Daily-Aware Personalized Recommendation based on Feature-Level Time Series Analysis

Zhang, Yongfeng; Zhang, Min; Zhang, Yi; Lai, Guokun; Liu, Yiqun; Zhang, Honghui; Ma, Shaoping

doi:10.1145/2736277.2741087

Cited by 59 publications

(24 citation statements)

References 40 publications

(63 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Products' features and users' opinions are extracted with phrase-level sentiment analysis from users' reviews to feed a matrix factorization framework. After that, a few improvements to EFM have been proposed to deal with temporal dynamics [48] and to use tensor factorization [9]. In particular, in the latter the aim is to predict both user preferences on features (extracted from textual reviews) and items.…”

Section: Related Workmentioning

confidence: 99%

How to Make Latent Factors Interpretable by Feeding Factorization Machines with Knowledge Graphs

Anelli

Noia

Sciascio

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Model-based approaches to recommendation can recommend items with a very high level of accuracy. Unfortunately, even when the model embeds content-based information, if we move to a latent space we miss references to the actual semantics of recommended items. Consequently, this makes non-trivial the interpretation of a recommendation process. In this paper, we show how to initialize latent factors in Factorization Machines by using semantic features coming from a knowledge graph in order to train an interpretable model. With our model, semantic features are injected into the learning process to retain the original informativeness of the items available in the dataset. The accuracy and effectiveness of the trained model have been tested using two well-known recommender systems datasets. By relying on the information encoded in the original knowledge graph, we have also evaluated the semantic accuracy and robustness for the knowledge-aware interpretability of the final model.

show abstract

Section: Related Workmentioning

confidence: 99%

How to Make Latent Factors Interpretable by Feeding Factorization Machines with Knowledge Graphs

Anelli

Noia

Sciascio

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Zhang et al [19] maked use of the large volume of textual reviews for the automatic extraction of domain knowledge and proposed a daily-aware personalized recommendation based on feature-level time series analysis. But it differs from ours work as they treated all reviews of a day as a whole to analyze the trend of product feature while we attempt to correlate each review with the related rating score to model changing of user tastes and item properties.…”

Section: Background and Related Workmentioning

confidence: 99%

“…The influence of those changes is global. In addition, the change can be different from person to person based on their circumstances or experience, so treating the historical decisions of a user or the received comments of an item as static, or long-term influential information sources is inappropriate [19], and it is necessary and important to model temporal dynamics at the level of each individual.…”

Section: Introductionmentioning

confidence: 99%

A Novel Recommendation Algorithm Incorporating Temporal Dynamics, Reviews and Item Correlation

Feng

Sang

et al. 2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARY Recommender systems (RS) exploit user ratings on items and side information to make personalized recommendations. In order to recommend the right products to users, RS must accurately model the implicit preferences of each user and the properties of each product. In reality, both user preferences and item properties are changing dynamically over time, so treating the historical decisions of a user or the received comments of an item as static is inappropriate. Besides, the review text accompanied with a rating score can help us to understand why a user likes or dislikes an item, so temporal dynamics and text information in reviews are important side information for recommender systems. Moreover, compared with the large number of available items, the number of items a user can buy is very limited, which is called the sparsity problem. In order to solve this problem, utilizing item correlation provides a promising solution. Although famous methods like TimeSVD++, TopicMF and CoFactor partially take temporal dynamics, reviews and correlation into consideration, none of them combine these information together for accurate recommendation. Therefore, in this paper we propose a novel combined model called TmRevCo which is based on matrix factorization. Our model combines the dynamic user factor of TimeSVD++ with the hidden topic of each review text mined by the topic model of TopicMF through a new transformation function. Meanwhile, to support our five-scoring datasets, we use a more appropriate item correlation measure in CoFactor and associate the item factors of CoFactor with that of matrix factorization. Our model comprehensively combines the temporal dynamics, review information and item correlation simultaneously. Experimental results on three real-world datasets show that our proposed model leads to significant improvement compared with the baseline methods.

show abstract

“…There has been a large body of research studying personalization for recommendation [35], search [29,32] and advertising [11]. Most of the research are based on matrix factorization (MF) [15] or neighborhood methods [17].…”

Section: Introductionmentioning

confidence: 99%

Perceive Your Users in Depth

Liu

et al. 2018

Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

Tasks such as search and recommendation have become increasingly important for E-commerce to deal with the information overload problem. To meet the diverse needs of different users, personalization plays an important role. In many large portals such as Taobao and Amazon, there are a bunch of different types of search and recommendation tasks operating simultaneously for personalization. However, most of current techniques address each task separately. This is suboptimal as no information about users shared across different tasks.In this work, we propose to learn universal user representations across multiple tasks for more effective personalization. In particular, user behavior sequences (e.g., click, bookmark or purchase of products) are modeled by LSTM and attention mechanism by integrating all the corresponding content, behavior and temporal information. User representations are shared and learned in an end-to-end setting across multiple tasks. Benefiting from better information utilization of multiple tasks, the user representations are more effective to reflect their interests and are more general to be transferred to new tasks. We refer this work as Deep User Perception Network (DUPN) and conduct an extensive set of offline and online experiments. Across all tested five different tasks, our DUPN consistently achieves better results by giving more effective user representations. Moreover, we deploy DUPN in large scale operational tasks in Taobao. Detailed implementations, e.g., incremental model updating, are also provided to address the practical issues for the real world applications.

show abstract

Daily-Aware Personalized Recommendation based on Feature-Level Time Series Analysis

Cited by 59 publications

References 40 publications

How to Make Latent Factors Interpretable by Feeding Factorization Machines with Knowledge Graphs

How to Make Latent Factors Interpretable by Feeding Factorization Machines with Knowledge Graphs

A Novel Recommendation Algorithm Incorporating Temporal Dynamics, Reviews and Item Correlation

Perceive Your Users in Depth

Contact Info

Product

Resources

About