基于多维相似度和情感词扩充的相同产品特征识别

Identification of the same product feature based on multi-dimension similarity and sentiment word expansion

针对现有相同产品特征识别方法受限于词典覆盖率或语料规模的不足,提出一种基于多维相似度和情感词扩充的识别方法。通过双向长短时记忆条件随机场(bi-directional long short-term memory and conditional random field, Bi-LSTM-CRF)模型抽取产品特征的扩充情感词,综合特征词的语素相似度、同义词林相似度和TF-IDF(term frequency-inverse document frequency)余弦相似度,采用K-medoids聚类算法,识别相同的产品特征。试验结果表明,在手机和笔记本数据集上,该方法的最大调整兰德指数分别达到0.579和0.595 9,而最小熵值分别达到0.782 6和0.745 7,均优于结合语素的调整Jaccard相似度、Word2Vec相似度和基于二分K-means的Word2Vec相似度三种基线试验方法。

Because the existing methods for identifying the same product features were limited by the lack of dictionary coverage or corpus size, an identification method was proposed based on multidimensional similarity and sentiment word expansion. Extracting emotional words of product features through bi-directional long short-term memory and conditional random field(Bi-LSTM-CRF), combining the morpheme similarity, Cilin similarity and term frequency-inverse document frequency(TF-IDF) cosine similarity of product feature words, the same product features were identified by K-medoids clustering algorithm. The experimental results showed that, on mobile and notebook datasets, the maximum adjusted rand index(ARI) reached 0.579 and 0.595 9 respectively, while the minimum entropy reached 0.782 6 and 0.745 7. The proposed method was superior to the adjusted Jaccard similarity combined morpheme, Word2 Vec similarity and Word2 Vec similarity based on bisecting K-means.