Tag recommendations based on tensor dimensionality reduction

@inproceedings{Symeonidis2008TagRB,
  title={Tag recommendations based on tensor dimensionality reduction},
  author={Panagiotis Symeonidis and Alexandros Nanopoulos and Yannis Manolopoulos},
  booktitle={RecSys '08},
  year={2008}
}
Social tagging is the process by which many users add metadata in the form of keywords, to annotate and categorize information items (songs, pictures, web links, products etc.). Collaborative tagging systems recommend tags to users based on what tags other users have used for the same items, aiming to develop a common consensus about which tags best describe an item. However, they fail to provide appropriate tag recommendations, because: (i) users may have different interests for an information… 

Figures and Tables from this paper

Speeding up tensor based recommenders with clustered tag space and improving quality of recommendations with Non-negative tensor factorization
TLDR
This work proposes to reduce tag space by exploiting clustering techniques so that execution time is improved and memory requirements are decreased while preserving the quality of the recommendations, and incorporates the personal prior knowledge to increase the precision of tensor based recommenders.
Recommending posts in political blogs based on tensor dimensionality reduction
TLDR
Higher Order SingularValue Decomposition (HOSVD) is applied on a 3-dimensional tensor to find latent semantic relationships between the three types of entities that exist in a social blogging system: users, posts, and tags.
Hybrid tag recommendation for social annotation systems
TLDR
A weighted hybrid tag recommender that blends multiple recommendation components drawing separately on complementary dimensions is proposed that has the added benefits of being scalable to large real world applications, extensible to incorporate a wide range of recommendation techniques, easily updateable, and more scrutable than other leading methods.
Tag-Based Recommendation
  • T. Bogers
  • Computer Science
    Social Information Access
  • 2018
TLDR
This chapter provides an overview of the state-of-the-art approaches to tag-based item recommendation, organised by the class of recommendation algorithms that is augmented with tags, such as collaborative filtering, dimensionality reduction, graph-based recommendation, content-based filtering, machine learning, and hybrid recommendation.
Item Recommendation via Latent Topic Tag
TLDR
A hybrid method, using Latent Dirichlet Allocation to form the topic tag and using Higher-Order Singular Value Decomposition (HOSVD) to recommend items on user-tag-item tripartite graphs, which outperforms the traditional collaborative filtering (CF) algorithm and Topic-Sensitive PageRank system (TSPR) algorithm based on users' bipartite graphs.
Attention-Based Neural Tag Recommendation
TLDR
This paper proposes a personalized tag recommender system based on neural networks and attention mechanism that utilizes the multi-layer perceptron to model the non-linearities of interactions among users, items and tags.
Research on personalized recommendation algorithm combined with time factor
TLDR
This work proposes an algorithm based on tensor factorization and combined with time change for improving the current collaborative filtering algorithms, and shows improvements compare to collaborative filtering algorithm and HOSVD algorithm in F1-Measure with two real world datasets.
Language Models and Topic Models for Personalizing Tag Recommendation
  • Ralf Krestel, P. Fankhauser
  • Computer Science
    2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology
  • 2010
TLDR
This paper introduces an approach to personalized tag recommendation that combines a probabilistic model of tags from a resource with tags from the user, and significantly outperforms state-of-the-art approaches.
Tag Recommendation Using Probabilistic Topic Models
TLDR
This paper introduces an approach based on Latent Dirichlet Allocation (LDA) for recommending tags of resources and evaluates recall and precision for the bibsonomy benchmark provided within the ECML PKDD Discovery Challenge 2009.
Latent dirichlet allocation for tag recommendation
TLDR
This paper introduces an approach based on Latent Dirichlet Allocation (LDA) for recommending tags of resources in order to improve search and shows that the approach achieves significantly better precision and recall than the use of association rules.
...
...

References

SHOWING 1-10 OF 22 REFERENCES
Towards the Semantic Web: Collaborative Tag Suggestions
TLDR
This work defines a set of general criteria for a good tagging system and proposes a collaborative tag suggestion algorithm using these criteria to spot high-quality tags and employs a goodness measure for tags derived from collective user authorities to combat spam.
Tag Recommendations in Folksonomies
TLDR
This paper evaluates and compares two recommendation algorithms on large-scale real life datasets: an adaptation of user-based collaborative filtering and a graph-based recommender built on top of FolkRank, showing that both provide better results than non-personalized baseline methods.
CubeSVD: a novel approach to personalized Web search
TLDR
Experimental evaluations using a real-world data set collected from an MSN search engine show that CubeSVD achieves encouraging search results in comparison with some standard methods.
Tag-based social interest discovery
TLDR
An Internet Social Interest Discovery system, ISID, to discover the common user interests and cluster users and their saved URLs by different interest topics, and shows that ISID can effectively cluster similar documents by interest topics and discover user communities with common interests no matter if they have any online connections.
Evaluation of Item-Based Top-N Recommendation Algorithms
TLDR
The experimental evaluation on five different datasets show that the proposed item-based algorithms are up to 28 times faster than the traditional user-neighborhood based recommender systems and provide recommendations whose quality is up to 27% better.
The Structure of Collaborative Tagging Systems
TLDR
A dynamical model of collaborative tagging is presented that predicts regularities in user activity, tag frequencies, kinds of tags used, bursts of popularity in bookmarking and a remarkable stability in the relative proportions of tags within a given url.
Applying associative retrieval techniques to alleviate the sparsity problem in collaborative filtering
TLDR
This article proposes to deal with the sparsity problem by applying an associative retrieval framework and related spreading activation algorithms to explore transitive associations among consumers through their past transactions and feedback to solve the problem of sparse transactional data.
The Dynamics and Semantics of Collaborative Tagging
TLDR
Whether the distribution of tag frequencies stabilizes is investigated, which indicates a degree of cohesion or consensus among users about the optimal tags to describe particular sites, and a generative model of collaborative tagging is produced in order to model and understand some of the basic dynamics behind the process.
An Empirical Analysis of Design Choices in Neighborhood-Based Collaborative Filtering Algorithms
TLDR
An analysis framework is applied that divides the neighborhood-based prediction approach into three components and then examines variants of the key parameters in each component, and identifies the three components identified are similarity computation, neighbor selection, and rating combination.
Information retrieval using a singular value decomposition model of latent semantic structure
In a new method for automatic indexing and retrieval, implicit higher-order structure in the association of terms with documents is modeled to improve estimates of term-document association, and
...
...