Deep learning for constructing microblog behavior representation to identify social media user's personality

Institute of Psychology, Chinese Academy of Sciences, Beijing, China
DOI
10.7287/peerj.preprints.1906v1
Subject Areas
Artificial Intelligence, Natural Language and Speech, Social Computing
Keywords
personality prediction, social media behavior, deep learning, feature learning
Copyright
© 2016 Liu et al.
Licence
This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Preprints) and either DOI or URL of the article must be cited.
Cite this article
Liu X, Zhu T. 2016. Deep learning for constructing microblog behavior representation to identify social media user's personality. PeerJ Preprints 4:e1906v1

Abstract

Due to the rapid development of information technology, Internet has become part of everyday life gradually. People would like to communicate with friends to share their opinions on social networks. The diverse social network behavior is an ideal users' personality traits reflection. Existing behavior analysis methods for personality prediction mostly extract behavior attributes with heuristic. Although they work fairly well, but it is hard to extend and maintain. In this paper, for personality prediction, we utilize deep learning algorithm to build feature learning model, which could unsupervised extract Linguistic Representation Feature Vector (LRFV) from text published on Sina Micro-blog actively. Compared with other feature extraction methods, LRFV, as an abstract representation of Micro-blog content, could describe use's semantic information more objectively and comprehensively. In the experiments, the personality prediction model is built using linear regression algorithm, and different attributes obtained through different feature extraction methods are taken as input of prediction model respectively. The results show that LRFV performs more excellently in micro-blog behavior description and improve the performance of personality prediction model.

Author Comment

This is a submission to PeerJ Computer Science for review.

Supplemental Information

Figure 1. The basic structure of an autoencoder

DOI: 10.7287/peerj.preprints.1906v1/supp-2

Figure 2. The training principle diagram of an autoencoder

DOI: 10.7287/peerj.preprints.1906v1/supp-3

Figure 3. The deep architecture of Stacked Autoencoders

DOI: 10.7287/peerj.preprints.1906v1/supp-4

Figure 4. The comparison of prediction results using linguistic feature vectors with different dimensionality. (a)The comparison of r

DOI: 10.7287/peerj.preprints.1906v1/supp-5

Figure 4. The comparison of prediction results using linguistic feature vectors with different dimensionality. (b)The comparison of RMSE

DOI: 10.7287/peerj.preprints.1906v1/supp-6