Augmented Context-Based Conceptual User Modeling for Personalized Recommendation System in Online Social Networks

Augmented Context-Based Conceptual User Modeling for Personalized Recommendation System in Online Social Networks

Ammar Alnahhas (Faculty of Information Technology Engineering, Damascus University, Syria) and Bassel Alkhatib (Faculty of Information Technology Engineering, Damascus University, Syria)
DOI: 10.4018/978-1-7998-9020-1.ch027
OnDemand PDF Download:
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

As the data on the online social networks is getting larger, it is important to build personalized recommendation systems that recommend suitable content to users, there has been much research in this field that uses conceptual representations of text to match user models with best content. This article presents a novel method to build a user model that depends on conceptual representation of text by using ConceptNet concepts that exceed the named entities to include the common-sense meaning of words and phrases. The model includes the contextual information of concepts as well, the authors also show a novel method to exploit the semantic relations of the knowledge base to extend user models, the experiment shows that the proposed model and associated recommendation algorithms outperform all previous methods as a detailed comparison shows in this article.
Chapter Preview
Top

Building recommendation systems for online social networks has attracted many researchers in the last few years, a few researchers aimed at studying content recommendation, but many user modelling techniques are used in other researches aiming at link, news or 'who to follow' recommendations. We can classify the researches in three different categories:

  • 1.

    Collaborative filtering: Where items are recommended to a user by considering users with similar interests, or by considering similar items to items already user interested in;

  • 2.

    Statistical content based: Where users are modelled according to the textual content of their items, the content is processed statistically like in IR systems, and items are recommended if its content is similar to the user model;

  • 3.

    Semantic analysis of content: Where users are modelled according to the semantics extracted from textual contents of their interest, item are recommended if its content is semantically similar to the user model.

Complete Chapter List

Search this Book:
Reset