Combat COVID-19 Infodemic Using Explainable Natural Language Processing Models
dc.contributor.author | Ayoub, Jackie | |
dc.contributor.author | Yang, "X. Jessie | |
dc.contributor.author | Zhou, Feng | |
dc.date.accessioned | 2021-03-01T05:08:35Z | |
dc.date.available | 2021-03-01T05:08:35Z | |
dc.date.issued | 2021-02-28 | |
dc.identifier.uri | https://hdl.handle.net/2027.42/166319 | en |
dc.description.abstract | Misinformation of COVID-19 is prevalent on social media as the pandemic un- folds, and the associated risks are extremely high. Thus, it is critical to detect and combat such misinformation. Recently, deep learning models using natural language processing techniques, such as BERT (Bidirectional Encoder Represen- tations from Transformers), have achieved great successes in detecting misinfor- mation. In this paper, we proposed an explainable natural language processing model based on DistilBERT and SHAP (Shapley Additive exPlanations) to com- bat misinformation about COVID-19 due to their efficiency and effectiveness. First, we collected a dataset of 984 claims about COVID-19 with fact checking. By augmenting the data using back-translation, we doubled the sample size of the dataset and the DistilBERT model was able to obtain good performance (accuracy: 0.972; areas under the curve: 0.993) in detecting misinformation about COVID-19. Our model was also tested on a larger dataset for AAAI2021 - COVID-19 Fake News Detection Shared Task and obtained good performance (accuracy: 0.938; areas under the curve: 0.985). The performance on both datasets was better than traditional machine learning models. Second, in or- der to boost public trust in model prediction, we employed SHAP to improve model explainability, which was further evaluated using a between-subjects ex- periment with three conditions, i.e., text (T), text+SHAP explanation (TSE), and text+SHAP explanation+source and evidence (TSESE). The participants were significantly more likely to trust and share information related to COVID- 19 in the TSE and TSESE conditions than in the T condition. Our results provided good implications in detecting misinformation about COVID-19 and improving public trust. | en_US |
dc.language.iso | en_US | en_US |
dc.publisher | elsevier | en_US |
dc.relation.ispartofseries | Manuscript Number: IPM-D-20-01187R1 | en_US |
dc.subject | COVID-19, misinformation detection, trust, BERT, DistilBERT, SHAP | en_US |
dc.title | Combat COVID-19 Infodemic Using Explainable Natural Language Processing Models | en_US |
dc.type | Article | en_US |
dc.description.peerreviewed | Peer Reviewed | en_US |
dc.contributor.affiliationum | PhD student | en_US |
dc.contributor.affiliationum | Assistant professor | en_US |
dc.contributor.affiliationum | Assistant professor | en_US |
dc.contributor.affiliationumcampus | Dearborn | en_US |
dc.description.bitstreamurl | http://deepblue.lib.umich.edu/bitstream/2027.42/166319/1/Covid_Information_Processing_and_Management.pdf | |
dc.identifier.doi | https://dx.doi.org/10.7302/242 | |
dc.identifier.source | Information Processing and Management | en_US |
dc.identifier.orcid | https://orcid.org/0000-0003-0274-492X | en_US |
dc.identifier.orcid | https://orcid.org/0000-0001-6071-0387 | en_US |
dc.identifier.orcid | https://orcid.org/0000-0001-6123-073X | en_US |
dc.description.depositor | SELF | en_US |
dc.identifier.name-orcid | Ayoub, Jackie; 0000-0003-0274-492X | en_US |
dc.identifier.name-orcid | Yang, X. Jessie; 0000-0001-6071-0387 | en_US |
dc.identifier.name-orcid | Zhou, Feng; 0000-0001-6123-073X | en_US |
dc.working.doi | 10.7302/242 | en_US |
dc.owningcollname | Industrial and Manufacturing Systems Engineering (IMSE, UM-Dearborn) |
Files in this item
Remediation of Harmful Language
The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.
Accessibility
If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.