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
Objective To study the news reports on COVID-19 through comparing the forwarding volume and posting time of microblogs from the government media and non-government media and exploring the advantages and disadvantages ...Objective To study the news reports on COVID-19 through comparing the forwarding volume and posting time of microblogs from the government media and non-government media and exploring the advantages and disadvantages of the two in mastering discourse power in public health emergencies,so to provide a reference for the government department to cope with online public opinion.Methods The GooSeeker data mining tool was used to collect the data of the six microblog accounts that reported the COVID-19 from January 1 to June 15,2020.Then the data were analyzed from two aspects of microblog forwarding volume and posting time.Results and Conclusion According to the analysis of the forwarding volume data,the government media had a greater influence on the public during the process of COVID-19.The analysis of the news release time showed that the government media and non-government media had similar ability in discourse power on public health emergencies.This paper proposes the following recommendations for government departments to enhance their abilities to cope with online public opinion on public health emergencies,such as releasing information promptly,cultivating opinion leaders,and reporting the fact to avoid public misunderstandings.展开更多
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%.
文摘Objective To study the news reports on COVID-19 through comparing the forwarding volume and posting time of microblogs from the government media and non-government media and exploring the advantages and disadvantages of the two in mastering discourse power in public health emergencies,so to provide a reference for the government department to cope with online public opinion.Methods The GooSeeker data mining tool was used to collect the data of the six microblog accounts that reported the COVID-19 from January 1 to June 15,2020.Then the data were analyzed from two aspects of microblog forwarding volume and posting time.Results and Conclusion According to the analysis of the forwarding volume data,the government media had a greater influence on the public during the process of COVID-19.The analysis of the news release time showed that the government media and non-government media had similar ability in discourse power on public health emergencies.This paper proposes the following recommendations for government departments to enhance their abilities to cope with online public opinion on public health emergencies,such as releasing information promptly,cultivating opinion leaders,and reporting the fact to avoid public misunderstandings.
