Paper Info
Title
A Heuristic Model for Supporting Users' Decision-Making in Privacy Disclosure for Recommendation.
Abstract
Privacy issues have become a major concern in the web of resource sharing, and users often have difficulty managing their information disclosure in the context of high-quality experiences from social media and Internet of Things. Recent studies have shown that users' disclosure decisions may be influenced by heuristics from the crowds, leading to inconsistency in the disclosure volumes and reduction of the prediction accuracy. Therefore, an analysis of why this influence occurs and how to optimize the user experience is highly important. We propose a novel heuristic model that defines the data structures of items and participants in social media, utilizes a modified decision-tree classifier that can predict participants' disclosures, and puts forward a correlation analysis for detecting disclosure inconsistences. The heuristic model is applied to real-time dataset to evaluate the behavioral effects. Decision-tree classifier and correlation analysis indeed prove that some participants' behaviors in information disclosures became decreasingly correlated during item requesting. Participants can be "persuaded" to change their disclosure behaviors, and the users' answers to the mildly sensitive items tend to be more variable and less predictable. Using this approach, recommender systems in social media can thus know the users better and provide service with higher prediction accuracy.
Year
DOI
Venue
2018
10.1155/2018/2790373
SECURITY AND COMMUNICATION NETWORKS
Field
DocType
Volume
Recommender system,Data structure,Crowds,Heuristic,User experience design,Internet privacy,Social media,Computer security,Computer science,Heuristics,Shared resource
Journal
2018
ISSN
Citations 
PageRank 
1939-0114
2
0.36
References 
Authors
17
4
Name
Order
Citations
PageRank
Hongchen Wu191.84
Huaxiang Zhang243656.32
Li-zhen Cui328271.41
Xinjun Wang4104.49