Personalized Email Prioritization Based on Content and Social Network Analysis

The proposed system combines unsupervised clustering, social network analysis, semisupervised feature induction, and supervised classification to model user priorities among incoming email messages.

Authors

• Yiming Yang Carnegie Mellon University
• Shinjae Yoo
• Frank Lin
• Il-Chul Moon KAIST

Keywords

• Electronic mail
• Training
• Social network services
• Feature extraction
• Support vector machines
• Data mining
• Vectors
• Social Networks
• Social Network Analysis
• Personal Email
• Social Groups
• Personal Data
• Data Privacy
• Feature Learning
• Unsupervised Clustering
• Graph Structure
• Personal Networks
• Development Cycle
• Important Message
• Email Message
• Similarity Judgments
• Personal Social Networks
• Global Social Networking
• Social Network Information
• Standard Support Vector Machine
• Training Set
• Training Data
• Message Sender
• Term In Formula
• In-degree Centrality
• Out-degree Centrality
• Betweenness Centrality
• High Scores
• Clustering Algorithm
• Training Examples
• Shortest Path
• Clustering Coefficient
• personalization
• clustering
• classification
• and association rules
• feature extraction or construction
• mining methods and algorithms
• intelligent systems