基于弹幕情感分析的视频片段推荐模型

doi:10.11772/j.issn.1001-9081.2017.04.1065

计算机应用 ›› 2017, Vol. 37 ›› Issue (4): 1065-1070.DOI: 10.11772/j.issn.1001-9081.2017.04.1065

基于弹幕情感分析的视频片段推荐模型

邓扬, 张晨曦, 李江峰

同济大学软件学院, 上海 201804

收稿日期:2016-10-25 修回日期:2016-12-21 出版日期:2017-04-10 发布日期:2017-04-19
通讯作者: 李江峰
作者简介:邓扬(1991-),男,四川成都人,硕士研究生,主要研究方向:信息检索、机器学习;张晨曦(1960-),男,福建龙岩人,教授,博士生导师,博士,主要研究方向:分布式计算、嵌入式系统;李江峰(1983-),男,湖北荆州人,讲师,博士,CCF会员,主要研究方向:分布式计算、社会网络计算。

Video shot recommendation model based on emotion analysis using time-sync comments

DENG Yang, ZHANG Chenxi, LI Jiangfeng

School of Software Engineering, Tongji University, Shanghai 201804, China

Received:2016-10-25 Revised:2016-12-21 Online:2017-04-10 Published:2017-04-19

摘要/Abstract

摘要： 针对传统的视频情感分析方法计算效率较低且结果不易解释等问题，提出一种基于弹幕文本的视频片段情感识别算法，并以此作为视频片段的推荐依据。首先对基于情感分析的视频片段推荐问题提出形式化描述。其次，通过构建基于隐含狄利克雷分布（LDA）的弹幕词语分类，评估弹幕词语在视频片段中的多维情感向量，同时，根据视频片段之间的情感依赖关系推荐视频的情感片段。所提方法的推荐准确度比基于词频-逆文档频率（TF-IDF）的推荐算法提高了28.9%，相对于传统LDA模型提高了43.8%。实验结果表明所提模型可有效应用于信息繁杂的不规则文本情感分析。

关键词: 视频片段推荐, 弹幕情感, 主题模型, 情感分析, 情感向量

Abstract: To solve the problem that traditional video emotional analysis methods can not work effectively and the results are not easy to explain, a video shot emotional analysis approach based on time-sync comments was proposed, as a basis for the recommendation of video shots. First, a formal description of video shots recommendation based on emotion analysis was studied. Then, after analyzing the classification of time sync comments based on Latent Dirichlet Allocation (LDA) topic model, the emotional vector of the words in time-sync comments were evaluated. Meanwhile, the emotion relationships among the video shots were analyzed for video shots recommendation. The recommendation precision of the proposed method was 28.9% higher than that of the method based on Term Frequency-Inverse Document Frequency (TF-IDF), and 43.8% higher than that of traditional LDA model. The experimental results show that the proposed model is effective in analyzing the complex emotion of different kinds of text information.

Key words: video shot recommendation, time-sync comments emotion, topic modeling, emotion analysis, emotional vector

中图分类号:

TP391.1

邓扬, 张晨曦, 李江峰. 基于弹幕情感分析的视频片段推荐模型[J]. 计算机应用, 2017, 37(4): 1065-1070.

DENG Yang, ZHANG Chenxi, LI Jiangfeng. Video shot recommendation model based on emotion analysis using time-sync comments[J]. Journal of Computer Applications, 2017, 37(4): 1065-1070.

参考文献

[1] WU B, ZHONG E, TAN B, et al. Crowdsourced time-sync video tagging using temporal and personalized topic modeling[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2014: 721-730.
[2] LV G, XU T, CHEN E, et al. Reading the videos: temporal labeling for crowdsourced time-sync videos based on semantic embedding[C]//Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence. Menlo Park, CA: AAAI Press, 2016:3000-3006.
[3] XIAN Y, LI J, ZHANG C, et al. Video highlight shot extraction with time-sync comment[C]//HOTPOST 2015: Proceedings of the 7th International Workshop on Hot Topics in Planet-scale Mobile Computing and Online Social neTworking. New York: ACM, 2015: 31-36.
[4] HAMASAKI M, TAKEDA H, HOPE T, et al. Network analysis of an emergent massively collaborative creation community[C]//Proceedings of the Third International ICWSM Conference. Menlo Park, CA: AAAI Press, 2009: 222-225.
[5] WU Z, ITO E. Correlation analysis between user's emotional comments and popularity measures[C]//Proceedings of the 2014ⅡAI 3rd International Conference on Advanced Applied Informatics. Piscataway, NJ: IEEE, 2014: 280-283.
[6] YOSHⅡ K, GOTO M. MusicCommentator: generating comments synchronized with musical audio signals by a joint probabilistic model of acoustic and textual features[EB/OL].[2016-03-10]. https://staff.aist.go.jp/m.goto/PAPER/ICEC2009yoshii.pdf.
[7] ZHAO J, LIU K, WANG G. Adding redundant features for CRFs-based sentence sentiment classification[C]//EMNLP 2008: Proceedings of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA, USA: Association for Computational Linguistics, 2008: 117-126.
[8] ZHOU L, XIA Y, LI B, et al. WIA-opinmine system in NTCIR-8 MOAT evaluation[EB/OL].[2016-03-10]. http://research.nii.ac.jp/ntcir/workshop/OnlineProceedings8/NTCIR/15-NTCIR8-MOAT-ZhouL.pdf.
[9] 李寿山, 黄居仁.基于Stacking组合分类方法的中文情感分类研究[J]. 中文信息学报, 2010, 24(5): 56-61.(LI S S, HUANG C R. Chinese sentiment classification based on stacking combination method[J]. Journal of Chinese Information Processing, 2010, 24(5): 56-61.)
[10] YU H, HATZIVASSILOGLOU V. Towards answering opinion questions: separating facts from opinions and identifying the polarity of opinion sentences[C]//EMNLP 2003: Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA, USA: Association for Computational Linguistics, 2003: 129-136.
[11] 刘志明, 刘鲁.基于机器学习的中文微博情感分类实证研究[J]. 计算机工程与应用, 2012, 48(1): 1-4.(LIU Z M, LIU L. Empirical study of sentiment classification for Chinese microblog based on machine learning[J]. Computer Engineering and Applications, 2012, 48(1): 1-4.)
[12] BLEI D M, NG A Y, JORDAN M I. Latent Dirichlet allocation[J]. Journal of Machine Learning Research, 2003, 3: 993-1022.
[13] HEINRICH G. Parameter estimation for text analysis[EB/OL].[2016-03-10]. http://www.arbylon.net/publications/text-est2.pdf.
[14] WU B, ZHONG E, HORNER A, et al. Music emotion recognition by multi-label multi-layer multi-instance multi-view learning[C]//Proceedings of the 22nd ACM International Conference on Multimedia. New York: ACM, 2014: 117-126.
[15] REN J. Document for Ren-CECps 1.0[EB/OL].[2016-03-10]. http://a1-www.is.tokushima-u.ac.jp/member/ren/RenCECps1.0/Ren-CECps1.0.html.
[16] QUAN C, REN F. Sentence emotion analysis and recognition based on emotion words using Ren-CECps[J]. International Journal of Advanced Intelligence, 2010, 2(1): 105-117.
[17] REN F, QUAN C. Linguistic-based emotion analysis and recognition for measuring consumer satisfaction: an application of affective computing[J]. Information Technology and Management, 2012, 13(4): 321-332.
[18] 郑飏飏, 徐健, 肖卓. 情感分析及可视化方法在网络视频弹幕数据分析中的应用[J]. 现代图书情报技术, 2015, 31(11): 82-90.(ZHENG Y Y, XU J, XIAO Z. Utilization of sentiment analysis and visualization in online video bullet-screen comments[J]. New Technology of Library and Information Service, 2015, 31(11): 82-90.)

基于弹幕情感分析的视频片段推荐模型

Video shot recommendation model based on emotion analysis using time-sync comments

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	章荪, 尹春勇. 基于多任务学习的时序多模态情感分析模型[J]. 计算机应用, 2021, 41(6): 1631-1639.
[2]	赖雪梅, 唐宏, 陈虹羽, 李珊珊. 基于注意力机制的特征融合-双向门控循环单元多模态情感分析[J]. 计算机应用, 2021, 41(5): 1268-1274.
[3]	杨丰瑞, 霍娜, 张许红, 韦巍. 基于注意力机制的主题扩展情感对话生成[J]. 计算机应用, 2021, 41(4): 1078-1083.
[4]	邱宁佳, 王晓霞, 王鹏, 王艳春. 融合语法规则的双通道中文情感模型分析[J]. 计算机应用, 2021, 41(2): 318-323.
[5]	孟祥瑞, 杨文忠, 王婷. 基于图文融合的情感分析研究综述[J]. 计算机应用, 2021, 41(2): 307-317.
[6]	杨书新, 张楠. 融合情感词典与上下文语言模型的文本情感分析[J]. 计算机应用, 2021, 41(10): 2829-2834.
[7]	杨璐, 何明祥. 基于门控机制和卷积神经网络的中文文本情感分析模型[J]. 计算机应用, 2021, 41(10): 2842-2848.
[8]	杨威亚, 余正涛, 高盛祥, 宋燃. 基于跨语言神经主题模型的汉越新闻话题发现方法[J]. 计算机应用, 2021, 41(10): 2879-2884.
[9]	朱思淼, 魏世伟, 魏思恒, 余敦辉. 基于弹幕情感分析和主题模型的视频推荐算法[J]. 计算机应用, 2021, 41(10): 2813-2819.
[10]	郭可心, 张宇翔. 基于多层次空间注意力的图文评论情感分析方法[J]. 计算机应用, 2021, 41(10): 2835-2841.
[11]	杨云龙, 孙建强, 宋国超. 基于门控循环单元和胶囊特征的文本情感分析[J]. 计算机应用, 2020, 40(9): 2531-2535.
[12]	尹春勇, 章荪. 面向短文本情感分类的端到端对抗变分贝叶斯方法[J]. 计算机应用, 2020, 40(9): 2536-2542.
[13]	孙敏, 李旸, 庄正飞, 余大为. 基于并行混合网络融入注意力机制的情感分析[J]. 计算机应用, 2020, 40(9): 2543-2548.
[14]	陈佳伟, 韩芳, 王直杰. 基于自注意力门控图卷积网络的特定目标情感分析[J]. 计算机应用, 2020, 40(8): 2202-2206.
[15]	田保军, 刘爽, 房建东. 融合主题信息和卷积神经网络的混合推荐算法[J]. 计算机应用, 2020, 40(7): 1901-1907.