Enriched LDA (ELDA): Combination of latent Dirichlet allocation with word co-occurrence analysis for aspect extraction

作者：

Highlights：

• Method to extract aspects by incorporating domain knowledge into the LDA model.

• The knowledge is automatically generated based on co-occurrence relations.

• Knowledge validation is used to prevent incorrect and general knowledge.

• The method is language independent, allowing it to be applied to all languages.

摘要

•Method to extract aspects by incorporating domain knowledge into the LDA model.•The knowledge is automatically generated based on co-occurrence relations.•Knowledge validation is used to prevent incorrect and general knowledge.•The method is language independent, allowing it to be applied to all languages.

论文关键词：Aspect extraction,Topic modeling,Sentiment analysis,Latent Dirichlet Allocation (LDA),Co-occurrence relations

论文评审过程：Received 6 October 2016, Revised 23 February 2017, Accepted 24 February 2017, Available online 27 February 2017, Version of Record 18 March 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.02.038