Short Video User Behavior Prediction Algorithm Based on Multi-task and User Interest
GU Yirana,b, XU Zebina, YANG Haigenc
a. College of Automation & College of Artificial Intelligence; b. Center of Smart Campus Research; c. Center of Wider and Wireless Communication Technology, Ministry of Education, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
Abstract：The user behavior of short video (such as viewing comments, likes, clicking on avatars, and forwarding) is predicted by considering the change of user interests. In this paper, the sorted user historical behavior sequence is introduced into word2vec as a corpus to train the word embedding model, learn the dynamic interests of users, and effectively capture the changes in user interests. The statistical features constructed by feature engineering and the user dynamic interest features constructed by the word embedding model are input into the multi task learning with multi gate mixture of experts (MMOE), and a new evaluation index W-uAUCis proposed to evaluate the prediction accuracy of the model. The experimental results show that compared with shared bottom, wide & deep and deepfm, the proposed MMOE model considering the change of user interest has the best prediction accuracy.
顾亦然, 徐泽彬, 杨海根. 基于多任务与用户兴趣变化的短视频用户行为预测算法[J]. 复杂系统与复杂性科学, 2023, 20(4): 69-76.
GU Yiran, XU Zebin, YANG Haigen. Short Video User Behavior Prediction Algorithm Based on Multi-task and User Interest. Complex Systems and Complexity Science, 2023, 20(4): 69-76.
[1] 周傲英,周敏奇,宫学庆.计算广告:以数据为核心的Web综合应用[J]. 计算机学报,2011,34(10):1805-1819. ZHOU A Y, ZHOU M Q, GONG X Q. Computational advertising: a data-centric comprehensive web application[J]. Chinese Journal of Computers, 2011,34(10):1805-1819. [2] TAO Z, WANG X, HE X, et al. Hoafm: a high-order attentive factorization machine for CTR prediction[J]. Information Processing & Management, 2020, 57(6): 102076. [3] CHENG H T, KOC L, HARMSEN J, et al. Wide & deep learning for recommender systems[C]//Proceedings of the 1st Workshop on Deep Learning for Recommender Systems.New York:ACM Press, 2016: 7-10. [4] GUO H F, TANG R M, YE Y M,et al. DeepFM: a factorization-machine based neural network for CTR prediction[C]//Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence.New York:ACM Press,2017:1725-1731. [5] RUDER S . An overview of multi-task learning in deep neural networks[DB/OL].[2022-01-15].https://arxiv.org/pdf/1706.05098.pdf. [6] WEI G Y, LEI J C, WEI Y M. News recommendation based on click-through rate prediction model[C]//10th International Conference on Logistics, Informatics and Service Sciences.Beijing, China: IEEE, 2022. [7] 朱思涵,浦剑.基于序列特征的点击率预测模型[J].华东师范大学学报(自然科学版),2020(4):134-146. ZHU S H, PU J, CTR prediction model based on sequence feature[J]. Journal of East China Normal University (Natural Sciences),2020(4):134-146. [8] 刘梦娟,曾贵川,岳威,等.基于融合结构的在线广告点击率预测模型[J].计算机学报,2019,42(7):1570-1587. LIU M J, ZENG G C, YUE W,et al. Online advertising ctr prediction model based on fusion structure[J]. Chinese Journal of Computers,2019,42 (7):1570-1587. [9] 许王昊,肖秦琨.基于注意力机制的兴趣网络点击率预估模型[J].计算机工程,2021,47(1):101-108. XU W H, XIAO Q K.Prediction model of interest Network click rate based on attention mechanism[J].Computer Engineering,2021,47 (1):101-108. [10] LI D, HU B, CHEN Q, et al. Attentive capsule network for click-through rate and conversion rate prediction in online advertising[J]. Knowledge-Based Systems, 2021(211): 106522. [11] FANG Y Y, CHEN Z H, MA Y X, et al. A network based on deep interest network for taobao click-through rate prediction[C]//2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering.Nanchang,China: IEEE, 2021: 978-981. [12] MA J, ZHAO Z, YI X, et al. Modeling task relationships in multi-task learning with multi-gate mixture-of-experts[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York:ACM Press,2018: 1930-1939. [13] MIKOLOV T, SUTSKEVER I, CHEN K, et al. Distributed representations of words and phrases and their compositionality[J]. Advances in neural information processing systems, 2013(1):311-3119. [14] MIKOLOV T, CHEN K, CORRADO G, et al. Efficient Estimation of Word Representations in Vector Space[DB/OL].[2022-01-15]. https://arxiv.org/pdf/1301.3781.pdf.
