Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (7): 1878-1884.DOI: 10.11772/j.issn.1001-9081.2020101619

Special Issue: 人工智能

• Artificial intelligence • Previous Articles     Next Articles

Deep attention video popularity prediction model fusing content features and temporal information

WU Wei1, LI Zeping1, YANG Huawei2, LIN Chuan1, WANG Zhongde1   

  1. 1. College of Computer Science and Technology, Guizhou University, Guiyang Guizhou 550025, China;
    2. College of Big Data Application and Economics, Guizhou University of Finance and Economics, Guiyang Guizhou 550025, China
  • Received:2020-10-19 Revised:2021-01-17 Online:2021-07-10 Published:2021-01-27
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61462014), the Science and Technology Foundation of Guizhou Province (S2017JP00401185093).


武维1, 李泽平1, 杨华蔚2, 林川1, 王忠德1   

  1. 1. 贵州大学 计算机科学与技术学院, 贵阳 550025;
    2. 贵州财经大学 大数据应用与经济学院, 贵阳 550025
  • 通讯作者: 李泽平
  • 作者简介:武维(1995-),女,贵州毕节人,硕士研究生,主要研究方向:流行度预测、流媒体;李泽平(1964-),男,贵州贵阳人,教授,博士,主要研究方向:流行度预测、计算机网络、流媒体;杨华蔚(1965-),女,贵州贵阳人,教授,博士,主要研究方向:金融风险管理;林川(1975-),男,四川自贡人,副教授,硕士,主要研究方向:计算机网络、云计算;王忠德(1963-),男,山东青岛人,实验师,主要研究方向:流媒体。
  • 基金资助:

Abstract: Aiming at the problem that it is difficult to capture the temporal information during the dynamic change of video popularity, a Deep Attention video popularity prediction model Fusing Content and Temporal information (DAFCT) was proposed. Firstly, according to the users' feedback information, an Attention mechanism based Long Short-Term Memory network (Attention-LSTM) model was constructed to capture the popular trend and mine the temporal information. Secondly, Neural Factorization Machine (NFM) was used to process multi-modal content features and embedding techniques were adopted to reduce the computational complexity of the model by reducing the dimension of sparse high-dimensional features. Finally, the concatenate method was employed to fuse the temporal information and content features, and a Deep Attention Video Popularity Prediction (DAVPP) algorithm was designed to solve the proposed DAFCT. Experimental results show that compared with Attention-LSTM model and NFM model, the recall of DAFCT is improved by 10.82 and 3.31 percentage points, and the F1 score was improved by 9.80 and 3.07 percentage points, respectively.

Key words: popularity prediction, content feature, time-series information, attention mechanism, Neural Factorization Machine (NFM)

摘要: 针对视频流行度动态变化过程中的时序信息难以捕捉的问题,提出一种融合内容特征和时序信息的深度注意力视频流行度预测模型(DAFCT)。首先,根据用户的反馈信息,构建基于注意力机制的长短期记忆网络(Attention-LSTM)模型来捕捉流行趋势并挖掘时序信息;然后,采用神经网络因子分解机(NFM)处理多模态的内容特征,并采用嵌入技术对稀疏的高维特征进行降维处理,从而降低模型的计算复杂性;最后,采用concatenate方法融合时序信息和内容特征,并设计了一种深度注意力视频流行度预测(DAVPP)算法来求解DAFCT。实验结果表明,与Attention-LSTM模型和NFM模型相比,DAFCT的召回率分别提高了10.82和3.31个百分点,F1分数分别提高了9.80和3.07个百分点。

关键词: 流行度预测, 内容特征, 时序信息, 注意力机制, 神经网络因子分解机

CLC Number: