| 摘要: |
| 目的 在大数据环境下，运用大数据技术提取赛珍珠文化元素，探究大数据挖掘理念在文创产品设计中应用的可行性。方法 首先，采集赛珍珠相关数据资料，借助网络爬虫工具采集网络媒体中赛珍珠相关的文本信息，同时人工搜集赛珍珠相关学术研究以及社会访谈资料，然后将数据保存为可编辑的文本形式。其次，运用中文分词工具对采集的文本信息进行处理，将语言字符串切分成词语，滤除中文停用词、低频词及干扰词，形成精炼的赛珍珠数据集合。之后，采用LDA主题模型算法对数据集合进行降维、聚类，形成初步的主题模型，然后经过人工筛选构建赛珍珠文化元素主题模型。最后，根据文化元素主题模型内容，选择赛珍珠文化元素进行赛珍珠文创产品设计实践。结论 依照大数据挖掘理念，通过对网络爬虫技术、中文分词工具以及LDA主题模型算法等大数据处理工具的综合应用，能够科学高效地从庞大的社会网络媒体中提炼赛珍珠文化元素，从而达到促进整个文创产品设计流程的效果。 |
| 关键词: 大数据挖掘 网络爬虫 中文分词 主题模型 赛珍珠 文创产品 |
| DOI：10.19554/j.cnki.1001-3563.2021.22.044 |
| 分类号:TB472 |
| 基金项目:镇江市2020年度社科应用研究项目 |
|
| Extraction and Application of Pearl S Buck’s Cultural Elements Based on Big Data Mining |
|
JIANG Si-ju, LU Zhang-ping, LI Ming-zhu
|
|
(Jiangsu University, Zhenjiang 212013, China)
|
| Abstract: |
| This paper aims to use big data technology to extract Pearl S Buck’s cultural elements and explore the feasibility of applying big data mining concepts in the design of cultural and creative products in the big data environment. First, collect data about Pearl S Buck, use web crawler tool to collect text information about Pearl S Buck in online media, and manually collect related academic research and social interviews about Pearl S Buck at the meantime, and then save the data in editable text form. Second, use the Chinese word segmentation tool to process the collected text information, divide the language string into words, filter out Chinese stop words, low-frequency words and noise words, and form a refined Pearl S Buck data set. After that, the LDA theme model algorithm is used to reduce the dimensionality and clustering of the data set to form a preliminary theme model, and then construct the theme model of Pearl S Buck’s cultural elements through manual screening. Finally, according to the content of the cultural element theme model, the Pearl S Buck’s cultural elements were selected for the practice of Pearl S Buck’s cultural and creative product design. According to the concept of big data mining, through the comprehensive application of big data processing tools such as web crawler technology, Chinese word segmentation tools and LDA theme model algorithm, it can scientifically and efficiently extract Pearl S Buck’s cultural elements from the huge social network media, so as to achieve the effect of promoting the entire cultural and creative product design process. |
| Key words: big data mining web crawler Chinese word segmentation theme model Pearl S Buck cultural and creative products |
渝公网安备 50010702501716号