A Weighted Ml-Knn Model For Predicting Users' Personality Traits
PROCEEDINGS OF 2013 INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE AND COMPUTER APPLICATIONS (ICSA 2013)(2013)
摘要
Gaining insight into human personality and its impact on human behavior is very valuable in many applications, such as web information credibility prediction. In this paper, we explore using weighted ML-kNN model for automatic recognition of personality traits of web users, based on a given composition text. After extracting features through analysis of the content of user's Essays statues updates, we discretize contiguous attribute using Kohonen's feature-map algorithm, and assign weight to extracted features based on information entropy. The Essays dataset is partitioned into training dataset and test dataset. For a given test user, the weighted distance between test user and training user is calculated, and based on which the nearest neighbors are identified. The personality traits of test user are then predicted by using ML-kNN algorithm. Our experiment on the Essays dataset shows expected positive results.
更多查看译文
关键词
Big-5 personality traits, personality prediction, ML-kNN, weighted feature, information entropy theory
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络