This project integrates advances in data science and key findings from psychological research to improve the prediction of trust in information on social media by modeling the psychological phenomenon known as the memory illusion. The memory illusion refers to memory errors that people make to remember information as an outcome of interpreting and making inferences from their past experience. This project will use social media data to examine the memory illusion with online information, and to understand how it is associated with people's trust in information on social media. Better understanding on the extent and impact of the memory illusion phenomenon using big data will inform machine-learning approaches to better measure trust in information with an additional human information-processing perspective, benefiting society by providing reliable online information, and increasing people's overall trust in information on social media.
This project pursues several research goals to advance the state-of-art of machine learning models to predict people's trust in information on social media. The first goal is to characterize the formation of associative inferences on Twitter information, and understand how it contributes to individuals' trust in tweets. To advance this goal, the research will use big data and data-driven machine learning models. Based on the insights learned from big data, the second goal is to establish the causal relations between identified associative inferences and people's trust of social media information with laboratory and online user studies. The last goal is to model associative inferences into machine learning algorithms to improve the prediction of user trust in online information. The project will advance the state-of-the-art with regard to our understanding on people's trust in social media information in particular and human memory illusion in general. Through interdisciplinary socio-technical collaboration, the project will advance machine-learning models considering human information processing to improve the prediction of people's trust in information on social media, and improve understanding of human behavior using a big data approach to reveal relations among psychological phenomena on a scale that has not been possible with the smaller data sets collected in the laboratory. The interdisciplinary research using data science and psychological research will address theory-based research questions regarding the relationships of information veracity, trust, and information context. Students will participate in all phases of the research.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
