scholarly journals Analyzing User Demographics and User Behavior for Trust Assessment

2014 ◽  
pp. 219-241
Author(s):  
Davide Ceolin ◽  
Paul Groth ◽  
Archana Nottamkandath ◽  
Wan Fokkink ◽  
Willem Robert van Hage
Keyword(s):  
User Behavior

Predictability of User Behavior in Social Media: Bottom-Up v Top-Down Modeling

2013 ◽  
Author(s):  
David Darmon ◽  
Jared Sylvester ◽  
Michelle Girvan ◽  
William M. Rand
Keyword(s):  
Social Media ◽  
User Behavior ◽  
Top Down ◽  
Bottom Up

A Survey on Improving the Web Search Ranking by User Behavior Information

2010 ◽  
Author(s):  
Mohamed Husain ◽  
Amarjeet Singh ◽  
Manoj Kumar ◽  
Rakesh Ranjan
Keyword(s):  
Web Search ◽  
User Behavior ◽  
The Web ◽  
Web Search Ranking

Asking costs little? The impact of tasks in video QoE studies on user behavior and user ratings

2013 ◽  
Author(s):  
Andreas Sackl ◽  
Michael Seufert ◽  
Tobias Hoßfeld
Keyword(s):  
User Behavior ◽  
User Ratings ◽  
The Impact

Resource Allocation in Cloud using Multi Bidding Model with User Centric Behavior Analysis

2020 ◽  
Vol 13 (5) ◽  
pp. 1008-1019
Author(s):  
N. Vijayaraj ◽  
T. Senthil Murugan
Keyword(s):  
Resource Allocation ◽  
Behavior Analysis ◽  
User Behavior ◽  
Low Cost ◽  
Cloud Services ◽  
Online Auction ◽  
Analysis Model ◽  
Efficient Resource ◽  
User Centric ◽  
Cloud Resources

Background: Number of resource allocation and bidding schemes had been enormously arrived for on demand supply scheme of cloud services. But accessing and presenting the Cloud services depending on the reputation would not produce fair result in cloud computing. Since the cloud users not only looking for the efficient services but in major they look towards the cost. So here there is a way of introducing the bidding option system that includes efficient user centric behavior analysis model to render the cloud services and resource allocation with low cost. Objective: The allocation of resources is not flexible and dynamic for the users in the recent days. This gave me the key idea and generated as a problem statement for my proposed work. Methods: An online auction framework that ensures multi bidding mechanism which utilizes user centric behavioral analysis to produce the efficient and reliable usage of cloud resources according to the user choice. Results: we implement Efficient Resource Allocation using Multi Bidding Model with User Centric Behavior Analysis. Thus the algorithm is implemented and system is designed in such a way to provide better allocation of cloud resources which ensures bidding and user behavior. Conclusion: Thus the algorithm Efficient Resource Allocation using Multi Bidding Model with User Centric Behavior Analysis is implemented & system is designed in such a way to provide better allocation of cloud resources which ensures bidding, user behavior. The user bid data is trained accordingly such that to produce efficient resource utilization. Further the work can be taken towards data analytics and prediction of user behavior while allocating the cloud resources.

scholarly journals Personalized project recommendations: using reinforcement learning

2019 ◽  
Vol 2019 (1) ◽  
Author(s):  
Faxin Qi ◽  
Xiangrong Tong ◽  
Lei Yu ◽  
Yingjie Wang
Keyword(s):  
Reinforcement Learning ◽  
User Behavior ◽  
Collaborative Work ◽  
Recursive Least Squares ◽  
The Internet ◽  
Dynamic Impact ◽  
Rls Algorithm ◽  
Trust Value ◽  
Q Learning ◽  
Actual Evaluation

AbstractWith the development of the Internet and the progress of human-centered computing (HCC), the mode of man-machine collaborative work has become more and more popular. Valuable information in the Internet, such as user behavior and social labels, is often provided by users. A recommendation based on trust is an important human-computer interaction recommendation application in a social network. However, previous studies generally assume that the trust value between users is static, unable to respond to the dynamic changes of user trust and preferences in a timely manner. In fact, after receiving the recommendation, there is a difference between actual evaluation and expected evaluation which is correlated with trust value. Based on the dynamics of trust and the changing process of trust between users, this paper proposes a trust boost method through reinforcement learning. Recursive least squares (RLS) algorithm is used to learn the dynamic impact of evaluation difference on user’s trust. In addition, a reinforcement learning method Deep Q-Learning (DQN) is studied to simulate the process of learning user’s preferences and boosting trust value. Experiments indicate that our method applied to recommendation systems could respond to the changes quickly on user’s preferences. Compared with other methods, our method has better accuracy on recommendation.

Sign in / Sign up

Export Citation Format

Share Document