Sentimental Analysis of Online Reviews of Egg Consumption Based on DSLML

被引：0

作者：

Bao Q. ^{[1
]}

Li J. ^{[1
]}

Shi S. ^{[1
]}

Dai Y. ^{[1
]}

Liu X. ^{[1
]}

机构：

[1] College of Information and Electric Engineering, China Agricultural University, Beijing

来源：

Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery | 2021年 / 52卷

关键词：

Domain sentimental lexicon; Egg; LDA theme model; Online reviews; Sentiment analysis; Sentimental classification of tendency;

D O I：

10.6041/j.issn.1000-1298.2021.S0.063

中图分类号：

学科分类号：

摘要：

With the rapid development of information technology, packaging and logistics technology, the range and scale of E-commerce products, including agricultural products, are getting larger and larger. At the same time, the online shopping review data has grown exponentially.The online reviews has become a hotspot. Taking JD's E-commerce platform as an example, the online reviews were mined out and the sentimental tendency of consumers about eggs consumption was analyzed deeply. The main research contents included proposing a domain sentimental lexicon with machine learning (DSLML) classification method. The semantic orientation pointwise mutual information (SO-PMI) method was used to construct the domain sentimental lexicon, and then a machine learning model was selected as the classifier to achieve the classification of sentimental orientation of online egg reviews. Then the LDA topic model was constructed to mine out the positive and negative topics in egg reviews. The experimental results showed that the DSLML classification model was improved in each indicator of text sentimental tendency classification, compared with machine learning models and domain sentimental lexicon (DSL) alone. From the results of the theme mining, the quality of eggs and the packaging of goods were the two aspects that consumers mostly concerned about. The conclusion of this research can provide data support and theoretical support for egg E-commerce operators to improve business strategies and service quality. © 2021, Chinese Society of Agricultural Machinery. All right reserved.

引用

页码：496 / 503

页数：7

共 38 条

[31]

ZOU Xiaohui, SUN Jing, Latent Dirichlet allocation topic model, Intelligent Computer and Applications, 4, 5, pp. 105-106, (2014)

[32]

MOMTAZI S., Unsupervised latent Dirichlet allocation for supervised question classification, Information Processing & Management, 54, 3, pp. 380-393, (2018)

[33]

SHI Jing, HU Ming, SHI Xin, Et al., Text segmentation based on model LDA, Chinese Journal of Computers, 31, 10, pp. 1865-1873, (2008)

[34]

CHIRU C, REBEDEA T, CIOTEC S., Comparison between LSA-LDA-Lexical chains, (2014)

[35]

BLEI D M, NG A Y., JORDAN M I., Latent Dirichlet allocation, Journal of Machine Learning Research, 3, pp. 993-1022, (2003)

[36]

LUO Anran, LIN Shanshan, Design of legal document crawler based on Python, Electronic Test, 19, pp. 94-95, (2020)

[37]

16, 2, (2017)

[38]

JING Li, LI Manman, HE Tingting, Sentiment classification of network reviews combining extended dictionary and self-supervised learning, Computer Science, 47, pp. 78-82, (2020)

← 1 2 3 4 →