when the topic-labeled questions and answers are fully accumulated.

목차 (Table of Contents)

• Abstract
• 1. 서론
• 2. 본론
• 3. 결론
• References

참고문헌 (Reference)

1 강형석, "한국어 단어 임베딩을 위한 Word2vec 모델의 최적화" 한국디지털콘텐츠학회 20 (20): 825-833, 2019

2 나상태, "토픽 모델링을 이용한 시뮬레이션 연구 동향 분석" 한국시뮬레이션학회 25 (25): 107-116, 2016

3 박찬혁, "텍스트 마이닝을 이용한 메이커 운동의 트렌드 분석" 한국콘텐츠학회 18 (18): 468-488, 2018

4 박서현, "최적의 luminescence 신호 분석을 위한유전자 전달 방법의 비교연구" 한국산학기술학회 17 (17): 640-647, 2016

5 황수영, "여행·호텔·항공·외식업의 e-CRM 활동에 관한 탐색적 연구" 한국관광학회 32 (32): 383-403, 2008

6 송애린, "WV-BTM: SNS 단문의 주제 분석을 위한 토픽 모델 정확도 개선 기법" 한국디지털콘텐츠학회 19 (19): 51-58, 2018

7 S. L. Pan, "Using e-CRM for a unified view of the customer" 46 (46): 95-99, 2003

8 Kotorov, P. Radoslav, "Ubiquitous organization : organizational design for e-CRM" 3 (3): 218-232, 2002

9 C. Li, "Topic modeling for short texts with auxiliary word embeddings" 165-174, 2016

10 Ashlee Vance, "This man is the godfather the AI Community Wants to Forget"

11 Jesse Davis, "The relationship between Precision-Recall and ROC curves" 233-240, 2006

12 J. L. Boyd-graber, "Syntactic Topic Models" 185-192, 2009

13 C. Bull, "Strategic issues in customer relationship management(CRM)implementation" 9 (9): 592-602, 2003

14 X. Quan, "Short and Sparse Text Topic Modeling via Self-Aggregation" 2015

15 T. Yun, "Malware Classification based on LSTM" 12 : 772-774, 2016

16 Hochreiter, Sepp, "Long short-term memory" 9 (9): 1735-1780, 1997

17 Sepp Hochreiter, "LSTM can solve hard long time lag problems" 473-479, 1997

18 M. Claesen, "Hyperparameter search in machine learning"

19 Aurelien, "Hands-On Machine Learning with Scikit-Learn &TensorFlow" O’REILLY 409-411, 2018

20 T. Mikolov, "Efficient Estimation of Word Representations in Vector Space"

21 T. Mikolov, "Distributed Representations of Words and Phrases and their Compositionality" 3111-3119, 2013

22 J. Grus, "Data science from scratch: first principles with Python" O'Reilly Media 239-240, 2019

23 H. Lee, "Analysis of reserch trends in technology management using topic modeling" 4 : 5208-5229, 2016

24 C. Voigt, "An empirically informed taxonomy for the Maker Movement" Springer, Cham 189-204, 2016

25 Y. Cho, "An Analysis of Online Customer Complaints : Implications for Web Complaint Management" IEEE 2308-2317, 2002

26 X. Yan, "A biterm topic model for short texts" 1445-1456, 2013