[1]王 力.基于视频弹幕的特征发现及情感分析研究[J].计算机技术与发展,2022,32(01):141-146.[doi:10. 3969 / j. issn. 1673-629X. 2022. 01. 024]
　WANG Li.Research on Feature Discovery and Sentiment Analysis ofBarrage Based on Electronic Product Review[J].,2022,32(01):141-146.[doi:10. 3969 / j. issn. 1673-629X. 2022. 01. 024]
点击复制

基于视频弹幕的特征发现及情感分析研究()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年01期
页码:
141-146
栏目:
应用前沿与综合
出版日期:
2022-01-10

文章信息/Info

Title:
Research on Feature Discovery and Sentiment Analysis ofBarrage Based on Electronic Product Review
文章编号:
1673-629X(2022)01-0141-06
作者:
王 力1; 2
1. 中国科学技术信息研究所,北京 100038;
2. 富媒体数字出版内容组织与知识服务重点实验室,北京 100038
Author(s):
WANG Li1; 2
1. China Institute of Science and Technology Information,Beijing 100038,China;
2. Key Laboratory of Rich-media Knowledge Organization and Service of Digital Publishing Content,Beijing 100038,China
关键词:
情感分析; 深度学习; 弹幕; 注意力机制; 双向长短记忆神经网络
Keywords:
sentiment analysis; deep learning; barrage; attention mechanism; BILSTM
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 01. 024
摘要:
随着数字媒体技术的快速发展,弹幕在电子产品评测视频中的使用频率逐年增高,越来越多的用户倾向于通过这种方式了解产品的信息并发表自己的见解。 该类弹幕评论除了具有短小、实时性强等特点外,还包含着大量弹幕用户的情感倾向信息。 这些信息对于网站和商家都具有重要意义。 针对这个问题,对爬取的华为 P30 手机评测视频共 9 万 2 千余条视频弹幕,使用统计方法分析该类弹幕评论特点;接着结合词向量技术( Word2Vec) 、卷积神经网络( CNN) 和双向长短记忆神经网络( BILSTM)的优势,在 BILSTM-CNN 对时序数据进行编码后,引入 ATTENTION 机制,构建 BILSTM-CNN-ATT 组合模型,并通过多组对比实验进行验证。 结果表明,弹幕长度和弹幕数量呈负相关关系。 在九种模型中,BILSTM-CNN-ATT 组合模型在电子产品评测视频的弹幕评论中具有良好的情感分析效果。
Abstract:
With the rapid development of digital media technology,the use frequency of barrage in electronic product evaluation video isincreasing year by year, and more and more users tend to know product information and express their opinions through this way. Inaddition to being short and real-time,such comments also contain a large amount of emotional information of barrage users,which is important to both the website and the business. In order to solve this problem,more than 92 000 video barrage clips were collected fromHuawei P30 mobile phone evaluation videos,and the characteristics of such barrage comments were analyzed by statistical methods. Thencombining the advantages of Word2Vec,CNN and BILSTM,the ATTENTION mechanism was introduced after BILSTM-CNN encodedthe time series data, and the BILSTM - CNN - ATT combination model was constructed and verified through multiple groups ofcomparative experiments. It is showed that there is a negative correlation between the length of barrage and the number of barrage.Among the nine models,the BILSTM- CNN - ATT combined model is effective on sentiment analysis in the barrage comments in theelectronic product evaluation video.

相似文献/References:

[1]李妍坊,许歆艺,刘功申. 面向情感倾向性识别的特征分析研究[J].计算机技术与发展,2014,24(09):33.
　LI Yan-fang,XU Xin-yi,LIU Gong-shen. Research on Feature Analysis Oriented Text Sentiment Identification[J].,2014,24(01):33.
[2]苏小英[][],孟环建[]. 基于神经网络的微博情感分析[J].计算机技术与发展,2015,25(12):161.
　SU Xiao-ying[][],MENG Huan-jian[]. Sentiment Analysis of Micro-blog Based on Neural Networks[J].,2015,25(01):161.
[3]陈浩翔,蔡建明,刘铿然,等. 手写数字深度特征学习与识别[J].计算机技术与发展,2016,26(07):19.
　CHEN Hao-xiang,CAI Jian-ming,LIU Keng-ran,et al. Deep Learning and Recognition of Handwritten Numeral Features[J].,2016,26(01):19.
[4]贺飞翔,赵启军. 基于深度学习的头部姿态估计[J].计算机技术与发展,2016,26(11):1.
　HE Fei-xiang,ZHAO Qi-jun. Head Pose Estimation Based on Deep Learning[J].,2016,26(01):1.
[5]曾志平[] [],萧海东[],张新鹏[]. 基于DBN的金融时序数据建模与决策[J].计算机技术与发展,2017,27(04):1.
　ZENG Zhi-ping[] [],XIAO Hai-dong[],ZHANG Xin-peng[]. Modeling and Decision-making of Financial Time Series Data with DBN[J].,2017,27(01):1.
[6]李宏林. 分析式纹理合成技术及其在深度学习的应用[J].计算机技术与发展,2017,27(11):7.
　LI Hong-lin. Analyzed Texture-synthesis Techniques and Their Applications in Deep Learning[J].,2017,27(01):7.
[7]曲之琳,胡晓飞.基于改进激活函数的卷积神经网络研究[J].计算机技术与发展,2017,27(12):77.[doi:10.3969/ j. issn.1673-629X.2017.12.017]
　QU Zhi-lin,HU Xiao-fei.Research on Convolutional Neural Network Based on Improved Activation Function[J].,2017,27(01):77.[doi:10.3969/ j. issn.1673-629X.2017.12.017]
[8]吴 超,邵 曦.基于深度学习的指静脉识别研究[J].计算机技术与发展,2018,28(02):200.[doi:10．3969/j．issn．1673－629X．2018．02．043]
　WU Chao,SHAO Xi.Research on Finger Vein Ｒecognition Based on Deep Learning[J].,2018,28(01):200.[doi:10．3969/j．issn．1673－629X．2018．02．043]
[9]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(01):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[10]施泽浩,赵启军.基于全卷积网络的目标检测算法[J].计算机技术与发展,2018,28(05):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
　SHI Ze-hao,ZHAO Qi-jun.Object Detection Algorithm Based on Fully Convolutional Neural Network[J].,2018,28(01):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
[11]王宇欣,方浩宇,张 伟,等.注意力机制在情感分析中的应用研究[J].计算机技术与发展,2022,32(04):193.[doi:10. 3969 / j. issn. 1673-629X. 2022. 04. 033]
　WANG Yu-xin,FANG Hao-yu,ZHANG Wei,et al.Application Research of Attention Mechanism in Sentiment Analysis[J].,2022,32(01):193.[doi:10. 3969 / j. issn. 1673-629X. 2022. 04. 033]

更新日期/Last Update: 2022-01-10