基于语义约束LDA的商品特征和情感词提取

随着网络购物的发展，Web上产生了大量的商品评论文本数据，其中蕴含着丰富的评价知识。如何从这些海量评论文本中有效提取商品特征和情感词，进而获取特征级别的情感倾向，是进行商品评论细粒度情感分析的关键。本文根据中文商品评论文本的特点，从句法分析、词义理解和语境相关等多角度获取词语间的语义关系，然后将其作为约束知识嵌入到主题模型，提出语义关系约束的主题模型SRC-LDA（semantic relation constrained LDA），用来实现语义指导下LDA的细粒度主题词提取。由于SRC-LDA改善了标准LDA对于主题词的语义理解和识别能力，从而提高了相同主题下主题词分配的关联度和不同主题下主题词分配的区分度，可以更多地发现细粒度特征词、情感词及其之间的语义关联性。通过实验表明，SRC-LDA对于细粒度特征和情感词的发现和提取具有较好的效果。

Extracting Product Aspects and User Opinions Based on Semantic Constrained LDA Model

With the development of online shopping,the Web has produced a large quantity of product reviews,which contains abundant evaluation knowledge about products.How to extract aspects and opinion words from the reviews,further obtain the sentiment polarity of the products at aspect level,is the key problems to solve in fine-grained sentiment analysis of product reviews.Firstly,considering the features of Chinese product reviews,the methods are designed to achieve the semantic relationships among words through the syntactic analysis,word meaning understanding and context relevance and then embed it as constrained knowledge into the topic model.Secondly,a semantic relation constrained topic model called SRC-LDA is proposed in this paper,which can guide the LDA to extract fine-grained topical words.Through the improvement of semantic comprehension and recognition ability of topical words in standard LDA,the proposed model can increase the words correlation under the same topic and the discrimination under the different topics,which can find more fine-grained aspect words,opinion words and the semantic associations of them.The experimental results show that the SRC-LDA is an effective approach for fine-grained aspects and opinion words extraction.