Multimedia Documents Adaptation Based on Semantic Multi-Partite Social Context-Aware Networks

Introduction

Nowadays, technologies are getting smarter towards users’ constraints and preferences, finding a way to reach further points where the users’ satisfaction is always needed taking into consideration users profile description and context. As the world is becoming a little village, exchanging information between people is crucial, the adaptation process should satisfy the users searching document priorities by virtue of location, service constraint, service content, etc.

An important issue in multimedia documents’ exchanges and adaptations is the management of large amount of context information generated from several social networks and the complexity of the representation of the underlying social network. Usually, it is represented as a graph, where nodes stand for users and edges for the relation that connects them (Papadopoulos et al., 2012; Truong and al., 2016). However, more complex representations are often needed. Adaptation process should vary according to each profile context; this mechanism requires producing new relationships to generate additional information which is called inference, to determine correspondences between different social concepts known as alignment. Ontologies seem to be the best ways to represent advanced semantic relations among profiles as it has become one of the most important research directions especially with the advent of the Semantic Web. Moreover, they play a crucial role as they share a common understanding of the structure and the semantics of information and make the domain hypothesis explicit. Ontologies are at present in the heart of our work. Aiming to establish the semantic relations among multi-partite context-aware social networks and context-aware users’ profiles to offer a unified context quality service to its users and facilitates the sharing of users’ experiences through the use of recommendations and social networking services (e.g. Facebook, LinkedIn, Twitter) for on-the-fly (at runtime) adaptation of multimedia documents.

Recently, several adaptation platforms (Da et al., 2014; Gherari et al., 2014; Yus et al., 2014; Aguilar et al., 2015, Saighi et al., 2017) are intended to support many different services, such as to monitor, to analyze and display information to users. These platforms are based on context modeling and provide the means for identifying specific situations with specific profiles (i.e. services’ descriptions). However, developing an intelligent context-aware mobile application using current platforms is a cumbersome task. The reasons are the following: (i) – they provide several components for each specific service profile; If the user context evolves rapidly and the user mobility introduces a higher degree of heterogeneity and dynamicity, the system may be overloaded, (ii) – they based on various entities of different types that are involved in recommendation of relevant services, such as a user context profile, the tags that describe the media content, and a reference to any external multimedia content, (iii) – the efficient selection of services among a large set of candidates has been rarely addressed in research and (iv) - none of them provide intelligent management of users’ situations, i.e., it is not possible to compute all specific situations for a particular user profile and explores individually, each service description and computes matching distance in order to select the relevant services. They are highly dynamically changing, according to different contexts (user profile, user environment, monitoring, social activities, etc.).