Sentiment analysis of online reviews of energy-saving products based on transfer learning and LBBA model

Jingwen Na; Ruyin Long; Hong Chen; Wanqi Ma; Han Huang; Meifen Wu; Shuhan Yang

doi:10.1016/j.jenvman.2024.121083

Sentiment analysis of online reviews of energy-saving products based on transfer learning and LBBA model

J Environ Manage. 2024 May 12:360:121083. doi: 10.1016/j.jenvman.2024.121083. Online ahead of print.

Authors

Jingwen Na¹, Ruyin Long², Hong Chen³, Wanqi Ma¹, Han Huang⁴, Meifen Wu⁴, Shuhan Yang⁴

Affiliations

¹ School of Business, Jiangnan University, Wuxi, 214122, China; The Institute for National Security and Green Development, Jiangnan University, Wuxi, 214122, China.
² School of Business, Jiangnan University, Wuxi, 214122, China; The Institute for National Security and Green Development, Jiangnan University, Wuxi, 214122, China. Electronic address: longruyin@163.com.
³ School of Business, Jiangnan University, Wuxi, 214122, China; The Institute for National Security and Green Development, Jiangnan University, Wuxi, 214122, China. Electronic address: hongchenxz@163.com.
⁴ The Institute for National Security and Green Development, Jiangnan University, Wuxi, 214122, China; School of Economics and Management, China University of Mining and Technology, Xuzhou, 221116, China.

PMID: 38739994
DOI: 10.1016/j.jenvman.2024.121083

Abstract

With the exacerbation of global climate change and the growing environmental awareness among the general public, the concept of green consumption has gained significant attention across various sectors of society. As a representative example of green consumer products, energy-saving products play a crucial role in the timely realization of dual carbon goals. However, an analysis of online comments regarding energy-saving products reveals that the majority of these products still exhibit shortcomings in terms of efficacy, noise level, cost-effectiveness, and particularly, energy-saving appliances. This study focuses on the user-generated online comments data from the Taobao e-commerce platform for Grade 1 energy-saving refrigerators. By employing text mining techniques, the study aims to extract the essential information and sentiments expressed in the comments, in order to explore the consumption characteristics of Grade 1 energy-saving refrigerators. Moreover, the LBBA (LDA-Bert-BiLSTM-Attention) model is utilized to investigate the consumer topics of interest and emotional features. Initially, the LDA model is adopted to identify the attributes and weights of consumer concerns. Subsequently, the Bert model is pre-trained with the online comment data, and combined with the BiLSTM algorithm and Attention mechanism to predict sentiment categories. Finally, a transfer learning approach is utilized to determine the sentiment inclination of user-generated online comments and to identify the primary driving factors behind each sentiment category. This research employs sentiment analysis on online comments data regarding energy-saving products to uncover consumer sentiment attributes and emotional characteristics. It provides decision-makers with a comprehensive and systematic understanding of public consumption intentions, offering decision support for the efficient operation and management of the energy-saving product market.

Keywords: Bert-BiLSTM-Attention model; Energy-saving products; LDA model; Sentiment analysis; Transfer learning.