Coronavirus Incidence Rate Estimation from Social Media Data in Iran

Coronavirus disease as a persistent epidemic of acute respiratory syndrome posed a challenge to global healthcare systems. Many people have been forced to stay in their homes due to unprecedented quarantine practices around the world. Since most people used social media during the Coronavirus epidemic, analyzing the user-generated social content can provide new insights and be a clue to track changes and their occurrence over time. An active area in this space is the prediction of new infected cases from Coronavirus-generated social content. Identifying the social content that relates to Coronavirus is a challenging task because a significant number of posts contain Coronavirus-related content but do not include hashtags or Corona-related words. Conversely, posts that have the hashtag or the word Corona but are not really related to the meaning of Coronavirus and are mostly promotional. In this paper, we propose a semantic approach based on word embedding techniques to model Corona and then introduce a new feature namely semantic similarity to measure the similarity of a given post to Corona in semantic space. Furthermore, we propose two other features namely fear emotion and hope feeling to identify the Coronavirus-related posts. These features are used as statistical indicators in a regression model to estimate the new infected cases. We evaluate our features on the Persian dataset of Instagram posts, which was collected in the first wave of Coronavirus, and demonstrate that the consideration of the proposed features will lead to improved performance of the Coronavirus incidence rate estimation.