http://iet.metastore.ingenta.com
1887

Graph-based recommendations: from data representation to feature extraction and application

Graph-based recommendations: from data representation to feature extraction and application

For access to this article, please select a purchase option:

Buy chapter PDF
$16.00
(plus tax if applicable)
Buy Knowledge Pack
10 chapters for $120.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
Big Data Recommender Systems - Volume 2: Application Paradigms — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

Modeling users for the purpose of identifying their preferences and then personalizing services on the basis of these models is a complex task, primarily due to the need to take into consideration various explicit and implicit signals, missing or uncertain information, contextual aspects, and more. In this study, a novel generic approach for uncovering latent preference patterns from user data is proposed and evaluated. The approach relies on representing the data using graphs, and then systematically extracting graph-based features and using them to enrich the original user models. The extracted features encapsulate complex relationships between users, items, and metadata. The enhanced user models can then serve as an input to any recommendation algorithm. The proposed approach is domain-independent (demonstrated on data from movies, music, and business systems) and is evaluated using several state-of-the-art machine-learning methods, on different recommendation tasks, and using different evaluation metrics. Overall, the results show an unanimous improvement in the recommendation accuracy across tasks and domains.

Chapter Contents:

  • 21.1 Introduction
  • 21.2 Background and related work
  • 21.2.1 Graph-based recommender systems
  • 21.2.1.1 Similarity measurement using graphs and their application
  • 21.2.1.2 Representing social data and trust using graphs
  • 21.2.2 Feature engineering for recommendations
  • 21.3 Graph- based data modeling for recommendation systems
  • 21.3.1 The structure of a recommender system dataset
  • 21.3.2 Transforming tabular into graph-based representation
  • 21.3.2.1 Basic graph representation for recommender systems data
  • 21.3.2.2 Multiple subgraph representations
  • 21.3.3 Distilling graph features
  • 21.3.3.1 Distilled graph features
  • 21.4 Experimental setting and datasets
  • 21.4.1 Dataset I—Last. fm
  • 21.4.2 Dataset II—Yelp (from RecSys-2013)
  • 21.4.3 Dataset III—Yelp II (with social links)
  • 21.4.4 Dataset IV—Movielens
  • 21.4.5 Summary of the datasets, features, and metrics
  • 21.5 Results and analysis
  • 21.5.1 Case study I: overall contribution of the graph- based approach
  • 21.5.1.1 Dataset I—Last. fm results
  • 21.5.1.2 Dataset II—Yelp results
  • 21.5.1.3 Dataset III—Yelp II (with social links) results
  • 21.5.1.4 Dataset IV—Movielens results
  • 21.5.1.5 Performance across learning methods, datasets, and metrics
  • 21.5.2 Case study II: different graph schemes and their impact on recommendations
  • 21.5.2.1 Dataset I—Last. fm results
  • 21.5.2.2 Dataset II—Yelp results
  • 21.5.2.3 Dataset III—Yelp II (with social links) results
  • 21.5.2.4 Dataset IV—Movielens results
  • 21.5.2.5 Summary
  • 21.6 Discussion and conclusions
  • 21.6.1 Discussion
  • 21.6.1.1 Overfitting
  • 21.6.1.2 Scalability
  • 21.6.1.3 Initial transition to the graph model
  • 21.6.2 Conclusions and future work
  • References

Inspec keywords: feature extraction; graph theory; recommender systems; learning (artificial intelligence); data structures; data handling; user modelling; meta data

Other keywords: user models; graph-based feature extraction; evaluation metrics; latent preference patterns; data representation; graph-based recommendations; metadata; machine-learning methods; recommendation accuracy; recommendation algorithm; recommendation tasks; users modeling

Subjects: User interfaces; Data handling techniques; File organisation; Combinatorial mathematics; Knowledge engineering techniques; Information networks

Preview this chapter:
Zoom in
Zoomout

Graph-based recommendations: from data representation to feature extraction and application, Page 1 of 2

| /docserver/preview/fulltext/books/pc/pbpc035g/PBPC035G_ch21-1.gif /docserver/preview/fulltext/books/pc/pbpc035g/PBPC035G_ch21-2.gif

Related content

content/books/10.1049/pbpc035g_ch21
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address