﻿ 基于在线评论获取产品优化辅助决策信息的算法研究
 计算机系统应用  2019, Vol. 28 Issue (9): 180-184 PDF

Online Comments Based Algorithm Research for Obtaining Product Optimization Assistant Decision Information
LI Xiang
School of Mechanical Engineering and Mechanics, Ningbo University, Ningbo 315211, China
Abstract: In the era of big data, how to grasp customer needs through data analysis and increase the scientific nature of product optimization is of strategic importance to enterprises. This study applies online comment data to the assisted optimization of enterprise products, proposes techniques and methods for obtaining product optimization information, and realizes the acquisition of product optimization information. Firstly, we calculate the indicators such as customer attention and satisfaction in online reviews, and construct a weighting algorithm model for customer opinions. Next, the word pairs of product characteristics and customer opinions are extracted, and the weight of customer opinions is calculated according to the weight algorithm model. Then, the corresponding product optimization information is found through the correlation matrix. Finally, the feasibility of the method is verified by an example.
Key words: product optimization     text mining     weight matrix     information acquisition     sentiment classification

1 研究框架

 图 1 基于在线评论的产品优化决策信息获取的挖掘流程

2 在线评论顾客意见的权重计算 2.1 产品特征的关注度分析

 $F({t_i}) = \frac{{f({t_i})}}{{\displaystyle \sum\limits_{{t_m} \subset T(t)} {f({t_m})} }}$ (1)
2.2 顾客的满意度分析

(1)预处理 通过编写代码自动实现评论数据的去重、清洗、分词、去停用词的工作.

(2)特征提取 由于机器学习只能对数值或类别数据进行训练, 所以需要转化成向量的形式, 文章通过Doc2Vec词向量模型[16]对处理好的数据进行特征向量提取.

(3)情感分类 通过逻辑回归分类器对提取的特征向量进行训练, 生成情感分类模型, 实现对评论数据的情感分类.

 $Q({t_i}) = \left\{ \begin{gathered} 1{\rm{ - }}{q_{\rm{i}}}\begin{array}{*{20}{c}} {\begin{array}{*{20}{c}} {}&{} \end{array}}&{{q_i} \ge {q_k}} \end{array} \\ \lambda (1 - {q_i})\begin{array}{*{20}{c}} {}&{{q_i} < {q_k}} \end{array} \\ \end{gathered} \right.$ (2)

2.3 在线评论顾客意见的权重计算

 ${W_{{O_j}}}[In({{\rm{t}}_i})] = \frac{{{o_{ji}}}}{{\displaystyle\sum\limits_{{o_{li}} \subset In({t_i})} {{o_{li}}} }}$ (3)
 ${W_{{O_j}}}[out({t_i})] = \frac{{{o_{ji}}}}{{\displaystyle\sum\limits_{{o_{jn}} \subset out({t_i})} {{o_{jn}}} }}$ (4)

 $W({t_i}{o_j}) = \frac{{\lambda \beta {o_{ji}}^2 \cdot f({t_i}) \cdot (1 - {q_i})}}{{\displaystyle\sum\limits_{{o_{li}} \subset In({t_i})} {{o_{li}}} \cdot \displaystyle\sum\limits_{{o_{jn}} \subset out({t_i})} {{o_{jn}}} \cdot \displaystyle\sum\limits_{{t_m} \subset T(t)} {f{t_m}} }}$ (5)

3 产品优化决策信息获取 3.1 在线评论中顾客意见提取流程

 图 2 顾客意见提取流程

3.2 基于顾客意见的产品优化决策信息获取

4 实例验证

 图 3 评论数据的词云图

 图 4 在线评论的情感分类结果

5 结语

 [1] 邵景波, 胡名叶, 许万有. 在线评论情感属性的动态变化——基于iPhone 4的实证研究. 预测, 2016, 35(5): 9-15. [2] 朱丽叶, 袁登华, 张静宜. 在线用户评论质量与评论者等级对消费者购买意愿的影响——产品卷入度的调节作用. 管理评论, 2017, 29(2): 87-96. [3] 王阳, 王伟军, 刘智宇. 在线负面评论信息对潜在消费者购买意愿影响研究. 情报科学, 2018, 36(10): 156-163. [4] 相甍甍, 郭顺利, 张向先. 面向用户信息需求的移动商务在线评论效用评价研究. 情报科学, 2018, 36(2): 132-138, 158. [5] 苗蕊, 徐健. 评分不一致性对在线评论有用性的影响--归因理论的视角. 中国管理科学, 2018, 26(5): 178-186. [6] Alaei AR, Becken S, Stantic B. Sentiment analysis in tourism: Capitalizing on big data. Journal of Travel Research, 2019, 58(2): 175-191. DOI:10.1177/0047287517747753 [7] 修国义, 王俭, 过仕明. 引入信息传递效率的在线评论效用评价. 情报科学, 2019, 37(1): 43-50. [8] Cheng XS, Fu SX, Sun JS, et al. An investigation on online reviews in sharing economy driven hospitality platforms: A viewpoint of trust. Tourism Management, 2019, 71: 366-377. DOI:10.1016/j.tourman.2018.10.020 [9] 于超, 樊治平. 基于顾客在线评论的服务要素优化配置方法. 计算机集成制造系统, 2019, 25(3): 714-725. [10] Elwalda A, Lü K, Ali M. Perceived derived attributes of online customer reviews. Computers in Human Behavior, 2016, 56: 306-319. DOI:10.1016/j.chb.2015.11.051 [11] 秦海菲, 杜军平. 酒店在线评论数据的特征挖掘. 智能系统学报, 2018, 13(6): 1006-1014. [12] Verhagen T, Nauta A, Feldberg F. Negative online word-of-mouth: Behavioral indicator or emotional release?. Computers in Human Behavior, 2013, 29(4): 1430-1440. DOI:10.1016/j.chb.2013.01.043 [13] 蔡淑琴, 秦志勇, 李翠萍, 等. 面向负面在线评论的情感强度对有用性的影响研究. 管理评论, 2017, 29(2): 79-86. [14] Geetha M, Singha P, Sinha S. Relationship between customer sentiment and online customer ratings for hotels - An empirical analysis. Tourism Management, 2017, 61: 43-54. DOI:10.1016/j.tourman.2016.12.022 [15] 郑丽娟, 王洪伟. 基于情感本体的在线评论情感极性及强度分析: 以手机为例. 管理工程学报, 2017, 31(2): 47-54. [16] 逯万辉, 谭宗颖. 学术成果主题新颖性测度方法研究--基于Doc2Vec和HMM算法. 数据分析与知识发现, 2018, 2(3): 22-29. DOI:10.11925/infotech.2096-3467.2017.1012