ABSTRACT
The mechanism of corrections on false information in real social network environments was analyzed. The effect of corrections was evaluated and its influencing factors were explored. Eight factors that affect the effectiveness of correction were summarized based on existing research and our hypotheses, such as the proportion of the original false information, whether it contains text warnings of false information, whether to explain the explanation, user influence, etc.. The effectiveness of correction posts was evaluated by sentiment analysis and the social context of themselves. Statistical methods were used to test the relationship between the pre-determined influencing factors and the effectiveness of correction. The experiment was conducted based on the false information data about COVID-19 epidemic collected from Sina Weibo. Results show that a higher proportion of false information in a correction reduces the effectiveness, and explaining the reason improves the effectiveness. Six conclusions that improve the effectiveness of corrections on social networks were proposed such as mentioning original misinformation less, explaining why original misinformation is wrong. Guidance was provided for related media to correct false information on social network. Copyright ©2021 Journal of Zhejiang University (Engineering Science). All rights reserved.