Mining multi-brand characteristics from online reviews for competitive analysis: A brand joint model using latent Dirichlet allocation
作者：
Highlights：
• Online review analysis helps us understand users’ needs and attitudes.
• We propose BJ-LDA model to analyse online reviews for multi brands simultaneously.
• This model captures general aspects with users’ opinions about multi-brands.
• It also captures specific aspects with users’ opinions within individual brands.
• Based on model results, we can get a deeper understanding of brand competition.
摘要
•Online review analysis helps us understand users’ needs and attitudes.•We propose BJ-LDA model to analyse online reviews for multi brands simultaneously.•This model captures general aspects with users’ opinions about multi-brands.•It also captures specific aspects with users’ opinions within individual brands.•Based on model results, we can get a deeper understanding of brand competition.
论文关键词：Brand competitive analysis,Latent Dirichlet allocation,Sentiment analysis,Reviews mining
论文评审过程：Received 6 February 2021, Revised 8 March 2022, Accepted 16 March 2022, Available online 21 March 2022, Version of Record 24 March 2022.
论文官网地址：https://doi.org/10.1016/j.elerap.2022.101141
