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/).
Cite this article
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 -