Mining product innovation ideas from online reviews
作者：
Highlights：
• Extracting innovative ideas from online reviews is important for product development.
• We introduce a novel deep learning approach to identify innovative ideas of products from online customer reviews.
• The approach ensembles multiple word embeddings.
• Focal loss function is adopted to handle the class imbalance problem.
• Results show that our model outperforms the baselines.
摘要
•Extracting innovative ideas from online reviews is important for product development.•We introduce a novel deep learning approach to identify innovative ideas of products from online customer reviews.•The approach ensembles multiple word embeddings.•Focal loss function is adopted to handle the class imbalance problem.•Results show that our model outperforms the baselines.
论文关键词：Information extraction,Deep learning,Product innovation,Online review mining,Text classification,Word embedding
论文评审过程：Received 15 November 2019, Revised 10 September 2020, Accepted 11 September 2020, Available online 1 October 2020, Version of Record 1 October 2020.
论文官网地址：https://doi.org/10.1016/j.ipm.2020.102389
