A Self-Reconfigurable System for Mobile Health Text Misinformation Detection

Abstract

Misinformation is always a serious problem for the general public, especially during pandemic. People constantly receive text messages of related coronavirus news and its cures from their smartphones. These health text messages help people update their coronavirus knowledge repeatedly and better manage their health, but some of the messages may mislead people and may even cause a fatal result. This research tries to identify mobile health text misinformation by proposing a self-reconfigurable system, which includes the preprocessing functions (involving lexical analysis, stopword removal, and stemming), a dataflow graph from TensorFlow, and a reconfiguration method for self-improvement. Experiment results show the proposed method significantly improves the accuracy of the mobile health text misinformation detection compared to the one without using self-reconfiguration. However, the results also show the accuracy still has room for improvement. More refinements need to be done before the method could be put into an effective use.