Author-Topic-Sentiment Mixture(ATSM) model for Author's Sentiment Analysis

DOI

10.2991/csss-14.2014.20How to use a DOI?

Keywords

LDA; author-topic; ATSM; Sentiment analysis; probabilistic topic models;Gibbs sampling; LDA

Abstract

In this paper,we propose a probabilistic modeling framework,called Author-Topic-Sentiment Mixture(ATSM) model,which based on Latent Dirichlet Allocation (LDA) to include authorship information and sentiments information.The proposed model can reveal the sentiment-topic and author’s sentiment.Each author associated with a distribution of the sentiment-topics,and each sentiment-topic is associated with a distribution of the words.Unlike other approaches to sentiment classification which often require labeled corpora or sentiment seed words,the proposed ATSM model is unsupervised .We show sentiment-topics recovered and the author’s distribution of sentiment-topic by the ATSM model.We compare the performance with two other generative models for documents :LDA and ATM,and illustrative a possible application of the ATSM.

Copyright

© 2014, 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  - Yang KeHua
AU  - Yang Xiang
PY  - 2014/06
DA  - 2014/06
TI  - Author-Topic-Sentiment Mixture(ATSM) model for Author's Sentiment Analysis
BT  - Proceedings of the 3rd International Conference on Computer Science and Service System
PB  - Atlantis Press
SP  - 89
EP  - 93
SN  - 1951-6851
UR  - https://doi.org/10.2991/csss-14.2014.20
DO  - 10.2991/csss-14.2014.20
ID  - KeHua2014/06
ER  -