smart.lab.tunisia@gmail.com +216 71 588 443
Connexion

Recommandation Systems

Description

Aucune description disponible pour cet axe de recherche.

Membres

Rahma Dhaouadi Rahma Dhaouadi
Manel Kridis Manel Kridis
Ibtissem Ben Ouhiba Ibtissem Ben Ouhiba

Publications

  • 2025
    Haithem Mezni, Mokhtar Sellami, Abeer Algarni, Hela Elmannai

    CrossRecSmart: A Cross-Network Anchor-Based Representation Learning for the Recommendation of Smart Services.

    Journal of Supercomputing, 2025

    Résumé

    In modern smart cities, user request handling has evolved beyond conventional software solutions and electronic services. Companies now leverage a diverse range of cutting-edge technologies, such as Artificial Intelligence, the Internet of Things (IoT), Edge/Fog computing, and Cloud computing, to deliver various smart services. These services cover domains such as smart healthcare, smart buildings, smart transportation, smart living, and smart administration. However, a significant challenge hindering the widespread adoption and effective deployment of these services is the limited awareness among citizens of their availability and features, including aspects like pricing models, security policies, and service-level agreements. This issue largely stems from the lack of centralized public repositories where companies can showcase their smart offerings. Consequently, citizens often rely on traditional Web search tools (e.g., search engines, social networks), which limits their ability to fully benefit from the advantages of smart services. In addition, users are often connected to multiple service providers, meaning that their related knowledge (e.g., profiles, service usage, ratings) is distributed across multiple information sources.
    To bridge the gap between smart service providers and citizens, and to effectively utilize user and service information across multiple networks, we propose CrossRecSmart, a cross-network recommender system built upon a multiplex network of smart services. This system can be conceptualized as a large-scale, distributed, domain-specific marketplace for available smart services. Our approach integrates Graph Neural Networks (GNNs) with cross-network representation learning to construct this multiplex network. The complex and distributed nature of this task is addressed through a cross-network learning model that facilitates collaboration among multiple smart service providers and enables the aggregation of their knowledge. This is achieved by interconnecting multiple networks through bridge nodes, also referred to as anchor entities. Furthermore, we introduce an algorithm for the cross-network recommendation of top-rated smart services. Comparative analyses with existing recommender systems designed for smart cities demonstrate the superiority of our proposed approach, owing to the concept of anchor links.

  • Haithem Mezni, Mokhtar Sellami, Amal Al-Rasheed, Hela Elmannai

    Cross-network service recommendation in smart cities

    Concurrency and Computation: Practice and Experience, 2024

    Résumé

    Nowadays, Internet of Things, artificial intelligence, cloud computing, and other revolutionary technologies (e.g., edge and fog computing) have become the pillar of smart cities. These latter make users' lives easier, thanks to a wide variety of smart services offered in different dimensions (e.g., smart living, smart mobility, smart economy, smart governance). However, the rapid adoption of smart services by users and the full servicelization of several cities around the world is faced with two major issues: the lack of knowledge regarding smart services' capacities (e.g., features, contextual requirements, pricing models, privacy policies, provisioning terms, etc.), and the lack of unified rating and quantification of smart services' QoS behavior. Indeed, interested users often exploit traditional search tools (e.g., Web search engines, social networks) to find and rate the needed services. This behavior has scattered the smart services' usage data (e.g., users contexts, ratings) across multiple providers platforms, which makes the search task beyond the capacity of users and, even, other service providers. Although recommender systems are a natural solution to exempt users from exploring the huge space of the offered smart services, current recommendation approaches for smart city environments are unable to deliver correct recommendations. In fact, they have been initially designed to single-network settings (a single service repository), while smart services' consumers often are involved in multiple provider platforms. To the best of our knowledge, there exists no approach that treated smart service recommendation across multiple information networks. Therefore, the goal of this paper is to propose a cross-network recommender system for smart cities. We first model the multiplex network of smart services' providers as a multirelational fuzzy lattice family thanks to fuzzy relational concept analysis (fuzzy RCA), which is a powerful mathematical method for data analysis and clustering. We also use the concept of anchor users to connect providers networks via the users involved in more than one provider platform. Guided by anchors' cross-network relations, we compute the similarity between users and we define algorithms for exploring the smart services' information network, i.e. lattice family. Extensive experiments have proved the effectiveness of cross-network recommendation and the quality of produced recommendations, compared to state-of-the-art single-network recommendation.

  • Haithem Mezni

    Temporal Knowledge Graph Embedding for Effective Service Recommendation

    IEEE Transactions on Services Computing, 2022

    Résumé

    Over the last decade, service selection and recommendation had been two strongly related service filtering steps. While service selection aims to filter the best available services according to QoS and contextual criteria, service recommendation refines the selection results by taking into account additional criteria, such as users feedbacks and ratings, similarities between users tastes, etc. However, the ever changing services environment, users tastes, as well as the perception and popularity of available services, rise a question regarding the appropriate means to capture and analyze such changes over time. Most service recommendation solutions are static and do not offer a multi-relational modeling of user-service interactions over time. Time is a contextual dimension that has, recently, received a lot of attention, leading to a new class of recommender systems, called time-aware recommender systems. In this work, we propose a service recommendation method that takes advantage of temporal knowledge graphs. As a de facto standard to model multiple and complex interactions between heterogeneous entities, knowledge graphs will serve as a historical knowledge base for our TASR system. We, first, model the user-service interactions over time, by constructing a temporal service knowledge graph (TSKG) that will be later enriched through a completion step. Second, to explore the TSKG and extract top-rated services, we use Convolutional Neural Networks (CNN) to embed the TSKG into a low-dimensional vector space, facilitating then its mining. Experimental studies have proven the effectiveness and accuracy of our approach, compared to traditional TASR methods and time-unaware KG-based recommendation.

  • Haithem Mezni, Djamal Benslimane, Ladjel Bellatreche

    Context-Aware Service Recommendation Based on Knowledge Graph Embedding

    IEEE Transactions on Knowledge and Data Engineering, 2021

    Résumé

    Over two decades, context awareness has been incorporated into recommender systems in order to provide, not only the top-rated items to consumers but also the ones that are suitable to the user context. As a class of context-aware systems, context-aware service recommendation (CASR) aims to bind high-quality services to users, while taking into account their context requirements, including invocation time, location, social profiles, connectivity, and so on. However, current CASR approaches are not scalable with the huge amount of service data (QoS and context information, users reviews and feedbacks). In addition, they lack a rich representation of contextual information, as they adopt a simple matrix view. Moreover, current CASR approaches adopt the traditional user-service relation and they do not allow for multi-relational interactions between users and services in different contexts. To offer a scalable and context-sensitive service recommendation with great analysis and learning capabilities, we provide a rich and multi-relational representation of the CASR knowledge, based on the concept of knowledge graph. The constructed context-aware service knowledge graph (C-SKG) is, then, transformed into a low-dimensional vector space to facilitate its processing. For this purpose, we adopt Dilated Recurrent Neural Networks to propose a context-aware knowledge graph embedding, based on the principles of first-order and subgraph-aware proximity. Finally, a recommendation algorithm is defined to deliver the top-rated services according to the target user's context. Experiments have proved the accuracy and scalability of our solution, compared to state-of-the-art CASR approaches.

    Haithem Mezni, Djamal benslimane, Ladjel Bellatreche

    Context-Aware Service Recommendation Based on Knowledge Graph Embedding

    International Conference on Data and Knowledge Engineering, 2021

    Résumé

    Over two decades, context awareness has been incorporated into recommender systems in order to provide, not only the top-rated items to consumers but also the ones that are suitable to the user context. As a class of context-aware systems, context-aware service recommendation (CASR) aims to bind high-quality services to users, while taking into account their context requirements, including invocation time, location, social profiles, connectivity, and so on. However, current CASR approaches are not scalable with the huge amount of service data (QoS and context information, users reviews and feedbacks). In addition, they lack a rich representation of contextual information, as they adopt a simple matrix view. Moreover, current CASR approaches adopt the traditional user-service relation and they do not allow for multi-relational interactions between users and services in different contexts. To offer a scalable and context-sensitive service recommendation with great analysis and learning capabilities, we provide a rich and multi-relational representation of the CASR knowledge, based on the concept of knowledge graph. The constructed context-aware service knowledge graph (C-SKG) is, then, transformed into a low-dimensional vector space to facilitate its processing. For this purpose, we adopt Dilated Recurrent Neural Networks to propose a context-aware knowledge graph embedding, based on the principles of first-order and subgraph-aware proximity. Finally, a recommendation algorithm is defined to deliver the top-rated services according to the target user's context. Experiments have proved the accuracy and scalability of our solution, compared to state-of-the-art CASR approaches.

  • Mayssa Fayala, Haithem Mezni

    Web service recommendation based on time-aware users clustering and multi-valued QoS prediction

    Concurrency and Computation: Practice and Experience, 2019

    Résumé

    With the growing number of functionally similar services over the Internet, recommendation techniques become a natural choice to cope with the challenging task of optimal service selection, and to help consumers satisfy their needs and preferences. However, most existing models on service recommendation are static, while in the real world, the perception and popularity of Web services may continually change. Time is becoming an increasingly important factor in recommender systems since time effects influence users' preferences to a large extent. In order to help users with this problem, we propose a time-aware Web service recommendation system. First, we use K-means clustering method in order to exclude the less similar users, which share few common Web services with the active user at different times. Slope One algorithm is also adopted in order to deal with data sparsity problem by predicting the missing ratings over time. Then, a recommendation algorithm is presented in order to recommend the top-rated Web services. Experiments proved the accuracy of our approach compared to five existing solutions.

  • Haithem Mezni, Sofiane Ait Arab, Djamal Benslimane, Karim Benouaret

    An evolutionary clustering approach based on temporal aspects for context-aware service recommendation

    Journal of Ambient Intelligence and Humanized Computing, 2018

    Résumé

    Over the last years, recommendation techniques have emerged to cope with the challenging task of optimal service selection, and to help consumers satisfy their needs and preferences. However, most existing models on service recommendation only consider the traditional user-service relation, while in the real world, the perception and popularity of Web services may depend on several conditions including temporal, spatial and social constraints. Such additional factors in recommender systems influence users’ preferences to a large extent. In this paper, we propose a context-aware Web service recommendation approach with a specific focus on time dimension. First, K-means clustering method is hybridized with a multi-population variant of the well-known Particle Swarm Optimization (PSO) in order to exclude the less similar users which share few common Web services with the active user in specific contexts. Slope One method is, then, applied to predict the missing ratings in the current context of user. Finally, a recommendation algorithm is proposed in order to return the top-rated services. Experimental studies confirmed the accuracy of our recommendation approach when compared to three existing solutions.

    Haithem Mezni, Tarek Abdeljaouad

    A cloud services recommendation system based on Fuzzy Formal Concept Analysis

    Data & Knowledge Engineering, 2018

    Résumé

    Cloud computing is an attractive paradigm which offers variant services on demand. Many available cloud services offer the same or similar functionalities, which made it challenging for cloud users to choose a suitable service that meets with their preferences. Existing service selection approaches were not enough to solve this challenge. That's why researchers went for recommendation approaches trying to find a solution. Cloud service recommendation has become an important technique for cloud services. It helps users decide whether a service satisfies their requirements or not. However, two main recommendation problems remain unsolved yet, data sparsity and cold start. In addition, existing solutions mostly tried to adapt techniques inherited from Web service and e-commerce domains. This approach is not always adequate due to many reasons such as the cloud architecture, the various service models, etc. To address the problems stated above, we propose a Collaborative Filtering based recommendation system for cloud services using Fuzzy Formal Concept Analysis (Fuzzy FCA). Fuzzy FCA has a solid mathematical foundation and it's based on the lattice theory. The lattice representation will give an explicit description of our cloud environment (users, services, ratings, etc.) and, then, extract the pertinent information from it (similar users to an active user, ratings of each similar user, top services, etc.) which will make the recommendations more suitable. Experimental results confirmed our expectations and proved the efficiency of such an approach.

    Haithem Mezni, Mayssa Fayala

    Time-aware service recommendation: Taxonomy, review, and challenges

    Software: Practice and Experience, 2018

    Résumé

    Nowadays, a huge number of available Web services offer the same functionalities and a high quality of service, which makes the selection of suitable services a difficult task. In such situation, the services must be differentiated by additional criteria such as users' ratings. To meet this goal, recommendation techniques become a natural choice to cope with the challenging task of optimal service selection and to help consumers satisfy their needs and preferences. However, most existing models on service recommendation are static, whereas in the real world, the perception and popularity of Web services may continually change, and users' preferences and habits also shift frequently. Time is becoming an increasingly important factor in recommender systems, since time effects influence users' preferences to a large extent. In addition, quality-of-service performance of Web services is strongly linked to the service status and network environments, which are variable against time. Recently, a wide range of service recommendation approaches, dealing with the time dimension in user modeling and recommendation strategies, have been proposed. Thus, the purpose of this survey is to present a comprehensive study and analysis of the state-of-the-art on time-aware service recommendation. We identify the techniques used in recommender systems to provide the best services. Moreover, we present a classification of time-aware recommender systems based on the target recommendation time, the type of relationship between users, and the type of feedback. Besides, we present a comparison between time-aware recommendation approaches, and we discuss their advantages and disadvantages. Finally, challenges and requirements of time-aware service recommendation as well as the future directions are identified according to the studied approaches.

  • Haithem Mezni

    A Multi-Recommenders System for Service Provisioning in Multi-Cloud Environment

    28th International Workshop on Database and Expert Systems Applications (DEXA), 2017

    Résumé

    Cloud service recommendation has become an important technique that helps users decide whether a service satisfies their requirements or not. However, the few existing recommendation systems are not suitable for real world environments and only deal with services hosted in a single cloud, which is simply unrealistic. In addition, a same service may be hosted on more than one cloud and, hence, may have different user ratings that depend on specific conditions of their cloud availability zones. This uncertainty regarding the real quality of the cloud service and users' satisfaction levels raises a question about how to trust the different users' ratings in order to recommend the adequate cloud service. Unlike existing solutions, the goal of this work is to propose a cooperative recommender system that aims to resolve two major issues: recommendation of cloud services in multiple clouds and recommendation under uncertainty of users' ratings. The proposed system will take advantage from a set of powerful techniques and paradigms in order to offer an overlay of cloud recommender entities that cooperate to deliver top-rated services to the user.