A Natural Language Processing and deep learning based model for automated vehicle diagnostics using free-text customer service reports
Initial fault detection and diagnostics are imperative measures to improve the efficiency, safety, and stability of vehicle operation. In recent years, numerous studies have investigated data-driven approaches to improve the vehicle diagnostics process using available vehicle data. Moreover, data-dr...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-12-01
|
| Series: | Machine Learning with Applications |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666827022000998 |
| _version_ | 1797980906162487296 |
|---|---|
| author | Ali Khodadadi Soroush Ghandiparsi Chen-Nee Chuah |
| author_facet | Ali Khodadadi Soroush Ghandiparsi Chen-Nee Chuah |
| author_sort | Ali Khodadadi |
| collection | DOAJ |
| description | Initial fault detection and diagnostics are imperative measures to improve the efficiency, safety, and stability of vehicle operation. In recent years, numerous studies have investigated data-driven approaches to improve the vehicle diagnostics process using available vehicle data. Moreover, data-driven methods are employed to enhance customer-service agent interactions. In this study, we demonstrate a machine learning pipeline to improve automated vehicle diagnostics. First, Natural Language Processing (NLP) is used to automate the extraction of crucial information from free-text failure reports (generated during customers’ calls to the service department). Then, deep learning algorithms are employed to validate service requests and filter vague or misleading claims. Ultimately, different classification algorithms are implemented to classify service requests so that valid service requests can be directed to the relevant service department. The proposed model – Bidirectional Long Short Term Memory (BiLSTM) along with Convolution Neural Network (CNN) – shows more than 18% accuracy improvement in validating service requests compared to technicians’ capabilities. In addition, using domain-based NLP techniques at preprocessing and feature extraction stages along with CNN-BiLSTM based request validation enhanced the accuracy (>25%), sensitivity (>39%), specificity (>11%), and precision (>11%) of Gradient Tree Boosting (GTB) service classification model. The Receiver Operating Characteristic Area Under the Curve (ROC-AUC) reached 0.82. |
| first_indexed | 2024-04-11T06:02:09Z |
| format | Article |
| id | doaj.art-96319186f6b94bbe951489cf717499b2 |
| institution | Directory Open Access Journal |
| issn | 2666-8270 |
| language | English |
| last_indexed | 2024-04-11T06:02:09Z |
| publishDate | 2022-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Machine Learning with Applications |
| spelling | doaj.art-96319186f6b94bbe951489cf717499b22022-12-22T04:41:39ZengElsevierMachine Learning with Applications2666-82702022-12-0110100424A Natural Language Processing and deep learning based model for automated vehicle diagnostics using free-text customer service reportsAli Khodadadi0Soroush Ghandiparsi1Chen-Nee Chuah2Corresponding author.; 545 Bainer Hall Dr, Davis, 95616, CA, United States of America545 Bainer Hall Dr, Davis, 95616, CA, United States of America545 Bainer Hall Dr, Davis, 95616, CA, United States of AmericaInitial fault detection and diagnostics are imperative measures to improve the efficiency, safety, and stability of vehicle operation. In recent years, numerous studies have investigated data-driven approaches to improve the vehicle diagnostics process using available vehicle data. Moreover, data-driven methods are employed to enhance customer-service agent interactions. In this study, we demonstrate a machine learning pipeline to improve automated vehicle diagnostics. First, Natural Language Processing (NLP) is used to automate the extraction of crucial information from free-text failure reports (generated during customers’ calls to the service department). Then, deep learning algorithms are employed to validate service requests and filter vague or misleading claims. Ultimately, different classification algorithms are implemented to classify service requests so that valid service requests can be directed to the relevant service department. The proposed model – Bidirectional Long Short Term Memory (BiLSTM) along with Convolution Neural Network (CNN) – shows more than 18% accuracy improvement in validating service requests compared to technicians’ capabilities. In addition, using domain-based NLP techniques at preprocessing and feature extraction stages along with CNN-BiLSTM based request validation enhanced the accuracy (>25%), sensitivity (>39%), specificity (>11%), and precision (>11%) of Gradient Tree Boosting (GTB) service classification model. The Receiver Operating Characteristic Area Under the Curve (ROC-AUC) reached 0.82.http://www.sciencedirect.com/science/article/pii/S2666827022000998Customer serviceNLPCNNBiLSTMClaim validationClassification |
| spellingShingle | Ali Khodadadi Soroush Ghandiparsi Chen-Nee Chuah A Natural Language Processing and deep learning based model for automated vehicle diagnostics using free-text customer service reports Machine Learning with Applications Customer service NLP CNN BiLSTM Claim validation Classification |
| title | A Natural Language Processing and deep learning based model for automated vehicle diagnostics using free-text customer service reports |
| title_full | A Natural Language Processing and deep learning based model for automated vehicle diagnostics using free-text customer service reports |
| title_fullStr | A Natural Language Processing and deep learning based model for automated vehicle diagnostics using free-text customer service reports |
| title_full_unstemmed | A Natural Language Processing and deep learning based model for automated vehicle diagnostics using free-text customer service reports |
| title_short | A Natural Language Processing and deep learning based model for automated vehicle diagnostics using free-text customer service reports |
| title_sort | natural language processing and deep learning based model for automated vehicle diagnostics using free text customer service reports |
| topic | Customer service NLP CNN BiLSTM Claim validation Classification |
| url | http://www.sciencedirect.com/science/article/pii/S2666827022000998 |
| work_keys_str_mv | AT alikhodadadi anaturallanguageprocessinganddeeplearningbasedmodelforautomatedvehiclediagnosticsusingfreetextcustomerservicereports AT soroushghandiparsi anaturallanguageprocessinganddeeplearningbasedmodelforautomatedvehiclediagnosticsusingfreetextcustomerservicereports AT chenneechuah anaturallanguageprocessinganddeeplearningbasedmodelforautomatedvehiclediagnosticsusingfreetextcustomerservicereports AT alikhodadadi naturallanguageprocessinganddeeplearningbasedmodelforautomatedvehiclediagnosticsusingfreetextcustomerservicereports AT soroushghandiparsi naturallanguageprocessinganddeeplearningbasedmodelforautomatedvehiclediagnosticsusingfreetextcustomerservicereports AT chenneechuah naturallanguageprocessinganddeeplearningbasedmodelforautomatedvehiclediagnosticsusingfreetextcustomerservicereports |