{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T11:56:49Z","timestamp":1780401409401,"version":"3.54.1"},"reference-count":30,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T00:00:00Z","timestamp":1755993600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2652023060"],"award-info":[{"award-number":["2652023060"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Category A, China University of Geosciences Beijing Undergraduate Innovation and Entrepreneurship Training Program","award":["2652023060"],"award-info":[{"award-number":["2652023060"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJGI"],"abstract":"<jats:p>With the growing adoption of electric vehicles, optimizing the user experience of charging infrastructure has become critical. However, extracting actionable insights from the vast number of user reviews remains a significant challenge, impeding demand-driven operational planning for charging stations and degrading the user experience. This study leverages three pre-trained language models to perform sentiment classification and multi-level topic identification on 168,129 user reviews from Beijing, facilitating a comprehensive understanding of user feedback. The experimental results reveal significant task-model specialization: RoBERTa-WWM excels in sentiment analysis (accuracy = 0.917) and fine-grained topic identification (Micro-F1 = 0.844), making it ideal for deep semantic extraction. Conversely, ELECTRA, after sufficient training, demonstrates a strong aptitude for coarse-grained topic summarization, highlighting its strength in high-level semantic generalization. Notably, the models offer capabilities beyond simple classification, including autonomous label normalization and the extraction of valuable information from comments with low information density. Furthermore, integrating textual and spatial analyses revealed striking patterns. We identified an urban\u2013rural emotional gap\u2014suburban users are more satisfied despite fewer facilities\u2014and used geographically weighted regression (GWR) to quantify the spatial differences in the factors affecting user satisfaction in Beijing\u2019s districts. We identified three types of areas requiring differentiated strategies, as follows: the northwestern region is highly sensitive to equipment quality, the central urban area has a complex relationship between supporting facilities and satisfaction, and the emerging adoption area is more sensitive to accessibility and price factors. These findings offer a data-driven framework for charging infrastructure planning, enabling operators to base decisions on real-world user feedback and tailor solutions to specific local contexts.<\/jats:p>","DOI":"10.3390\/ijgi14090325","type":"journal-article","created":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:09:53Z","timestamp":1756080593000},"page":"325","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Enhancing Electric Vehicle Charging Infrastructure Planning with Pre-Trained Language Models and Spatial Analysis: Insights from Beijing User Reviews"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9081-0833","authenticated-orcid":false,"given":"Yanxin","family":"Hou","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, China University of Geosciences Beijing, Beijing 100083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peipei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, China University of Geosciences Beijing, Beijing 100083, China"},{"name":"Hebei Key Laboratory of Geospatial Digital Twin and Collaborative Optimization, China University of Geosciences Beijing, Beijing 100083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7777-1409","authenticated-orcid":false,"given":"Zhuozhuang","family":"Yao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, China University of Geosciences Beijing, Beijing 100083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8850-0912","authenticated-orcid":false,"given":"Xinqi","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, China University of Geosciences Beijing, Beijing 100083, China"},{"name":"Technology Innovation Center for Territory Spatial Big-Data, Ministry of Natural Resources of the People\u2019s Republic of China, Beijing 100036, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziying","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, China University of Geosciences Beijing, Beijing 100083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"111733","DOI":"10.1016\/j.rser.2021.111733","article-title":"The state of play in electric vehicle charging services\u2014A review of infrastructure provision, players, and policies","volume":"154","author":"LaMonaca","year":"2022","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/j.tranpol.2024.02.004","article-title":"Preferences for public electric vehicle charging infrastructure locations: A discrete choice analysis","volume":"149","author":"Bhat","year":"2024","journal-title":"Transp. Policy"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Li, S.G., Liu, F., Zhang, Y.Q., Zhu, B.Y., Zhu, H., and Yu, Z.X. (2022). Text Mining of User-Generated Content (UGC) for Business Applications in E-Commerce: A Systematic Review. Mathematics, 10.","DOI":"10.3390\/math10193554"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"23522","DOI":"10.1109\/ACCESS.2020.2969854","article-title":"Sentiment Analysis for E-Commerce Product Reviews in Chinese Based on Sentiment Lexicon and Deep Learning","volume":"8","author":"Yang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Kim, Y. (2014, January 25\u201329). Convolutional Neural Networks for Sentence Classification. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar.","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Alemayehu, F., Meshesha, M., and Abate, J. (2023). Amharic political sentiment analysis using deep learning approaches. Sci. Rep., 13.","DOI":"10.1038\/s41598-023-45137-9"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2098","DOI":"10.1016\/j.jksuci.2022.02.025","article-title":"Bidirectional convolutional recurrent neural network architecture with group-wise enhancement mechanism for text sentiment classification","volume":"34","author":"Onan","year":"2022","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"ref_8","unstructured":"Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019, January 2\u20137). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, MN, USA."},{"key":"ref_9","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., and Stoyanov, V. (2019). RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3504","DOI":"10.1109\/TASLP.2021.3124365","article-title":"Pre-Training with Whole Word Masking for Chinese BERT","volume":"29","author":"Cui","year":"2021","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_11","unstructured":"Clark, K., Luong, M.-T., Le, Q.V., and Manning, C.D. (2020). ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1109\/TAFFC.2020.2970399","article-title":"Issues and Challenges of Aspect-based Sentiment Analysis: A Comprehensive Survey","volume":"13","author":"Nazir","year":"2022","journal-title":"IEEE Trans. Affect. Comput."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"11019","DOI":"10.1109\/TKDE.2022.3230975","article-title":"A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges","volume":"35","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"6652","DOI":"10.1016\/j.jksuci.2021.08.030","article-title":"Arabic aspect based sentiment analysis using bidirectional GRU based models","volume":"34","author":"Abdelgwad","year":"2022","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Hu, B., and Ester, M. (2013, January 12\u201316). Spatial topic modeling in online social media for location recommendation. Proceedings of the 7th ACM Conference on Recommender Systems, Hong Kong, China.","DOI":"10.1145\/2507157.2507174"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Mao, H., Fan, Y., and Tong, M. (2024). Research on aspect-based sentiment analysis of movie reviews based on deep learning. J. Inf. Sci.","DOI":"10.1177\/01655515241292353"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"9984343","DOI":"10.1155\/2021\/9984343","article-title":"A Study on Selection Strategies for Battery Electric Vehicles Based on Sentiments, Analysis, and the MCDM Model","volume":"2021","author":"Ren","year":"2021","journal-title":"Math. Probl. Eng."},{"key":"ref_18","unstructured":"Chen, S., and Tu, C. (2024). Fine-Grained Sentiment Analysis of Electric Vehicle User Reviews: A Bidirectional LSTM Approach to Capturing Emotional Intensity in Chinese Text. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"425","DOI":"10.3390\/analytics3040023","article-title":"Electric Vehicle Sentiment Analysis Using Large Language Models","volume":"3","author":"Sharma","year":"2024","journal-title":"Analytics"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"152628","DOI":"10.1109\/ACCESS.2021.3127140","article-title":"Arabic Aspect-Based Sentiment Analysis: A Systematic Literature Review","volume":"9","author":"Obiedat","year":"2021","journal-title":"IEEE Access"},{"key":"ref_21","unstructured":"Li, F., Huang, M., Yang, Y., and Zhu, X. (2011, January 16\u201322). Learning to identify review spam. Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, Barcelona, Spain."},{"key":"ref_22","unstructured":"Huang, C., and He, G. (2024). Text Clustering as Classification with LLMs. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"e2305016120","DOI":"10.1073\/pnas.2305016120","article-title":"ChatGPT outperforms crowd workers for text-annotation tasks","volume":"120","author":"Gilardi","year":"2023","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Fonferko-Shadrach, B., Strafford, H., Jones, C., Khan, R.A., Brown, S., Edwards, J., Hawken, J., Shrimpton, L.E., White, C.P., and Powell, R. (2024). Annotation of epilepsy clinic letters for natural language processing. J. Biomed. Semant., 15.","DOI":"10.1186\/s13326-024-00316-z"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Ivanisenko, T.V., Demenkov, P.S., and Ivanisenko, V.A. (2024). An Accurate and Efficient Approach to Knowledge Extraction from Scientific Publications Using Structured Ontology Models, Graph Neural Networks, and Large Language Models. Int. J. Mol. Sci., 25.","DOI":"10.3390\/ijms252111811"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"e1044","DOI":"10.7717\/peerj-cs.1044","article-title":"Deep learning for aspect-based sentiment analysis: A review","volume":"8","author":"Zhu","year":"2022","journal-title":"PeerJ Comput. Sci."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"82924","DOI":"10.1109\/ACCESS.2023.3276320","article-title":"Multi-Tasking for Aspect-Based Sentiment Analysis via Constructing Auxiliary Self-Supervision ACOP Task","volume":"11","author":"Wu","year":"2023","journal-title":"IEEE Access"},{"key":"ref_28","unstructured":"Bucher, M.J.J., and Martini, M. (2024). Fine-tuned\u2019 small\u2019 LLMs (still) significantly outperform zero-shot generative AI models in text classification. arXiv."},{"key":"ref_29","unstructured":"Wang, Y., Qu, W., and Ye, X. (2024). Selecting between BERT and GPT for text classification in political science research. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Malvankar, K., Fallon, E., Connolly, P., and Flanagan, K. (2023, January 21\u201323). Performance optimization for transformer models on text classification tasks. Proceedings of the 2023 International Conference on Emerging Techniques in Computational Intelligence (ICETCI), Hyderabad, India.","DOI":"10.1109\/ICETCI58599.2023.10330958"}],"container-title":["ISPRS International Journal of Geo-Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2220-9964\/14\/9\/325\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:35:14Z","timestamp":1760034914000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2220-9964\/14\/9\/325"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,24]]},"references-count":30,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["ijgi14090325"],"URL":"https:\/\/doi.org\/10.3390\/ijgi14090325","relation":{},"ISSN":["2220-9964"],"issn-type":[{"value":"2220-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,24]]}}}