An Iterative Method of Sentiment Analysis for Reliable User Evaluation

Abstract

Benefited from the booming social network, reading posts from other users over the internet is becoming one of commonest ways for people to intake information. One may also have noticed that sometimes we tend to focus on users provide well-founded analysis, rather than those merely who vent their emotions. This thesis aims at finding a simple and efficient way to recognize reliable information sources among countless internet users by examining the sentiments from their past posts. To achieve this goal, the research utilized a dataset of tweets about Apple's stock price retrieved from Twitter. Key features we studied include post-date, user name, number of followers of that user, and the sentiment of that tweet. Prior to making further use of the dataset, tweets from users who do not have sufficient posts are filtered out. To compare user sentiments and the derivative of Apple's stock price, we use Pearson correlation between them to describe how well each user performs. Then we iteratively increase the weight of reliable users and lower the weight of untrustworthy users, the correlation between overall sentiment and the derivative of stock price will finally converge. The final correlations for individual users are their performance scores. Due to the chaos of real-world data, manual segmentation via data visualization is also proposed as a denoise method to improve performance. Besides our method, other metrics can also be considered as user trust index, such as numbers of followers of each user. Experiments are conducted to prove that our method outperforms others. With simple input, this method can be applied to a wide range of topics including election, economy, and the job market.