@inproceedings{f23d0364a7d74ad19450ffdd3978fa4f,
title = "Sentiment analysis on chinese health forums: A preliminary study of different language models",
abstract = "Sentiment analysis on Chinese health forums is challenging because of the language, platform, and domain characteristics. Our research investigates the impact of three factors on sentiment analysis: sentiment polarity distribution, language models, and model settings. We manually labeled a large sample of Chinese health forum posts, which showed an extremely unbalanced distribution with a very small percentage of negative posts, and found that the balanced training set could produce higher accuracy than the unbalanced one. We also found that the hybrid approaches combining multiple language model based approaches for sentiment analysis performed better than individual approaches. Finally we evaluated the effects of different model settings and improved the overall accuracy using the hybrid approaches in their optimal settings. Findings from this preliminary study provide deeper insights into the problem of sentiment analysis on Chinese health forums and will inform future sentiment analysis studies.",
keywords = "Chinese health forum, Language model, Sentiment analysis",
author = "Yan Zhang and Yong Zhang and Jennifer Xu and Chunxiao Xing and Hsinchun Chen",
note = "Funding Information: This work was supported by the National High-tech R&D Program of China (Grant No. SS2015AA020102), National Basic Research Program of China (Grant No. 2011CB302302), the 1000-Talent program, and the Tsinghua University Initiative Scientific Research Program. We appreciate the research assistance provided by Qingbo Cao, Yanshen Yin, and Xinhuan Chen at Tsinghua University. Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2016.; International Conference for Smart Health, ICSH 2015 ; Conference date: 17-11-2015 Through 18-11-2015",
year = "2016",
doi = "10.1007/978-3-319-29175-8_7",
language = "English (US)",
isbn = "9783319291741",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer-Verlag",
pages = "68--81",
editor = "Hsinchun Chen and Zeng, {Daniel Dajun} and Xiaolong Zheng and Leischow, {Scott J.}",
booktitle = "Smart Health - International Conference, ICSH 2015, Revised Selected Papers",
}