TY - JOUR
T1 - Modeling User Interests with Online Social Network Influence by Memory Augmented Sequence Learning
AU - Wang, Yu
AU - Piao, Chengzhe
AU - Liu, Chi Harold
AU - Zhou, Chijin
AU - Tang, Jian
N1 - Funding Information:
Manuscript received August 17, 2020; revised October 27, 2020; accepted December 12, 2020. Date of publication December 15, 2020; date of current version March 17, 2021. This work was supported by National Natural Science Foundation of China (No. 62022017). Recommended for acceptance by Dr. Shiwen Mao. (Corresponding author: Chi Harold Liu.) Yu Wang, Chengzhe Piao, Chi Harold Liu, and Chijin Zhou are with the School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China. (e-mail: 2656886245@qq.com; 363317018@qq.com; liuchi02@gmail.com; tlock.chijin@gmail.com). Jian Tang is with the AI Labs, DiDi Chuxing, Beijing 100193, China. (e-mail: tangjian@didiglobal.com). Digital Object Identifier 10.1109/TNSE.2020.3044964
Publisher Copyright:
© 2013 IEEE.
PY - 2021/1/1
Y1 - 2021/1/1
N2 - Online social networks, such as Facebook and Twitter, enable users to share their shopping/travel experiences with their friends. However the influence on users' decision-making on next visit/buy has sparse research exposure, by accurately modeling long-term user behaviors from historical data. The existing methods do not fully take advantage of the underlying social networks to model user interests, nor they have not modeled long-term transitional behavior patterns. In this paper, we propose a novel Social Influence aware and Memory augmented Sequence learning (SIMS) model, on what a user will likely buy/visit next. Specifically, SIMS first learns a representation for the visiting/purchasing sequence of each user using the sequence-to-sequence learning method. Then it predicts the interest of a user by integrating the representation of his/her own sequence, with another representation of the corresponding social influence, which is learned using an autoencoder-based model. In addition, we leverage an emerging memory augmented neural network, Differentiable Neural Computer (DNC), to further improve prediction accuracy. We conduct extensive experiments to evaluate the proposed model using three real-world datasets, Yelp, Epinions and Ciao. When compared with 10 other baselines and state-of-the-art solutions, the experimental results show that 1) the proposed model significantly outperforms all other methods in terms of various accuracy-related metrics; 2) the proposed social influence modeling and memory augmentation do lead to the performance gain.
AB - Online social networks, such as Facebook and Twitter, enable users to share their shopping/travel experiences with their friends. However the influence on users' decision-making on next visit/buy has sparse research exposure, by accurately modeling long-term user behaviors from historical data. The existing methods do not fully take advantage of the underlying social networks to model user interests, nor they have not modeled long-term transitional behavior patterns. In this paper, we propose a novel Social Influence aware and Memory augmented Sequence learning (SIMS) model, on what a user will likely buy/visit next. Specifically, SIMS first learns a representation for the visiting/purchasing sequence of each user using the sequence-to-sequence learning method. Then it predicts the interest of a user by integrating the representation of his/her own sequence, with another representation of the corresponding social influence, which is learned using an autoencoder-based model. In addition, we leverage an emerging memory augmented neural network, Differentiable Neural Computer (DNC), to further improve prediction accuracy. We conduct extensive experiments to evaluate the proposed model using three real-world datasets, Yelp, Epinions and Ciao. When compared with 10 other baselines and state-of-the-art solutions, the experimental results show that 1) the proposed model significantly outperforms all other methods in terms of various accuracy-related metrics; 2) the proposed social influence modeling and memory augmentation do lead to the performance gain.
KW - Memory augmented network
KW - online social network influence
KW - user interests modeling
UR - http://www.scopus.com/inward/record.url?scp=85098755877&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85098755877&partnerID=8YFLogxK
U2 - 10.1109/TNSE.2020.3044964
DO - 10.1109/TNSE.2020.3044964
M3 - Article
AN - SCOPUS:85098755877
SN - 2327-4697
VL - 8
SP - 541
EP - 554
JO - IEEE Transactions on Network Science and Engineering
JF - IEEE Transactions on Network Science and Engineering
IS - 1
M1 - 9294053
ER -