Research on Automobile Product User Experience based on Semantic Analysis

Hongjing He; Li Yang; Wei Shang

doi:10.62051/ijsspa.v4n1.21

Authors

Hongjing He
Li Yang
Wei Shang

DOI:

https://doi.org/10.62051/ijsspa.v4n1.21

Keywords:

User Experience, Word Segmentation, Word Vector, Word2Vec, Factor Analysis

Abstract

The advantages and disadvantages of automobile products are related to the fate of automobile enterprises, in which user experience is very important in the design of automobile products. At present, most of the research on the user experience of automotive products focuses on the analysis of user behavior information, and mining the user experience characteristics from online reviews is a new direction. The first is to determine the data source and preprocess the data source; The second is to use word segmentation technology, word vector technology and Word2Vec model to build the automobile product feature word database; The third is to use factor analysis method to screen out the most representative product feature words; The fourth is to use syntactic dependency to extract the views of user comments; The fifth is the user experience analysis based on the sentiment dictionary in the automobile industry. To a certain extent, the method proposed in this paper satisfies the user experience method to provide certain reference opinions for automotive product design.

Downloads

Download data is not yet available.

References

[1] Xie Xuemei, Wang Minghui. Research on User Experience of intelligent Human-Computer Interaction products based on Dependency syntax analysis. Digital Library Forum, 2024, 20 (06): 44-53.

[2] Zhan Beiling, Lu Jing. A review of research on emotion measurement and emotion Recognition in User Experience [J]. Packaging Engineering, 2024, 45 (12): 12-21. DOI:10.19554/j.cnki.1001-3563.2024.12.002.

[3] https://blog.csdn.net/qq_29831163/article/details/88908811

[4] Xiangguang Dai,Nian Zhang,Keke Zhang,Jiang Xiong. Weighted Nonnegative Matrix Factorization for Image Inpainting and Clustering[J]. International Journal of Computational Intelligence Systems,2020.

[5] Ding Yulian,Wang Fei,Lei Xiujuan,Liao Bo,Wu Fang-Xiang. Deep belief network-Based Matrix Factorization Model for MicroRNA-Disease Associations Prediction.[J]. Evolutionary bioinformatics online, 2020,16.

[6] Guangfu Chen,Chen Xu,Jingyi Wang,Jianwen Feng,Jiqiang Feng. Nonnegative matrix factorization for link prediction in directed complex networks using PageRank and asymmetric link clustering information[J]. Expert Systems With Applications, 2020,148.