Abstract
The vast and unstructured data on social media platforms offer insights into user-perceived quality, presenting a novel avenue for new energy vehicle companies to analyze product quality. In response, this study introduces a methodology that integrates dependency syntactic parsing with hierarchical clustering to derive multi-level insights on user-perceived quality. Initially, we employ dependency syntactic parsing and part-of-speech tagging to identify compound noun phrases within comments. These phrases serve as a specialized out-of-vocabulary library pertinent to the new energy vehicle sector, from which a selection of words is chosen as potential evaluation metrics. Subsequently, we utilize Word2Vec to develop word vectors from automotive forum corpora. Leveraging these word vectors and the identified evaluation metrics, a hierarchical clustering algorithm is then applied to establish a comprehensive three-level user-perceived quality indicator system. Experimental validation conducted on forum comment data from BYD's new energy vehicles confirms the reliability and effectiveness of the proposed methodology. The user-perceived quality extraction method delineated in this research aids automotive firms in pinpointing areas of user interest, thereby substantially enhancing user loyalty and satisfaction.
Original language | English |
---|---|
Pages (from-to) | 576-583 |
Number of pages | 8 |
Journal | Procedia Computer Science |
Volume | 242 |
DOIs | |
State | Published - 2024 |
Externally published | Yes |
Event | 11th International Conference on Information Technology and Quantitative Management, ITQM 2024 - Bucharest, Romania Duration: 23 Aug 2024 → 25 Aug 2024 |
Keywords
- attribute extraction
- automotive industry
- dependency parsing
- hierarchical clustering
- perceived quality