Automatic Conditional Generation of Personalized Social Media Short Texts

TL;DR

This paper introduces a conditional language model that generates human-like social media texts personalized with Big Five personality traits, combining deep learning with psychological linguistics for more natural and individualized outputs.

Contribution

The study presents a novel BFP-dependent text generation model that incorporates personality features into deep neural networks to produce personalized social media texts.

Findings

Generated texts exhibit discriminative personality styles.

Texts are syntactically correct and semantically smooth.

Model can be applied to various natural language generation tasks.

Abstract

Automatic text generation has received much attention owing to rapid development of deep neural networks. In general, text generation systems based on statistical language model will not consider anthropomorphic characteristics, which results in machine-like generated texts. To fill the gap, we propose a conditional language generation model with Big Five Personality (BFP) feature vectors as input context, which writes human-like short texts. The short text generator consists of a layer of long short memory network (LSTM), where a BFP feature vector is concatenated as one part of input for each cell. To enable supervised training generation model, a text classification model based convolution neural network (CNN) has been used to prepare BFP-tagged Chinese micro-blog corpora. Validated by a BFP linguistic computational model, our generated Chinese short texts exhibit discriminative personality styles, which are also syntactically correct and semantically smooth with appropriate emoticons. With combination of natural language generation with psychological linguistics, our proposed BFP-dependent text generation model can be widely used for individualization in machine translation, image caption, dialogue generation and so on.