A personalized recommender system for pervasive social networks

Arnaboldi, Valerio; Campana, Mattia Giovanni; Delmastro, Franca; Pagani, Elena

doi:10.1016/j.pmcj.2016.08.010

Cited by 18 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ouyang et al use multi-graph neural network to balance the weight of each domain and efficiently train the model [24]. Arnaboldi et al propose a PLIERS tag-based recommender system to discover and select content of interest to individual mobile users in a highly personalized way [32]. The effectiveness of the recommendation has been significantly improved.…”

Section: Et Al Alleviate the Data Sparsity Problem Caused By Version ...mentioning

confidence: 99%

Comprehensive Analysis for Intelligent Recommendation on Mobile Applications

2023

ACE

View full text Add to dashboard Cite

With the development of mobile devices and mobile apps, corresponding app recommendation analysis has received increasing focus in recent years. Such recommendation analysis covers aims including app evaluation, API-based app development, customer investigation, app security, etc. Meanwhile, various types of recommendation techniques are exploited in the app recommendation analysis, which continually improves the development of this direction. However, there is still a lack of a systematical study providing an overall development picture for these app recommendation efforts. Thus, it faces an obstacle for related researchers following this direction of work, and correspondingly is not conducive to the future development. To overcome the problem, in this paper, we take the first step to systematically investigate this direction of efforts. To this end, we summary the main works and techniques used in more than 35 important works in this direction. To better understand the development routines, we have analyzed the characteristics of these works from two perspectives, i.e., technology and research scenario. We have obtained some interesting conclusions within this research direction, and put forward some work suggestions according to the overall research.

show abstract

Section: Et Al Alleviate the Data Sparsity Problem Caused By Version ...mentioning

confidence: 99%

Comprehensive Analysis for Intelligent Recommendation on Mobile Applications

2023

ACE

View full text Add to dashboard Cite

show abstract

“…UbiqLog (UL) : this dataset has been collected in order to characterize dailylife events by using smartphone-embedded sensors [73,74], and it is available on the public UCI Machine Learning repository 10 . The data collection has been conducted in 2013 with 35 participants, for a period of one month.…”

Section: Extrasensory (Es)mentioning

confidence: 99%

“…The most important parameters of DT and the corresponding values space we considered are the following: (i) min sample leaf (min sl ∈ [10,50,100,200]), the minimum number of training samples used to define a leaf node; and max depth (max d ∈ [10,50,100,200]), that represents the maximum depth of the decision tree. RF shares with DT the first two parameters to define the structure of the decision tree used in the whole model.…”

Section: Complexity Evaluationmentioning

confidence: 99%

“…This new paradigm creates additional opportunities for the development of novel pervasive and context-aware mobile applications which can benefit from low-latency device-to-device communications and sensing capabilities of modern mobile devices. Examples of these applications include networking services, like data dissemination algorithms [4] and forwarding protocols [5], but also applicationoriented services like mobile health systems [6,7], intelligent transportation systems [8], augmented reality applications [9], and pervasive recommender systems [10,11].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On-device modeling of user's social context and familiar places from smartphone-embedded sensor data

Campana¹,

Delmastro²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Context modeling and recognition represent complex tasks that allow mobile and ubiquitous computing applications to adapt to the user's situation. The real advantage of context-awareness in mobile environments mainly relies on the prompt system's and applications' reaction to context changes. Current solutions mainly focus on limited context information generally processed on centralized architectures, potentially exposing users' personal data to privacy leakage, and missing personalization features. For these reasons on-device context modeling and recognition represent the current research trend in this area. Among the different information characterizing the user's context in mobile environments, social interactions and visited locations remarkably contribute to the characterization of daily life scenarios. In this paper we propose a novel, unsupervised and lightweight approach to model the user's social context and her locations based on ego networks directly on the user mobile device. Relying on this model, the system is able to extract high-level and semantic-rich context features from smartphone-embedded sensors data. Specifically, for the social context it exploits data related to both physical and cyber social interactions among users and their devices. As far as location context is concerned, we assume that it is more relevant to model the familiarity degree of a specific location for the user's context than the raw location data, both in terms of GPS coordinates and proximity devices. We demonstrate the effectiveness of the proposed approach with 3 different sets of experiments by using 5 real-world datasets collected from a total of 956 personal mobile devices. Specifically, we assess the structure of the social and location ego networks, we provide a semantic evaluation of the proposed models and a complexity evaluation in terms of mobile computing performance. Finally, we demonstrate the relevance of the extracted features by showing the performance of 3 different machine learning algorithms to recognize daily-life situations, obtaining an improvement of 3% of AUROC, 9% of Precision, and 5% in terms of Recall with respect to use only features related to physical context.

show abstract

“…These aspects are paving the way towards new types of computing models, shifting most of the tasks from centralized architectures (e.g., remote servers and cloud-based computing) to distributed solutions, where the data available at the edge is directly processed by mobile devices [5]. This paradigm shift creates new opportunities for the creation of novel pervasive mobile applications (e.g., data dissemination algorithms [6], forwarding protocols [7], and personalized services [8,9]), which benefit from low-latency direct communications and the sensing capabilities of modern mobile devices. Specifically, the great variety of sensors embedded in the personal mobile devices of the users provides essential information to recognize the context and the situation in which the user is involved, making context-awareness a real feature of new pervasive computing applications.…”

Section: Introductionmentioning

confidence: 99%