Distilling wisdom of crowds in online communities: A novel prediction market constructed with comment posters

Abstract

Aggregating the wisdom of crowds from user-generated content in the online community can be valuable for decision-making. However, low-quality comments pose significant challenges for traditional wisdom extraction algorithms, such as prediction polls. Therefore, to extract the wisdom of online crowds effectively, we propose a novel artificial prediction market that can dynamically filter out low-quality comments using the market mechanism. Unlike traditional prediction markets where real human traders participate in contract trading, traders in the proposed market, referred to as artificial human traders, are constructed with posters’ online comments. We constructed artificial human traders using the comment data from the Eastmoney stock forum. Then, we validated the effectiveness of the proposed market in predicting the price movements of the constituent stocks in the Shanghai Stock Exchange 50 Index. Experimental results demonstrate that the proposed market excels in extracting the wisdom of crowds from online communities for stock price movement predictions and conducting investment portfolios based on these prediction results. Additionally, to investigate the factors contributing to the superior performance of the proposed artificial prediction market, we compare it with the prediction poll, a well-known opinion aggregation algorithm. The results indicate that the artificial prediction market performs better in assessing the quality of comments compared with the prediction poll.