论文信息 - Unsupervised Sentiment Analysis of Objective Texts

Unsupervised Sentiment Analysis of Objective Texts

Unsupervised learning is an emerging approach in sentiment analysis. In this paper, we apply unsupervised word and document embedding algorithms, Word2Vec and Doc2Vec, to medical and scientific text. We use SentiWordNet as the benchmark measures. Our empirical study is done on the Obesity NLP Challenge data set and four Science subgroups from Reuters 20 Newsgroups. Our results show that Word2Vec demonstrates a reliable performance in sentiment analysis of the text, whereas Doc2Vec requires more detailed studies.

Marina Sokolova | Qufei Chen | Marina Sokolova | Qufei Chen

[1] Marina Sokolova,et al. NLP can help parents to understand rare diseases , 2013 .

[2] Jeffrey Dean,et al. Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[3] Yihan Deng,et al. Retrieving Attitudes: Sentiment Analysis from Clinical Narratives , 2014, MedIR@SIGIR.

[4] Quoc V. Le,et al. Distributed Representations of Sentences and Documents , 2014, ICML.

[5] Ming Zhou,et al. Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification , 2014, ACL.

[6] D. Toher,et al. Why Welch’s test is Type I error robust , 2016 .

[7] Marina Sokolova,et al. Word2Vec and Doc2Vec in Unsupervised Sentiment Analysis of Clinical Discharge Summaries , 2018, ArXiv.

[8] Andrea Esuli,et al. SENTIWORDNET: A Publicly Available Lexical Resource for Opinion Mining , 2006, LREC.