Sentiment analysis from Customer-generated online videos on product review using topic modeling and Multi-attention BLSTM

Sentiment analysis from Customer-generated online videos on product review using topic modeling and Multi-attention BLSTM
复制标题

使用主题建模和多注意力 BLSTM 对客户生成的产品评论在线视频进行情感分析

DOI:
10.1016/j.aei.2022.101588
复制
发表时间:
2022-04
影响因子:
8.8
通讯作者:
Xuening Chu
Xuening Chu
中科院分区:
工程技术1区
文献类型:
--
作者:
Zheng Wang;Peng Gao;Xuening Chu

文献摘要

参考文献

相似文献

随着包括Instagram、YouTube、TikTok等在内的社交网站和移动的应用的普及,由客户分享的在线视频呈现了他们对产品的想法和评论,每天发布的数量越来越多。这些包含客户之声(VOC)的在线视频对于产品设计师或经理捕捉客户情绪和了解客户偏好非常宝贵。为此,我们提出了一种新的方法来分析客户的情绪从在线视频上的产品评论。首先,潜在的Dirichlet分配(LDA)模型被应用于识别在线视频的数据预处理后的主题。然后,可以使用我们新设计的多注意双向LSTM(BLSTM(MA))识别视频中每个说话者的每个主题对应的情感极性,这可以更好地挖掘说话者对不同主题的情感之间的复杂关系。本文对于公司管理者和研究者更好地了解大量顾客对具体产品的意见具有很大的实用价值。为了说明该方法的应用并证明其有效性,最后分别在智能手机和几个已发表的数据集上开发了两个案例。
With the popularity of social websites and mobile applications including Instagram, YouTube, TikTok, etc., online videos shared by customers presenting their thoughts and reviews on products are posted daily in increasing numbers. Such online videos containing Voice of Customer (VOC) are precious for product designers or managers to capture customer sentiment and understand customer preference. For this purpose, we propose a novel method for analyzing customer sentiment from online videos on product review. Firstly, latent Dirichlet allocation (LDA) modeling is applied to identify the topics from the online videos after data preprocessing. Then sentiment polarity corresponding to each topic of each speaker in videos can be identified using our newly designed multi-attention bi-directional LSTM (BLSTM(MA)), which can better mine complex relationships among a speaker’s sentiments on different topics. This paper is of great practical value for company managers and researchers to better understand a large number of customer opinions on specific products. To explain the application of this method and prove its effectiveness, two cases respectively on smartphones and several published datasets are developed finally.
DOI: 10.1142/s0219877018500086
发表时间: 2018-02
影响因子: 1.8
作者:
F. Geyer;Jens Lehnen;C. Herstatt
通讯作者: F. Geyer;Jens Lehnen;C. Herstatt
DOI: --
发表时间: 2016-09
期刊: ArXiv
影响因子: --
作者:
Haohan Wang;Aaksha Meghawat;Louis-Philippe Morency;E. Xing
通讯作者: Haohan Wang;Aaksha Meghawat;Louis-Philippe Morency;E. Xing
DOI: 10.1016/j.aei.2021.101304
发表时间: 2021-08
期刊: Adv. Eng. Informatics
影响因子: --
作者:
Juram Kim;Chiehyeon Lim
通讯作者: Juram Kim;Chiehyeon Lim
DOI: 10.18653/v1/d15-1303
发表时间: 2015
期刊: --
影响因子: --
作者:
Soujanya Poria;E. Cambria;Alexander Gelbukh
通讯作者: Soujanya Poria;E. Cambria;Alexander Gelbukh
DOI: 10.1088/1742-6596/971/1/012053
发表时间: 2018-03
期刊: Journal of Physics: Conference Series
影响因子: --
作者:
P. Sari;A. Alamsyah;Sulistyo Wibowo
通讯作者: P. Sari;A. Alamsyah;Sulistyo Wibowo