Building user profiles in niche field based on web browsing behavior

被引：0
|
作者：
Zhang T. [1 ,2 ]
Weng K. [1 ]
Deng Y. [1 ]
Yang M. [1 ]
Zhang Y. [3 ]
机构：
[1] School of Information Management and Engineering, Shanghai University of Finance and Economics, Shanghai
[2] Shanghai Key Laboratory of Financial Information Technology (Shanghai University of Finance and Economics), Shanghai
[3] School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai
来源：
Xitong Gongcheng Lilun yu Shijian/System Engineering Theory and Practice | 2020年 / 40卷 / 03期
基金：
上海市自然科学基金; 中国国家自然科学基金;
关键词：
Profile generation algorithm; Profile optimization algorithm; Simi-ontology; User profile; Word vector;
D O I：
10.12011/1000-6788-2018-1742-12
中图分类号：
学科分类号：
摘要：
This paper mainly researches how to build users’ interest profile in niche field based on web browsing behavior. We present a method of building simi-ontology based on field text, and mine users’ interest from user’s web browsing behavior, finally generate a profile of users based on the domain interest. Then the user profile is applied to the personalized recommendation. This method solves the problem that it is difficult for niche field to accurately portray the user profile because of the small amount of users and the lack of information. This method is significantly different from other existing related research work in the following three aspects: 1) Based on domain text, the domain seim-ontology is generated quickly, and a user profile modeling method based on semi-ontology is constructed; 2) The word vector is used to map the web page to the semi-ontology, and the algorithm of creating the user profile is constructed; 3) Based on the similarity between domain concepts, a portrait optimization algorithm is presented. This paper carries out an empirical analysis with several indicators using the ticket sales data of the symphony orchestra and the user’s web browsing data. The results show that the model and algorithm for user profile proposed in this paper are valid and rational. © 2020, Editorial Board of Journal of Systems Engineering Society of China. All right reserved.
引用
收藏
页码：641 / 652
页数：11
相关论文
共 35 条
  • [1] Cai S.Q., Yuan Q., Zhou P., Et al., Collaborative filtering recommendation model in micro-blogging website based on information diffusion theory, Systems Engineering-Theory & Practice, 35, 5, pp. 1267-1275, (2015)
  • [2] Ren X.Y., Song M.N., Song J.D., Context-aware point-of-interest recommendation in location-based social networks, Chinese Journal of Computers, 40, 4, pp. 824-841, (2017)
  • [3] Dao T.H., Jeong S.R., Ahn H., A novel recommendation model of location-based advertising: Context-aware collaborative filtering using GA approach, Expert Systems with Applications, 39, 3, pp. 3731-3739, (2012)
  • [4] Kong X.X., Su B.C., Wang H.Z., Et al., Research on the modeling and related algorithms of label-weight rating based recommendation system, Chinese Journal of Computers, 40, 6, pp. 1440-1452, (2017)
  • [5] Zhu G.W., Zhou L., Hybrid recommendation based on forgetting curve and domain nearest neighbor, Journal of Management Sciences in China, 15, 5, pp. 55-64, (2012)
  • [6] Zhang Z., Liu Y., Xu G., Et al., A weighted adaptation method on learning user preference profile, Knowledge-Based Systems, 112, pp. 114-126, (2016)
  • [7] Zhou X., Wang W., Jin Q., Multi-dimensional attributes and measures for dynamical user profiling in social networking environments, Multimedia Tools & Applications, 74, 14, pp. 5015-5028, (2015)
  • [8] Vainio J., Holmberg K., Highly tweeted science articles: Who tweets them? An analysis of Twitter user profile descriptions, Scientometrics, 112, 1, pp. 345-366, (2017)
  • [9] Kosinski M., Bachrach Y., Kohli P., Et al., Manifestations of user personality in website choice and behaviour on online social networks, Machine Learning, 95, 3, pp. 357-380, (2014)
  • [10] Ikeda K., Hattori G., Ono C., Et al., Twitter user profiling based on text and community mining for market analysis, Knowledge-Based Systems, 51, 1, pp. 35-47, (2013)
1234