잠재적 차량 결함 탐지를 위한 비정형 고객불만 텍스트 데이터 분류
Classification of Unstructured Customer Complaint Text Data for Potential Vehicle Defect Detection
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This research proposes a novel approach to tackle the challenge of categorizing unstructured customer complaints in the automo- tive industry. The goal is to identify potential vehicle defects based on the findings of our algorithm, which can assist automakers in mitigating significant losses and reputational damage caused by mass claims. To achieve this goal, our model uses the Word2Vec method to analyze large volumes of unstructured customer complaint data from the National Highway Traffic Safety Administration (NHTSA). By developing a score dictionary for eight pre-selected criteria, our algorithm can efficiently categorize complaints and detect potential vehicle defects. By calculating the score of each complaint, our algorithm can identify patterns and correlations that can indicate potential defects in the vehicle. One of the key benefits of this approach is its ability to handle a large volume of unstructured data, which can be challenging for traditional methods. By using machine learning techniques, we can extract meaningful insights from customer complaints, which can help automakers prioritize and address potential defects before they become widespread issues. In conclusion, this research provides a promising approach to categorize unstructured customer complaints in the automotive industry and identify potential vehicle defects. By leveraging the power of machine learning, we can help automakers improve the quality of their products and enhance customer satisfaction. Further studies can build upon this approach to explore other potential applications and expand its scope to other industries.
Abstract
This research proposes a novel approach to tackle the challenge of categorizing unstructured customer complaints in the automo- tive industry. The goal is to identify potential vehicle defects based on the findings of our algorithm, which can assist automakers in mitigating significant losses and reputational damage caused by mass claims. To achieve this goal, our model uses the Word2Vec method to analyze large volumes of unstructured customer complaint data from the National Highway Traffic Safety Administration (NHTSA). By developing a score dictionary for eight pre-selected criteria, our algorithm can efficiently categorize complaints and detect potential vehicle defects. By calculating the score of each complaint, our algorithm can identify patterns and correlations that can indicate potential defects in the vehicle. One of the key benefits of this approach is its ability to handle a large volume of unstructured data, which can be challenging for traditional methods. By using machine learning techniques, we can extract meaningful insights from customer complaints, which can help automakers prioritize and address potential defects before they become widespread issues. In conclusion, this research provides a promising approach to categorize unstructured customer complaints in the automotive industry and identify potential vehicle defects. By leveraging the power of machine learning, we can help automakers improve the quality of their products and enhance customer satisfaction. Further studies can build upon this approach to explore other potential applications and expand its scope to other industries.
참고문헌 (17)
- Acocella, I., "The Focus Groups in Social Research : Advantages and Disadvantages", Quality & Quantity, 46, pp.1125~1136 (2012)
- "Amherst, Identification and validation of themes from vehicle owner complaints and fatality reports using text analysis - Shashank Kumar Mehrotra Graduate Research Assistant Human Performance Laboratory University of Massachusett", ~ (2019)
- Cornelia Kiefer, "A Hybrid information extraction ap-proach exploiting structured data within a text mining process" (2019), stuttgart
- Das, T. K., "Big Data Analytics : A Framework for Unstructured Data Analysis", International Journal of Engineering Technology, 5(1), pp.153~156 (2013)
- Eboli, M. G., "Detecting poten-tial vehicle concerns using natural language processing applied to automotive big data", General Motors United States of America (2019)
- Gantz, J., "The digital universe in 2020:Big data, bigger digital shadows, and biggest growth in the far east", IDC iView: IDC Anal, Future, 2007, pp.1~16 (2012)
- Consumer Complaints and Traffic Fatalities: Insights from the NHTSA Vehicle Owner’s Complaint Database, "Ghazizadeh, M.", Department of Industrial and Systems Engineering University of Wisconsin-Madison, ~ (2012)
- Joachims, T, "Learning to Classify Text Using Support Vector Machines" (2002)
- Kaveh Bastani, "Latent Dirichlet Allocation(LDA)for topic modeling of the CFPB consumer complaints" (2019), cincin-nati
- A study on the unstructured big data morpheme classification model using customized dictionary techni-ques, "Kim, S.J", ~ (2021)
- King, T., "80 Percent of Your Data Will Be Unstructured in Five Years", Data Management Solutions Review, 24 (2019)
- Partial Amendment to the Enforcement Regulations of the Automobile Management Act, "Ministry of Land, Infrastructure and Transport", ~ (2009)
- Morgan, D. L., "Focus groups", Annual Review of Sociology, 22(1), pp.129~152 (1996)
- Netzer, O., "Mine Your Own Business : Market-structure Survei-llance Through Text Mining", Marketing Science, 31(3), pp.521~543 (2012)
- Sobhan Sarkar, "Text-clustering based deep neural network for prediction of occupational acci-dent risk", IIT kharagpur (2019)
- Subasish Das, "vehicle consumer complaint reports lnvolv-ing severe incidents-Mining Large Contingency Tables", Texas, ~ (2018)
- Zhang, X, "Identifying Product Defects from User Complaints: A Probabilistic Defect Model", ~ (2016)