Nassim Dennouni
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Nassim Dennouni has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Ahmed Harbouche
Hassiba Benbouali University, Chlef, Algeria
1 shared publication - Amina Azzaz
EEDIS Laboratory, Djillali Liabes University at Sidi Bel Abbes, Sidi Bel Abbès, Algeria
1 shared publication - Djelloul Bettache
Hassiba Benbouali University
1 shared publication - Luigi Lancieri
France Télécom R&D, France
1 shared publication - Mimoun Malki
Ecole Supérieure en Informatique de Sidi Bel-Abbes
1 shared publication - Mourad Loukam
Hassiba Benbouali University of Chlef
1 shared publication
Latest Publications
- Open Access
- 4 June 2025
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 15 (3) , 23629-23634
Improving POI Recommendation through Collaborative Filtering by incorporating the Geographical Factor into the Similarity Calculation
In recent years, the popularity of Location-Based Social Networks (LBSNs) has surged among tourists seeking to share their travel experiences with their social circles. Although these platforms generate vast amounts of data, effectively utilizing this information to provide personalized recommendations poses significant challenges. Point-Of-Interest (POI) recommendation systems have emerged as a promising solution, leveraging data from LBSNs to suggest tailored destinations for tourists. Collaborative Filtering (CF) has gained recognition as a widely adopted memory-based technique. By analyzing user similarities, CF often uses similarity metrics to predict the likelihood of tourists visiting specific POIs. This study introduces a novel method, called IUPJS (Incorporation of User Proximity in Jaccard Similarity), which extends the traditional Jaccard index by integrating geographic proximity into the similarity calculation. Experimental evaluations on a Foursquare data set indicate that the proposed IUPJS significantly enhances the effectiveness of the recommendation system. This improvement is particularly evident in key evaluation metrics, including precision, recall, F1-score, mAP, and NDCG, exceeding the performance of traditional methods commonly employed in the literature.
- 4 June 2025
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 15 (3) , 23629-23634
Open AccessImproving POI Recommendation through Collaborative Filtering by incorporating the Geographical Factor into the Similarity Calculation
In recent years, the popularity of Location-Based Social Networks (LBSNs) has surged among tourists seeking to share their travel experiences with their social circles. Although these platforms generate vast amounts of data, effectively utilizing this information to provide personalized recommendations poses significant challenges. Point-Of-Interest (POI) recommendation systems have emerged as a promising solution, leveraging data from LBSNs to suggest tailored destinations for tourists. Collaborative Filtering (CF) has gained recognition as a widely adopted memory-based technique. By analyzing user similarities, CF often uses similarity metrics to predict the likelihood of tourists visiting specific POIs. This study introduces a novel method, called IUPJS (Incorporation of User Proximity in Jaccard Similarity), which extends the traditional Jaccard index by integrating geographic proximity into the similarity calculation. Experimental evaluations on a Foursquare data set indicate that the proposed IUPJS significantly enhances the effectiveness of the recommendation system. This improvement is particularly evident in key evaluation metrics, including precision, recall, F1-score, mAP, and NDCG, exceeding the performance of traditional methods commonly employed in the literature.
- Open Access
- 4 June 2025
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 15 (3) , 23360-23366
Social Information Retrieval using Linked Data and Deep Learning
Online Social Networks (OSNs) are becoming increasingly important in business, government, and all areas of life. For-profit companies use them as rich sources of information and dynamic platforms to drive strategies in product design, innovation, relationship management, and marketing. However, analyzing and retrieving information from these platforms presents distinct challenges due to their inherent characteristics and dynamic nature. To address this, researchers have proposed various approaches for social information retrieval, ranging from term-based analysis to semantic-based methods. To overcome the limitations of existing techniques, the present study proposes a multilayer model that integrates graph analysis, semantic content, and deep learning. The general proposed approach is also presented. By combining learning-to-rank techniques with linked data, a robust framework for social information retrieval is constructed. This method enables a more nuanced understanding by leveraging both the rich contextual information provided by linked data and the structural characteristics of social networks. The proposed model is a flexible framework that can be easily extended to add or remove features and can be applied to various tasks. The experimental results confirm the effectiveness and efficiency of the proposed approach.
- 4 June 2025
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 15 (3) , 23360-23366
Open AccessSocial Information Retrieval using Linked Data and Deep Learning
Online Social Networks (OSNs) are becoming increasingly important in business, government, and all areas of life. For-profit companies use them as rich sources of information and dynamic platforms to drive strategies in product design, innovation, relationship management, and marketing. However, analyzing and retrieving information from these platforms presents distinct challenges due to their inherent characteristics and dynamic nature. To address this, researchers have proposed various approaches for social information retrieval, ranging from term-based analysis to semantic-based methods. To overcome the limitations of existing techniques, the present study proposes a multilayer model that integrates graph analysis, semantic content, and deep learning. The general proposed approach is also presented. By combining learning-to-rank techniques with linked data, a robust framework for social information retrieval is constructed. This method enables a more nuanced understanding by leveraging both the rich contextual information provided by linked data and the structural characteristics of social networks. The proposed model is a flexible framework that can be easily extended to add or remove features and can be applied to various tasks. The experimental results confirm the effectiveness and efficiency of the proposed approach.
- Open Access
- 3 April 2025
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 15 (2) , 21249-21256
Point of Interest Recommendation using Implicit Trust based on Combining Ratings and Check-ins of Smartphone Users
This paper introduces a hybrid model called Implicit Trust based on Combining point-of-interest Ratings and user Check-ins (ITCRC) to address the cold-start challenges commonly associated with trust-based collaborative filtering methods. The model combines Point of Interest (POI) ratings and user check-ins to estimate implicit trust, facilitating location recommendations in a Location-Based Social Network (LBSN). In the Yelp dataset, the ITCRC model's trust and prediction matrices are calculated using Trust based on Ratings (TR), Trust derived from Check-ins (TC), and Trust based on the Hybridization of ratings and check-ins (TH), as well as three approaches derived by adapting O'Donovan's trust formula to the LBSN context. These six approaches are then compared using sparsity metrics and evaluation parameters such as RMSE, precision, and recall. The comparisons revealed that the TH approach significantly reduces the data sparsity of the prediction matrix by 36.08%, the TR and TC approaches improve the relevance of the recommendations (0.77% of precision and 0.99% of recall), and the OR, OC, and OH approaches improve the prediction accuracy by 0.2% in terms of RMSE.
- 3 April 2025
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 15 (2) , 21249-21256
Open AccessPoint of Interest Recommendation using Implicit Trust based on Combining Ratings and Check-ins of Smartphone Users
This paper introduces a hybrid model called Implicit Trust based on Combining point-of-interest Ratings and user Check-ins (ITCRC) to address the cold-start challenges commonly associated with trust-based collaborative filtering methods. The model combines Point of Interest (POI) ratings and user check-ins to estimate implicit trust, facilitating location recommendations in a Location-Based Social Network (LBSN). In the Yelp dataset, the ITCRC model's trust and prediction matrices are calculated using Trust based on Ratings (TR), Trust derived from Check-ins (TC), and Trust based on the Hybridization of ratings and check-ins (TH), as well as three approaches derived by adapting O'Donovan's trust formula to the LBSN context. These six approaches are then compared using sparsity metrics and evaluation parameters such as RMSE, precision, and recall. The comparisons revealed that the TH approach significantly reduces the data sparsity of the prediction matrix by 36.08%, the TR and TC approaches improve the relevance of the recommendations (0.77% of precision and 0.99% of recall), and the OR, OC, and OH approaches improve the prediction accuracy by 0.2% in terms of RMSE.
- Open Access
- 8 October 2018
- Published by MECS Publisher in International Journal of Intelligent Systems and Applications
- Vol. 10 (10) , 42-52
Towards an Incremental Recommendation of POIs for Mobile Tourists without Profiles
Mobile tourism or m-tourism can assist and help tourists anywhere and anytime face the overload of information that may appear in their smartphones. Indeed, these mobile users find difficulties in the choice of points of interest (POIs) that may interest them during their discovery of a new environment (a city, a university campus ...). In order to reduce the number of POIs to visit, the recommendation systems (RS) represent a good solution to guide each tourist towards personalized paths close to his instantaneous location during his visit. In this article, we focus on (1) the detection of the spatiotemporal context of the tourist to filter the POIs and (2) the use of the previous notations of the places. These two criteria make it possible to integrate the evolutionary context of the visit in order to predict incrementally the most relevant transitions to be borrowed by the tourists without profile. These predictions are calculated using collaborative filtering algorithms that require the collection of traces of tourists to better refine the recommendation of POIs. In our software prototype, we have adapted the SLOPE ONE algorithm to our context of discovering the city of Chlef to avoid problems like data scarcity, cold start and scalability. In order to validate the use of this prototype, we conducted experiments by tourists in order to calculate indicators to assess the relevance of the recommendations provided by our system.
- 8 October 2018
- Published by MECS Publisher in International Journal of Intelligent Systems and Applications
- Vol. 10 (10) , 42-52
Open AccessTowards an Incremental Recommendation of POIs for Mobile Tourists without Profiles
Mobile tourism or m-tourism can assist and help tourists anywhere and anytime face the overload of information that may appear in their smartphones. Indeed, these mobile users find difficulties in the choice of points of interest (POIs) that may interest them during their discovery of a new environment (a city, a university campus ...). In order to reduce the number of POIs to visit, the recommendation systems (RS) represent a good solution to guide each tourist towards personalized paths close to his instantaneous location during his visit. In this article, we focus on (1) the detection of the spatiotemporal context of the tourist to filter the POIs and (2) the use of the previous notations of the places. These two criteria make it possible to integrate the evolutionary context of the visit in order to predict incrementally the most relevant transitions to be borrowed by the tourists without profile. These predictions are calculated using collaborative filtering algorithms that require the collection of traces of tourists to better refine the recommendation of POIs. In our software prototype, we have adapted the SLOPE ONE algorithm to our context of discovering the city of Chlef to avoid problems like data scarcity, cold start and scalability. In order to validate the use of this prototype, we conducted experiments by tourists in order to calculate indicators to assess the relevance of the recommendations provided by our system.