Performance attributes of new energy vehicles.

This dataset proposes a new energy vehicle procurement decision-making framework that integrates data mining and social network group decision-making in an intuitive fuzzy environment. This dataset proposes a new energy vehicle procurement decision-making framework that integrates data mining and social network group decision-making in an intuitive fuzzy environment. These data were crawled through the API provided by the Sina Weibo Open Platform (https://weibo.com). The crawling time range was from December 1 to 31, 2024, and a total of 87,673 online blog posts about new energy vehicle performance were obtained, aiming to gain a preliminary understanding of the popular evaluation attributes on social media as a reference for NEVs performance evaluation. To ensure the standardization and high quality of the text content, we performed strict data preprocessing on the original text. Specific measures include removing URL links, special symbols, and redundant spaces. In order to avoid the interference of high-frequency meaningless words on the results, we used the stop word list of CNStopwords for filtering. After the above preprocessing, we initially extracted the top ten high-frequency performance attribute feature words, which directly reflect the main concerns of social media users on NEVs.

本数据集提出了一种在直觉模糊环境下融合数据挖掘与社交网络群体决策的新能源汽车采购决策新框架。本数据集提出了一种在直觉模糊环境下融合数据挖掘与社交网络群体决策的新能源汽车采购决策新框架。本数据集所用数据通过新浪微博开放平台（Sina Weibo Open Platform）提供的API接口爬取获取，爬取时间范围为2024年12月1日至31日，共采集到87673条关于新能源汽车（New Energy Vehicles, NEVs）性能的网络博文，旨在初步掌握社交媒体上的热门评价属性，为新能源汽车性能评价提供参考依据。为保障文本内容的规范性与高质量，我们对原始文本开展了严格的数据预处理工作，具体措施包括移除URL链接、特殊符号与冗余空格；为避免高频无意义词汇对分析结果造成干扰，我们采用CNStopwords停用词表进行过滤。经上述预处理步骤后，我们初步提取出前十大高频性能属性特征词，这些特征词直接反映了社交媒体用户对新能源汽车的主要关注点。