摘要
随着互联网技术的不断创新,各大电影平台如豆瓣电影蕴含海量在线评论文本信息,挖掘并分析评论的观点以及隐藏的情感具有重要商业价值。以影院在线评论为研究对象,通过爬虫(Python)获取《我和我的祖国》评论数据,运用语义网络图、LDA模型等方法分析其中蕴含的情感信息。结果表明:大多数观众对电影持力荐态度,整体评论积极且正面;观众对于影片中《白昼流星》《前夜》《夺冠》《回归》这四个单元短片有着更多的关注,导演、短片单元部分与主体联系较为密切;LDA模型分析结果表明,观众对部分单元评价存在争议。因此,制片方要重视影评数据情感倾向与电影传播之间的关系。最后,根据研究结果提出相应的建议。
With the continuous innovation of Internet technology,major movie platforms such as Douban Movies contain a large amount of online review text information,and mining and analyzing the opinions of reviews and hidden emotions have important commercial value.The study takes the cinema online review article as research object,obtains the review data of"MY PEOPLE,MY COUNTRY"through the crawler,and analyzes the emotional information using methods such as semantic network diagram and LDA model.The results showed that:1)The majority of the audience held a strong recommendation attitude and the overall performance was positive;2)The audience paid more attention to the four short films of The Guiding Star,The Eve,The Champion and Going Home.The director and the short film unit are closely related to the main part;3)The analysis results of the LDA model show that the audience has disputes over the evaluation of some units.Therefore,we must pay attention to the relationship between the emotional tendency of film review data and film communication,and finally put forward corresponding suggestions based on the results.
作者
旷开金
廖海琳
裴文庆
KUANG Kaijin;LIAO Hailin;PEI Wenqing(School of Finance,Fujian Jiangxia University,Fuzhou,Fujian 350108;Key Laboratory of Fujian Universities for Ecology and Resource Statistics,Fuzhou,Fujian 350002;School of Marxism,Fujian Agriculture and Forestry University,Fuzhou,Fujian 350002)
出处
《武夷学院学报》
2022年第5期68-74,共7页
Journal of Wuyi University
基金
福建省中青年教师教育科研项目(JT180584)
福建省财政资助科研项目(2019CZ09)
福建江夏学院校级科研项目(JXS2020007)
生态与资源统计福建省高校重点实验室开放课题(PTJH1701102)。
