用微调的Sentence-BERT提升电商评论主题挖掘精度
Topic mining based on fine-tuning Sentence-BERT and LDA
- 微调Sentence-BERT提取语义更丰富的词向量
- 主题一致性比其他模型高0.5，提升提取准确率
- 适合需要精准分析商品多维度评价的用户
随着社会发展，消费者在购物时愈发关注商品细粒度属性。本研究对Sentence-BERT词嵌入模型和LDA模型进行联合微调，从电商平台在线评论中挖掘商品主题特征，帮助消费者了解商品各方面的具体表现。首先，在电商评论领域微调Sentence-BERT，将评论文本转化为富含语义信息的词向量集合；其次，将向量化后的词集输入LDA模型进行主题特征提取；最后，基于主题下的关键词分析聚焦产品关键功能。实验结果表明，该模型的主题一致性比其他词嵌入模型与LDA组合方式高出0.5，显著提升了主题提取的准确性。
原文摘要 · Abstract (English)
Research background: With the continuous development of society, consumers pay more attention to the key information of product fine-grained attributes when shopping. Research purposes: This study will fine tune the Sentence-BERT word embedding model and LDA model, mine the subject characteristics in online reviews of goods, and show consumers the details of various aspects of goods. Research methods: First, the Sentence-BERT model was fine tuned in the field of e-commerce online reviews, and the online review text was converted into a word vector set with richer semantic information; Secondly, the vectorized word set is input into the LDA model for topic feature extraction; Finally, focus on the key functions of the product through keyword analysis under the theme. Results: This study compared this model with other word embedding models and LDA models, and compared it with common topic extraction methods. The theme consistency of this model is 0.5 higher than that of other models, which improves the accuracy of theme extraction
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。