• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学 ›› 2022, Vol. 44 ›› Issue (03): 521-529.

• 人工智能与数据挖掘 • 上一篇    下一篇

基于弹幕文本挖掘的社交媒体KOL研究

周忠宝1,朱文静1,王皓1,郭修远2,王立峰2   

  1. (1.湖南大学工商管理学院,湖南 长沙 410082;2.湖南大学新闻与传播学院,湖南 长沙 410082)

  • 收稿日期:2020-04-15 修回日期:2020-11-23 接受日期:2022-03-25 出版日期:2022-03-25 发布日期:2022-03-24
  • 基金资助:
    国家自然科学基金(71771082);湖南省社科基金(20YBA060);湖南省杰出青年科学基金(2017JJ1012);湖南省“芙蓉学者奖励计划”

Social media KOL based on barrage text mining

ZHOU Zhong-bao1,ZHU Wen-jing1,WANG Hao1,GUO Xiu-yuan2,WANG Li-feng2   

  1. (1.School of Business Administration,Hunan University,Changsha 410082;
    2.School of Journalism and Communication,Hunan University,Changsha 410082,China)
  • Received:2020-04-15 Revised:2020-11-23 Accepted:2022-03-25 Online:2022-03-25 Published:2022-03-24

摘要: 社交媒体关键意见领袖KOL为品牌营销带来更多机会,所以备受广告主青睐,但KOL行业的低门槛进入和数据造假行为,导致广告主无法快速找到与自身品牌匹配的KOL。基于以上背景,对KOL发布在社交平台的视频进行研究,对视频中的弹幕文本进行动态主题分析,刻画弹幕主题随时间的变化,同时使用卷积神经网络模型对含有广告的视频弹幕文本进行情感分析,进一步分析观众对于KOL推广行为的情感极性。实验结果表明,本文提出的KOL分析方法更加全面具体地评估了KOL的商业价值,能够帮助广告主高效找到合适的KOL。

关键词: 社交媒体, 关键意见领袖, 弹幕文本挖掘, 卷积神经网络

Abstract: Social media Key Opinion Leader (KOL) is very popular with advertisers because of their excellent business value. However, with the low entry threshold of the KOL industry and data fraud, advertisers are unable to find a KOL that matches their own brand quickly. Based on the above background, this paper studies the video released by KOL on social platforms, analyzes the dynamic theme of the barrage text in the video, and describes the change of the theme of the barrage over time. At the same time, a convolutional neural network model is used to perform sentiment analysis on the barrage text of the video containing the advertisement, and further analyze the audience's emotional polarity to the situation that the video released by KOL containing the advertisement. The experimental results show that the proposed KOL analysis method evaluates the commercial value of KOL more comprehensively and specifically, helping advertisers find a suitable KOL efficiently.

Key words: social media, key opinion leader, video barrage text mining, convolutional neural network