No abstract

On and after the Great Eastern Japan Earthquake, various false information and rumor have been spread on Twitter. To cope with this, we proposed the method for automatically assessing the credibility of information based on the topic and opinion classification. The information credibility is assessed calculating the ratio of the positive opinions to all opinions about a topic. To identify the topic of a tweet, topic models are generated using Latent Dirichlet Allocation. To identify if an opinion of the tweet is positive or negative, sentiment analysis is performed using a semantic orientation dictionary. However, the accuracy of the method is susceptible to the number of tweets. That is to say, if the number of tweets with the same topic is small, the denominator is reduced. Thus the accuracy is also reduced. To cope with this problem, a new method of providing an expertise score is proposed. The score is used to calculate the information credibility depending on user's knowledge (expertise). This makes tweets of a user handled as a more reliable opinion even if it is a minor opinion.

No abstract

No abstract