A Weighted ML-KNN Model for Predicting Users’Personality Traits

DOI

10.2991/isca-13.2013.58How to use a DOI?

Keywords

Big-5 personality traits; personality prediction; ML-kNN; weighted feature; information entropy theory

Abstract

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.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Xianglin Zuo
AU  - Baoping Feng
AU  - Yuan Yao
AU  - Tianyi Zhang
AU  - Qian Zhang
AU  - Mengmeng Wang
AU  - Wanli Zuo
PY  - 2013/10
DA  - 2013/10
TI  - A Weighted ML-KNN Model for Predicting Users’Personality Traits
BT  - Proceedings of 2013 International Conference on Information Science and Computer Applications
PB  - Atlantis Press
SP  - 345
EP  - 350
SN  - 1951-6851
UR  - https://doi.org/10.2991/isca-13.2013.58
DO  - 10.2991/isca-13.2013.58
ID  - Zuo2013/10
ER  -