Tree-Structured Neural Networks With Topic Attention for Social Emotion Classification

Minghua Xu,Bang Wang,Chang Wang

doi:10.1109/access.2019.2929204

Minghua Xu, Bang Wang + Show 1 more

Open Access

https://doi.org/10.1109/access.2019.2929204

Copy DOI

Journal: IEEE Access	Publication Date: Jan 1, 2019
Citations: 10	License type: CC BY 4.0

Affiliation: Huazhong University of Science and Technology

Abstract

Social emotion classification studies the emotion distribution evoked by an article among numerous readers. Although recently neural network-based methods can improve the classification performance compared with the previous word-emotion and topic-emotion approaches, they have not fully utilized some important sentence language features and document topic features. In this paper, we propose a new neural network architecture exploiting both the syntactic information of a sentence and topic distribution of a document. The proposed architecture first constructs a tree-structured long short-term memory (Tree-LSTM) network based on the sentence syntactic dependency tree to obtain a sentence vector representation. For a multi-sentence document, we then use a Chain-LSTM network to obtain the document representation from its sentences’ hidden states. Furthermore, we design a topic-based attention mechanism with two attention levels. The word-level attention is used for weighting words of a single-sentence document and the sentence-level attention for weighting sentences of a multi-sentence document. The experiments on three public datasets show that the proposed scheme outperforms the state-of-the-art ones in terms of higher average Pearson correlation coefficient and MicroF1 performance.

Highlights

Social emotion classification is to study the evoked emotion distribution among a great number of readers who have read a same article [1]
We model each sentence by a Tree-LSTM network in a similar way as that for single-sentence document
We argue that the multi-sentence document (MSDoc) representation dms contains the syntactic information of individual sentences from their composing words by the lower-layer Tree-LSTM network, and includes the topic information of the whole document from its composing sentences yet weighted by the sentence-level Latent Dirichlet Allocation (LDA) attention

Summary

INTRODUCTION

Social emotion classification is to study the evoked emotion distribution among a great number of readers who have read a same article [1]. Wang et al.: Tree-Structured Neural Networks With Topic Attention for Social Emotion Classification tasks, such as neural language models [12]–[14], text classification [15] and sentiment classification [16], some neural network-based methods have been proposed for social emotion classification [17], [18] They adopt a convolutional neural network (CNN) or a recurrent neural network (RNN) to learn the semantic features (like the temporal order) and obtain a vector representation of the document. We propose a two-layer neural network structure with a LDA-based attention mechanism for social emotion classification. We propose to use a Tree-LSTM network to encode syntactic dependency for words in a sentence and integrate a LDA-based attention mechanism into the neural network, to simultaneously exploit syntactic and topic information for social emotion classification. To denote a word embedding, sentence vector and document vector, respectively

VECTOR REPRESENTATION FOR SINGLE-SENTENCE DOCUMENT

SOCIAL EMOTION CLASSIFICATION

EVALUATION METRICS

CONCLUSION