TY - JOUR
T1 - DualTaxoVec
T2 - Web user embedding and taxonomy generation
AU - Zhao, Qinpei
AU - Fan, Lingjun
AU - Zhang, Yinjia
AU - Li, Jiangfeng
AU - Shi, Yang
AU - Rao, Weixiong
AU - Liu, Xiang
N1 - Funding Information:
This work is partially supported by National Key Research and Development Program of China ( 2021YFC3340601 , 2021YFE204500 ), National Natural Science Foundation of China (Grant No. 61972286 , 62172301 and 61772371 ), the Shanghai Municipal Science and Technology Major Project, China ( 2021SHZDZX0100 ), the Science and Technology Program of Shanghai, China (Grant No. 20ZR1460500 , 22511104300 ), the Fundamental Research Funds for the Central Universities, China under Grant No. 22120210545 and the CCF-NSFOCUS Kunpeng Fund, S&T Program of Hebei, China (Grant No. 21550101K ).
Publisher Copyright:
© 2023
PY - 2023/7/8
Y1 - 2023/7/8
N2 - Learning web user embedding based on interaction data in the context of taxonomy is a way of studying the correlation between two web users. Such user embedding is important for further user analysis. Interaction data is made up of users and the items they interact within a domain, which is a group of entities with a basic common property. Usually a taxonomy of these items that users interact with is a hierarchical category structure for a domain. However, the taxonomy is not totally suitable for a particular task. To solve this problem, we propose a dual-way method DualTaxoVec, which learns the user embedding based on the taxonomy of the user interaction items. Meanwhile, it automatically constructs the taxonomy for the items that adapts the domain of users. It is composed of user–item and item–user tracks to construct the taxonomy and embed users in a dual-way. According to the experimental results, the validity and effectiveness of the DualTaxoVec has been demonstrated.
AB - Learning web user embedding based on interaction data in the context of taxonomy is a way of studying the correlation between two web users. Such user embedding is important for further user analysis. Interaction data is made up of users and the items they interact within a domain, which is a group of entities with a basic common property. Usually a taxonomy of these items that users interact with is a hierarchical category structure for a domain. However, the taxonomy is not totally suitable for a particular task. To solve this problem, we propose a dual-way method DualTaxoVec, which learns the user embedding based on the taxonomy of the user interaction items. Meanwhile, it automatically constructs the taxonomy for the items that adapts the domain of users. It is composed of user–item and item–user tracks to construct the taxonomy and embed users in a dual-way. According to the experimental results, the validity and effectiveness of the DualTaxoVec has been demonstrated.
KW - Clustering
KW - Taxonomy
KW - User embedding
KW - User interaction data
UR - http://www.scopus.com/inward/record.url?scp=85153686056&partnerID=8YFLogxK
U2 - 10.1016/j.knosys.2023.110565
DO - 10.1016/j.knosys.2023.110565
M3 - Article
AN - SCOPUS:85153686056
SN - 0950-7051
VL - 271
JO - Knowledge-Based Systems
JF - Knowledge-Based Systems
M1 - 110565
ER -