Article: Emotion-driven recommender system for low-carbon products: sentiment feedback and satisfaction evaluation from online reviews Journal: International Journal of Information and Communication Technology (IJICT) 2026 Vol.27 No.64 pp.1 - 22 Abstract: The aim of this research is to fully examine the consideration and emotional inclination of Chinese consumers towards low-carbon products and offer empirical evidence in order to raise the level of awareness of the population on low-carbon consumption. Towards this, 62,271 online reviews of common low-carbon products in JD.com which is a Chinese e-commerce were gathered. The reviews contained six types of consumer goods used every day: paper products and cleaning supplies, household goods, electronic appliances, clothing and accessories, home improvement and decoration, and beauty and personal care. SnowNLP natural language processing sentiment analysis component was used to determine the intensity of emotion of consumers on different low-carbon products. Moreover, most of the online reviews were analysed and latent topics were identified with the LDA topic model as part of establishing the impact of these latent topics on the positive and negative feelings of the consumers. Inderscience Publishers - linking academia, business and industry through research

Title: Emotion-driven recommender system for low-carbon products: sentiment feedback and satisfaction evaluation from online reviews

Authors: Dongyi Zhang; Shulan Yu

Addresses: College of Furnishings and Industrial Design, Nanjing Forestry University, Nanjing, 210037, China ' College of Furnishings and Industrial Design, Nanjing Forestry University, Nanjing, 210037, China

Abstract: The aim of this research is to fully examine the consideration and emotional inclination of Chinese consumers towards low-carbon products and offer empirical evidence in order to raise the level of awareness of the population on low-carbon consumption. Towards this, 62,271 online reviews of common low-carbon products in JD.com which is a Chinese e-commerce were gathered. The reviews contained six types of consumer goods used every day: paper products and cleaning supplies, household goods, electronic appliances, clothing and accessories, home improvement and decoration, and beauty and personal care. SnowNLP natural language processing sentiment analysis component was used to determine the intensity of emotion of consumers on different low-carbon products. Moreover, most of the online reviews were analysed and latent topics were identified with the LDA topic model as part of establishing the impact of these latent topics on the positive and negative feelings of the consumers.

Keywords: low-carbon products; consumer sentiment; online reviews; consumer satisfaction; topic modelling; ICT-based analytics; e-commerce.

DOI: 10.1504/IJICT.2026.154112

International Journal of Information and Communication Technology, 2026 Vol.27 No.64, pp.1 - 22

Received: 10 Dec 2025
Accepted: 30 Mar 2026
Published online: 12 Jun 2026 *

Title: Emotion-driven recommender system for low-carbon products: sentiment feedback and satisfaction evaluation from online reviews

Keep up-to-date