Xiaohongshu_data

This dataset contains UGC-related data collected from Xiaohongshu app. We select the UGC related to product recommendations, and distinguish product types into search products and experience products (i.e., taking skincare products and cosmetics as experience products; meanwhile, mobile phones, computers and digital cameras as search products). After data preprocessing, we obtained a total of 16,974 records, including content information of UGC posts and personal information of their creators.
All text fields have been datalized, some dummy variables are encoded (i.e., ProductType is encoded 0 for search products and 1 for experience products; Media is encoded 0 for photo-text format and 1 for video-text format; Cooperation is encoded 0 for organic post,1 for sponsored post).

本数据集汇集了源自小红书应用的UGC（用户生成内容）相关数据。经过精心筛选，我们选取了与产品推荐相关的UGC，并将产品类型区分为搜索产品和体验产品（例如，将护肤品和化妆品归类为体验产品；而将手机、电脑和数码相机归类为搜索产品）。经过数据预处理，我们共获得16,974条记录，包括UGC帖子的内容信息和创作者的个人资料。所有文本字段均已数据化，部分虚拟变量已进行编码（例如，产品类型以0编码搜索产品，以1编码体验产品；媒体类型以0编码图片-文本格式，以1编码视频-文本格式；合作类型以0编码原创帖子，以1编码赞助帖子）。