A Study of News Sentiment &; Public Opinion Detection and Tracking－A Big Data Research Approach

• Main Author: 鄒函升
• Other Authors: 楊建民
• Format: Others
• Language: zh-TW
• Online Access: http://ndltd.ncl.edu.tw/handle/j5gbug

碩士 === 國立政治大學 === 資訊管理研究所 === 102 === Recently, acquiring knowledge and current events from the Internet is gradually replacing traditional media. However, It is more difficult for people to organize and absorb because of the huge amount of news information. In addition, the news is the social conditions that verified and packaged through the media. It implies the public sentiment and public opinions. Therefore, how to effectively and accurately find the information in a large amount of data is a important issue. More importantly, founding &; solving problem and even predicting the future is significant issue in this current. In this study, in addition to the use of detection and tracking technique to find the information more effectively, we also apply opinion mining to analyze news sentiment to understand about the optimistic or pessimistic social conditions. In this study, we write a program to collect the political news automatically from The Central News Agency. And then applying event detection and tracking algorithm for classification and opinion mining for sentiment analysis. In the conclusions, we take public opinion polls to valid our results, founding between the news sentiment and public opinion polls exist a certain relevance. Besides, it found that all the negative news lasts about four weeks at peak periods. Overall news sentiment trends have the exceeding seventy percent correlation with the dissatisfaction index of Premier. The results can be effectively reflected the public opinion. In the data science of current, we propose a real-time and resource saving way to observe the news events and society. In the future, we will plan to add various media sources to reflect directly the real public opinion and even become a new way to insight into the public opinion.