An improved recommender based on hidden Markov model

Authors:
Jialing Li;Li Li;Yuheng Wu;Shangxiong Chen
Affiliations:
Institute of Logic and Intelligence, Faculty of Computer and Information Science, Southwest University, Chongqing, China;Institute of Logic and Intelligence, Faculty of Computer and Information Science, Southwest University, Chongqing, China;Institute of Logic and Intelligence, Faculty of Computer and Information Science, Southwest University, Chongqing, China;Institute of Logic and Intelligence, Faculty of Computer and Information Science, Southwest University, Chongqing, China
Venue:
PRICAI'12 Proceedings of the 12th Pacific Rim international conference on Trends in Artificial Intelligence
Year:
2012

Citing 4
Cited 0

Hybrid Recommender Systems: Survey and Experiments

User Modeling and User-Adapted Interaction
Eigentaste: A Constant Time Collaborative Filtering Algorithm

Information Retrieval
TOAST: a topic-oriented tag-based recommender system

WISE'11 Proceedings of the 12th international conference on Web information system engineering
Using time topic modeling for semantics-based dynamic research interest finding

Knowledge-Based Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In reality, users rarely dedicate excessive interest into only one topic over a long time. We propose a topic-based hidden Markov model to analyze temporal dynamics of users' preference. Experiments show that given observations of a new entrant, the proposed model is able to recommend a specific user group he/she can be classified into and also can anticipate what topic he/she will be mostly interested in.