Modeling user preference dynamics with coupled tensor factorization for social media recommendation

Abstract

An essential problem in real-world recommender systems is that user preferences are not static and users are likely to change their preferences over time. Recent studies have shown that the modelling and capturing the dynamics of user preferences lead to significant improvements on recommendation accuracy and, consequently, user satisfaction. In this paper, we develop a framework to capture user preference dynamics in a personalized manner based on the fact that changes in user preferences can vary individually. We also consider the plausible assumption that older user activities should have less influence on a user’s current preferences. We introduce an individual time decay factor for each user according to the rate of his preference dynamics to weigh the past user preferences and decrease their importance gradually. We exploit users’ demographics as well as the extracted similarities among users over time, aiming to enhance the prior knowledge about user preference dynamics, in addition to the past weighted user preferences in a developed coupled tensor factorization technique to provide top-K recommendations. The experimental results on the two real social media datasets—Last.fm and Movielens—indicate that our proposed model is better and more robust than other competitive methods in terms of recommendation accuracy and is more capable of coping with problems such as cold-start and data sparsity.

Research on personalized user-centered product improvement based on sentiment mining of online reviews and competitor analysis

“…Secondly, this paper enriches the research on online review mining by designing sentiment analysis method based on word2vec technology and LSTM neural network, which is not only accurately applicable to specific product domain, but also can predict the sentiment tendency of product attributes that have not been evaluated in reviews. In addition, considering the heterogeneity of consumers preferences and needs (Tahmasbi et al, 2021;F. Wang et al, 2015), our study improves the traditional IPA method based on KANO theory and puts forward personalized product improvement strategies for different user groups.…”

“…Some studies have presented user preference models by constructing the ordering relation of candidate set (Qi et al, 2016), which is a qualitative method. In other studies, a series of linear or nonlinear methods are used to calculate the relative weight of each product attribute to quantitatively build the user preference model (Tahmasbi et al, 2021), which is a quantitative method.…”

“…These studies ignore the influence of competitive products on consumer behavior and satisfaction decision, greatly restricting the effectiveness and benefits of product improvement. Second, numerous studies have proved that user preferences are characterized by dynamics and diversity (Tahmasbi et al, 2021;F. Wang et al, 2015), that is, different users have various needs and evaluation criteria for the same product.…”

User Bias Drift Social Recommendation Algorithm based on Metric Learning

“…To solve the data sparsity and the cold start problems, social information is incorporated into the recommendation process, resulting in social recommendation algorithms [4][5]. For example, the recommendation algorithm based on matrix decomposition [6][7][8], the recommendation algorithm based on graph, the recommendation algorithm based on clustering [9], etc. Among them, the recommendation algorithm based on matrix decomposition is a popular algorithm in social recommendation because of its advantages such as being flexible, not easily affected by data sparsity, and good interpretability.…”

“…In Eq (7),. ud b represents the user's distance bias (User distance bias), od b represents the user's distance bias due to its own characteristics (Original distance bias ), and dd b indicates the drift of the distance bias due to the influence of friends (Distance bias drift).…”