Jointly Modeling Review Content and Aspect Ratings for Review Rating Prediction
Zhipeng Jin1,2; Qiudan Li1; Daniel D. Zeng1,2,3; YongCheng Zhan3; Ruoran Liu1,2; Lei Wang1; Hongyuan Ma4
2016
会议名称Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval
会议录名称Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval, SIGIR 2016, Pisa, Italy, July 17-21, 2016. ACM 2016, ISBN 978-1-4503-4069-4
会议日期July 17-21, 2016
会议地点Pisa, Italy
摘要Review rating prediction is of much importance for sentiment analysis and business intelligence. Existing methods work well when aspect-opinion pairs can be accurately extracted from review texts and aspect ratings are complete. The challenges of improving prediction accuracy are how to capture the semantics of review content and how to fill in the missing values of aspect ratings. In this paper, we propose a novel review rating prediction method, which improves the prediction accuracy by capturing deep semantics of review content and alleviating data missing problem of aspect ratings. The method firstly learns the latent vector representation of review content using skip-thought vectors, a state-of-the-art deep learning method, then, the missing values of aspect ratings are filled in based on users’ history reviewing behaviors, finally, a novel optimization framework is proposed to predict the review rating. Experimental results on two real-world datasets demonstrate the efficacy of the proposed method.
关键词Review Rating Prediction Aspect Rating Data Missing
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/12272
专题复杂系统管理与控制国家重点实验室_互联网大数据与信息安全
通讯作者Qiudan Li
作者单位1.The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
2.University of Chinese Academy of Sciences, Beijing, China
3.Department of Management Information Systems, University of Arizona, Tucson, Arizona, USA
4.CNCERT/CC, Beijing, China
推荐引用方式
GB/T 7714
Zhipeng Jin,Qiudan Li,Daniel D. Zeng,et al. Jointly Modeling Review Content and Aspect Ratings for Review Rating Prediction[C],2016.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Jointly Modeling Rev(1256KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhipeng Jin]的文章
[Qiudan Li]的文章
[Daniel D. Zeng]的文章
百度学术
百度学术中相似的文章
[Zhipeng Jin]的文章
[Qiudan Li]的文章
[Daniel D. Zeng]的文章
必应学术
必应学术中相似的文章
[Zhipeng Jin]的文章
[Qiudan Li]的文章
[Daniel D. Zeng]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Jointly Modeling Review Content and Aspect Ratings for Review Rating Prediction.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。