Abstarct: Corona 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, which have changed their lifestyles. Therefore, early presentation of symptoms before the outbreak is essential for early public health responses. Since most people used social media during the Corona 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 Corona-generated social content. Identifying the social content that relates to Corona is a challenging task because a significant number of posts contain Corona-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 Corona and are mostly promotional. In this paper, we propose a semantic approach baxsed 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. In addition to semantic similarity, we propose two other features namely fear emotion and hope feeling to identify the Corona-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 Corona, and demonstrate that the consideration of the proposed features will lead to improved performance of the Corona incidence rate estimation. Furthermore, we show that the interpolation of these features with each other improves the estimation performance.