Abstract
User tag suggestion technique, aiming at learning users’ preferences over knowledge products from their historical behaviors, plays an important role in generating personalized recommendation in online innovation community. However, most current user tagging solutions only utilize a single kind of behavior to predict a single tag for users, resulting in weak generalization of user profile. In this paper, we propose a multiple time series perceptive network (MTSPN) for user tagging tasks in online innovation community. In particular, MTSPN takes multiple kinds of user behaviors into consideration for collaborative perception purpose, in which multi-scale sequential features are extracted from different sequential behaviors, and a multi-label classification module is built-in the proposed MTSPN model to predict multiple tags for users. Our encouraging experimental results on a real-world dataset collected from “Thingiverse” community validate the superiority of the our MTSPN model over several existing user tagging methods.
Highlights
With the rapid increase of knowledge products in the online innovation community, the need for personalized recommendation is occurring more and more frequently
We propose a novel user tag suggestion scheme, termed multiple time series perceptive network (MTSPN), which predicts multi-tag for users by exploiting multiple kinds of user behaviors
We summarize the contributions of our work as follows: 1) Multi-behavior collaborative perception: MTSPN aims at learning multi-scale sequential features from multiple kinds of user behaviors, which can better perceive the diversity of users’ information need; 2) Multi-label prediction for user tagging: MTSPN can predict multiple tags for users, which is beneficial to describe the users’ multifaceted preference on knowledge products; 3) We construct a specialized dataset for the task of user tag suggestion in the scenario of online innovation community
Summary
With the rapid increase of knowledge products in the online innovation community, the need for personalized recommendation is occurring more and more frequently. We summarize the contributions of our work as follows: 1) Multi-behavior collaborative perception: MTSPN aims at learning multi-scale sequential features from multiple kinds of user behaviors, which can better perceive the diversity of users’ information need; 2) Multi-label prediction for user tagging: MTSPN can predict multiple tags for users, which is beneficial to describe the users’ multifaceted preference on knowledge products; 3) We construct a specialized dataset for the task of user tag suggestion in the scenario of online innovation community. Bi-LSTM [22] adds the reverse feature transfer operation, and combines the results of two directions as the final output features, which can enable the network to learn the correlation between user behavior information at different times more fully, so as to improve the performance of user tag suggestion. Where, N is the total number of training samples, C is the total number of knowledge product categories, Yjui denotes whether the i-th user is interested in the j-th product category, and the value is 0 or 1. σ (·) is the sigmoid function, σ Fjui is the output of the classifier Sj, which represents the preference probability of the i-th user to the j-th product category
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
