Preference dynamics with multimodal user-item interactions in social media recommendation

Rafailidis, Dimitrios; Kefalas, Pavlos; Manolopoulos, Yannis

doi:10.1016/j.eswa.2017.01.005

Cited by 57 publications

(33 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another approach is micro profiling (Baltrunas & Amatriain, 2009), in which user data is divided into small time-frames (e.g., a day, month or season), in order to capture patterns of user behavior during such time spans. A potential concern is that preference dynamics may occur both in preference data as well as in auxiliary user-item interaction data (e.g., comments) and do not necessarily evolve in the same way, therefore, benefit from being captured separately (Rafailidis et al, 2017).…”

Section: Domain Characteristicsmentioning

confidence: 99%

The recommender canvas: A model for developing and documenting recommender system design

Capelleveen

Amrit

Yazan

et al. 2019

Expert Systems with Applications

View full text Add to dashboard Cite

The task of designing a recommender system is a complex process. Because of the many technological advancements that may be included in a recommender system, engineers are faced with a fast growing number of design related decisions to be taken. Unfortunately, there is no general approach yet for decision makers that can act as a framework guiding the design of a recommender system. The rich collection of literature on recommender systems, though, offers a great source to identify the key areas where these decisions need to be taken. In this paper, we survey existing literature with the aim of building a recommender system model inspired by Osterwalder's canvas theory. The result of our semi-structured synthesis is a novel design approach in the form of a canvas for designing recommender systems. This work provides a better understanding and can serve as a guide for decision making in recommender system design.

show abstract

Section: Domain Characteristicsmentioning

confidence: 99%

The recommender canvas: A model for developing and documenting recommender system design

Capelleveen

Amrit

Yazan

et al. 2019

Expert Systems with Applications

View full text Add to dashboard Cite

show abstract

“…Similarly, [20] presented the Tensor Factorization and Tag Clustering Model (TCM) for recommendations in social tagging systems in which content information is processed to find tags among comparable items, then the tag clusters are formed and finally, association among users, items, and topics are discovered by working upon the Tensor Factorization technique, i.e. Higher Order Singular Value Decomposition (HOSVD).…”

Section: Theoretical Reviewmentioning

confidence: 99%

“…In the study, the Higher Order Singular Value Decomposition (HOSVD) Model is used to factor the tensors in matrices obtained from the qualification matrix. The main benefit of using HOSVD is to address the high dimensionality of the data in an effective way [14] and [20], which helps to discover the relationship between users, the qualifications, and other contextual dimensions such as age, gender, and academic term.…”

Section: Decomposition Of the Singular Value Of Higher Ordermentioning

confidence: 99%

Multi-dimension Tensor Factorization Collaborative Filtering Recommendation for Academic Profiles

Silva

Varela

Lezama

et al. 2019

Advances in Neural Networks – ISNN 2019

View full text Add to dashboard Cite

The choice of academic itineraries and/or optional subjects to attend is not usually an easy decision since, in most cases, students lack the information, maturity, and knowledge required to make right decisions. This paper evaluates the support of Collaborative Systems for helping and guiding students in this decision-making process, considering the behavior and impact of these systems on the use of data different from the formal information the students usually use. For this purpose, the research applied the clustering based Multi-Dimension Tensor Factorization approach to build a recommendation system and confirm that the increment in tensors improves the recommendation accuracy. As a result, this approach permits the user to take advantage of the contextual information to reduce the sparsity issue and increase the recommendation accuracy.

show abstract

“…There are a few approaches that have handled user preference drift and other subproblems, such as data sparsity [29], [30], [42], [55]. Recently, OCF-DR [29] use neighborhood factor to track the drift of users' preference.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, OCF-DR [29] use neighborhood factor to track the drift of users' preference. TCMC [42] was proposed by combining multimodal information with scores to reduce data sparsity, but this model also considered multimodal data that did not uncover the hidden topic factor from reviews to explain the score on each time step.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Collaborative Filtering Based on User Preference Drift and Topic Evolution

Wangwatcharakul

Wongthanavasu

2020

IEEE Access

View full text Add to dashboard Cite

Recommender systems are efficient tools for online applications; these systems exploit historical user ratings on items to make recommendations of items to users. This paper aims to enhance dynamic collaborative filtering on recommender systems under volatile conditions in which both users' preferences and item properties dynamically change over time. Moreover, existing collaborative filtering models mainly rely on solving data sparsity by adding side information to improve performance. We propose a model to capture the user preference dynamics in the rating matrix by using a joint decomposition method to extract user latent transition patterns and combine latent factors together with the associated topic evolution of review texts by using topic modeling based on the dynamic environment. We evaluate the accuracy on real datasets, and the experimental results show that the model leads to a significant improvement compared with the state-of-the-art dynamic CF models.

show abstract

Preference dynamics with multimodal user-item interactions in social media recommendation

Cited by 57 publications

References 9 publications

The recommender canvas: A model for developing and documenting recommender system design

The recommender canvas: A model for developing and documenting recommender system design

Multi-dimension Tensor Factorization Collaborative Filtering Recommendation for Academic Profiles

Dynamic Collaborative Filtering Based on User Preference Drift and Topic Evolution

Contact Info

Product

Resources

About