All Title Author
Keywords Abstract

Publish in OALib Journal
ISSN: 2333-9721
APC: Only $99

ViewsDownloads

Relative Articles

More...

基于LDA模型的商品评论情感分析研究
Research on Sentiment Analysis of Product Reviews Based on LDA Model

DOI: 10.12677/HJDM.2023.133023, PP. 230-234

Keywords: LDA模型,TF-IDF词向量,情感分析,逻辑回归模型,LDA Model, TF-IDF Word Vector, Emotional Analysis, Logical Regression Mode

Full-Text   Cite this paper   Add to My Lib

Abstract:

在大数据时代,商品评论情感分析可以帮助公司制定销售策略,提高产品性能,从而让消费者可以购买到优质产品。本文提出了一种基于LDA模型商品评论情感分析方法。该方法综合实际打分、预测出的评论为正面的概率、“有用”比例、是否购买、是否是会员五项指标计算出评论文本的综合情感得分。并根据以上研究结果,提出相关商品的改进建议,从而提高商品销售率。
In the era of big data, emotional analysis of product reviews can help companies develop sales strategies, improve product performance, and enable consumers to purchase high-quality products. This article proposes a LDA based method for the sentiment analysis of product reviews. This method calculates the comprehensive sentiment score of the review text by integrating five indica-tors: actual scoring, probability of predicted positive reviews, “useful” ratio, whether to purchase, and whether to be a member. And through the above research results, suggestions for improving relevant products are proposed to improve the sales rate of the products.

References

[1]  张建成. 基于在线商品评论的消费者满意度和认知研究[D]: [硕士学位论文]. 宁波: 宁波大学, 2012.
[2]  王鹤琴, 王杨. 基于情感倾向和SVM混合极短文本分类模型[J]. 科技通报, 2018, 34(8): 149-154.
[3]  Saranya, S., Veena, S., Vivek, D., et al. (2018) Finding Reputed Items Based on Sentimental Analysis of User Reviews and Ratings. Journal of Computational and Theoretical Nanoscience, 15, 3057-3061.
https://doi.org/10.1166/jctn.2018.7591
[4]  刘永芬. 支持向量机在入侵检测中的应用[D]: [硕士学位论文]. 福州: 福建师范大学, 2010.
[5]  曾小芹, 余宏. 基于Python的商品评论文本情感分析[J]. 电脑知识与技术, 2020, 16(8): 181-183.
[6]  王梦宇. 基于LDA主题模型的在线评论聚类研究[D]: [硕士学位论文]. 兰州: 兰州大学, 2021.
[7]  刘擎权. 基于改进的TFIDF算法在文本分析中的应用[D]: [硕士学位论文]. 南昌: 南昌大学, 2019.
[8]  赵雅平. 基于逻辑回归模型的天津市老年人健康养老服务需求研究[D]: [硕士学位论文]. 天津: 天津财经大学, 2019.

Full-Text

comments powered by Disqus

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133

WeChat 1538708413