【目的】應用細粒度情感分析方法提取產品屬性及情感,進而將屬性詞聚類到屬性面,分析用戶在產品屬性面的情感。【方法】通過CRF抽取產品屬性詞,利用基于注意力機制的長短期記憶網絡做屬性情感分析,最后基于Word2Vec將屬性詞聚集為屬性面,并分析電商平臺產品屬性面的情感。【結果】CRF抽取屬性詞的F1值為0.76,ATAE-LSTM屬性情感分析的F1值為0.78。【局限】只抽取顯式屬性詞,對隱式屬性詞抽取效果較差;數據集偏小。【結論】通過對屬性詞的抽取、情感分析以及屬性面聚類,可較好地解釋用戶對產品的屬性偏好。

[Objective] This paper tries to extract product attributes, aiming to cluster these words and analyze user’s sentiments. [Methods] Firstly, we identified the attributes of products with CRF technique. Then, we analyzed the sentiment of extracted terms with attention-based LSTM. Finally, we clustered these terms into appropriate categories with the help of Word2 Vec and conducted fine-grained sentiment analysis of the products.[Results] The F1 values of term extraction and sentiment analysis were 0. 76 and 0. 78. [Limitations] We only retrieved explicit terms for this study and the sample size needs to be expanded. [Conclusions] The proposed method could effectively explore user’s preference in products.