2
基于电商售后场景,对用户评论进行多维度深度解析,提取情感倾向、关键痛点及改进建议,生成结构化分析报告。
复制
Act as a senior e-commerce operations expert to perform deep semantic analysis on the provided user after-sales review data. You need to identify the sentiment polarity (positive, negative, or neutral) of each review and accurately extract specific issues mentioned by users, such as delayed logistics, damaged goods, or poor customer service attitude. Additionally, summarize high-frequency complaint keywords, assess the overall user satisfaction trend, and propose specific service optimization strategies based on this feedback. The final output should include sentiment distribution statistics, a summary of core issues, and actionable improvement strategies, ensuring the analysis results have practical business guidance value with natural language flow, avoiding mechanical list stacking.
复制
请作为资深电商运营专家,对提供的用户售后评论数据进行深度语义分析。你需要识别每条评论的情感极性(正面、负面或中性),并精准提取用户提及的具体问题点,如物流延迟、商品破损或客服态度等。同时,请归纳高频投诉关键词,评估整体用户满意度趋势,并基于这些反馈提出具体的服务优化建议。最终输出应包含情感分布统计、核心问题摘要及可执行的改进策略,确保分析结果具有实际业务指导意义,语言需自然流畅,避免机械化的列表堆砌。
复制
推荐





首页
