Sentic Computing for Patient Centered Applications

摘要：

Next-generation patients are far from being peripheral to health-care. They are central to understanding the effectiveness and efficiency of services and how they can be improved. Today a lot of patients are used to reviewing local health services on-line but this social information is just stored in natural language text and it is not machine-accessible and machine-processable. To distil knowledge from this extremely unstructured information we use Sentic Computing, a new opinion mining and sentiment analysis paradigm which exploits AI and Semantic Web techniques to better recognize, interpret and process opinions and sentiments in natural language text. In particular, we use a language visualization and analysis system, a novel emotion categorization model, a resource for opinion mining based on a web ontology and novel techniques for finding and defining topic dependent concepts, namely spectral association and CF-IOF weighting respectively.

关键词： AI Semantic Networks Knowledge Base Management NLP Opinion Mining and Sentiment Analysis E-Health

作者: Erik Cambria Amir Hussain Tariq Durrani Catherine Havasi Chris Eckl James Munro

作者单位: Dept.of Computing Science and Mathematics, University of Stirling, Stirling, FK9 4LA, UK MIT Media Lab, MIT, Cambridge, MA 02142-1323, USA Sitekit Labs, Sitekit Solutions Ltd., Portree, IV51 9HL, UK; Patient Opinion, Sheffield, S3 8EN, UK

会议类型: 国际会议

会议名称: 2010 IEEE 10th International Conference on Signal Processing(第十届信号处理国际会议 ICSP 2010)

会议地点: 北京

会议语种:英文

页码: 1279-1282

在线出版日期: 2010-08-24（万方平台首次上网日期，不代表论文的发表时间）