Today, Social Networking Sites （SNS）, online forum, and e-mail communication have become a daily phenomenon in Indonesia. Thousands and even millions of the people have been using Blog, Facebook, MySpace, Twitter, a...Today, Social Networking Sites （SNS）, online forum, and e-mail communication have become a daily phenomenon in Indonesia. Thousands and even millions of the people have been using Blog, Facebook, MySpace, Twitter, and others as a communication medium. Many of them are mobile connected and have made it a daily practices. Interestingly, all these changes are not followed by Onmi International Hospital which it ultimately in 2009 led to the crisis. This crisis was beginning from the customer, Prita Mulyasari, who felt disappointed at the hospital service, and wrote an e-mail to her friend. Suddenly, in a short time the e-mail was disseminated widely on the Internet and produced a lot of support and public humiliation to the Omni International Hospital. This paper aims at explaining the cybcr crisis experienced by Omni International Hospital and how to overcome the problem at corporate level.展开更多
There is a major defect when using the traditional topic-opinion model for post opinion classifications in an online forum discussion.The accuracy of the classification based on the topic-opinion model highly depends ...There is a major defect when using the traditional topic-opinion model for post opinion classifications in an online forum discussion.The accuracy of the classification based on the topic-opinion model highly depends on the observable topic-opinion features aiming at the subject,while a large number of posts do not have such features in a forum.Therefore,for the most part,the accuracy is less than 78%.To solve this problem,we propose a new method to identify post opinions based on the Tree Conditional Random Fields(T-CRFs)model.First,we select the topic-opinion features of the posts and associated opinion features between posts to construct the T-CRFs model,and then we use the T-CRFs model to label the opinions of the tree-structured posts under the same topic iteratively to reach a maximum joint probability.To reduce the training cost,we design a simplified tree diagram module and some feature templates.Experimental results suggest the proposed method costs less training time and improves the accuracy by 11%.展开更多
文摘Today, Social Networking Sites （SNS）, online forum, and e-mail communication have become a daily phenomenon in Indonesia. Thousands and even millions of the people have been using Blog, Facebook, MySpace, Twitter, and others as a communication medium. Many of them are mobile connected and have made it a daily practices. Interestingly, all these changes are not followed by Onmi International Hospital which it ultimately in 2009 led to the crisis. This crisis was beginning from the customer, Prita Mulyasari, who felt disappointed at the hospital service, and wrote an e-mail to her friend. Suddenly, in a short time the e-mail was disseminated widely on the Internet and produced a lot of support and public humiliation to the Omni International Hospital. This paper aims at explaining the cybcr crisis experienced by Omni International Hospital and how to overcome the problem at corporate level.
基金supported by the National Natural Science Foundation of China under Grant No. 60873246China Information Technology Security Evaluation Centre
文摘There is a major defect when using the traditional topic-opinion model for post opinion classifications in an online forum discussion.The accuracy of the classification based on the topic-opinion model highly depends on the observable topic-opinion features aiming at the subject,while a large number of posts do not have such features in a forum.Therefore,for the most part,the accuracy is less than 78%.To solve this problem,we propose a new method to identify post opinions based on the Tree Conditional Random Fields(T-CRFs)model.First,we select the topic-opinion features of the posts and associated opinion features between posts to construct the T-CRFs model,and then we use the T-CRFs model to label the opinions of the tree-structured posts under the same topic iteratively to reach a maximum joint probability.To reduce the training cost,we design a simplified tree diagram module and some feature templates.Experimental results suggest the proposed method costs less training time and improves the accuracy by 11%.
