Zhou Lichun
School of Media and Communication, Shangqiu Normal University, Shangqiu, China.
Front Psychol. 2022 May 12;13:915443. doi: 10.3389/fpsyg.2022.915443. eCollection 2022.
This paper takes laptops as an example to carry out research on quantitative model of brand recognition based on sentiment analysis of big data. The basic idea is to use web crawler technology to obtain the most authentic and direct information of different laptop brands from first-line consumers from public spaces such as buyer reviews of major e-commerce platforms, including review time, text reviews, satisfaction ratings and relevant user information, etc., and then analyzes consumers' sentimental tendencies and recognition status of the product brands. This study extracted a total of 437,815 user reviews of laptops from e-commerce platforms from January 1, 2019 to December 31, 2021, and performed data preprocessing on the obtained review data, followed by sentiment dictionary construction, attribute expansion, text quantification and algorithm evaluation. This paper analyzed the information receiving and processing hierarchy of the quantitative model of brand recognition, discussed the interactive relationship between brand recognition and consumer sentiment, discussed the brand recognition bias, style and demand in the context of big data, and performed the sentiment statistics and dimension analysis in the quantitative model of brand recognition. The study results show that the quantitative model of brand recognition based on sentiment analysis of big data can transform and map the keywords in text to word vectors in the high-dimensional semantic space by performing unsupervised machine learning on the text based on artificial neural network computer bionic metaphors; the model can accumulate each brand-related buyer review in the corresponding brand recognition dimension, so as to obtain the value of each product in each dimension of brand recognition; finally, the model will add the values of each dimension of brand recognition, that is, obtain the relevant value of the sum of each brand recognition. The results of this paper may provide a reference for further research on the quantitative model of brand recognition based on sentiment analysis of big data.
本文以笔记本电脑为例，开展基于大数据情感分析的品牌识别量化模型研究。基本思路是利用网络爬虫技术，从主流电商平台买家评论等公共场所的一线消费者那里获取不同笔记本电脑品牌最真实、最直接的信息，包括评论时间、文字评论、满意度评分及相关用户信息等，进而分析消费者对产品品牌的情感倾向和识别状况。本研究共提取了2019年1月1日至2021年12月31日电商平台上437,815条笔记本电脑用户评论，并对获取的评论数据进行数据预处理，随后进行情感词典构建、属性扩展、文本量化及算法评估。本文分析了品牌识别量化模型的信息接收与处理层级，探讨了品牌识别与消费者情感的互动关系，讨论了大数据背景下的品牌识别偏差、风格及需求，并在品牌识别量化模型中进行了情感统计与维度分析。研究结果表明，基于大数据情感分析的品牌识别量化模型可通过基于人工神经网络计算机仿生隐喻对文本进行无监督机器学习，将文本中的关键词转换并映射到高维语义空间中的词向量；该模型能在相应品牌识别维度中累积每条与品牌相关的买家评论，从而获得各产品在品牌识别各维度的数值；最后，模型将品牌识别各维度的数值相加，即得到各品牌识别总和的相关数值。本文的研究结果可能为基于大数据情感分析的品牌识别量化模型的进一步研究提供参考。
