Identification and Explanation of Individuals’ Compliance Intention Model with Health Recommendations during Coronavirus )COVID-19 (Pandemic based on Sentiment Analysis of Social Media Users

One of the valuable resources for individuals’ emotions about various phenomena is social networks, which can be analyzed to obtain valuable information. The aim of this study was to investigate the model of compliance intention with health recommendations based on the analysis of the emotions of virtual network users in the Corona pandemic. This study was conducted by the data mining method. The statistical population of this study was the texts of Iranian users on virtual social networks Twitter, Telegram, and Instagram. In order to conduct this research, a sample of 2500 texts of pre-processed data of virtual networks Twitter, Telegram, and Instagram from February 20, 2020, to April 19, 2020, were studied, and using the support vector machine algorithm, they were classified into categories intention to compliance health recommendations, and feeling. Finally, the logistic regression method was used to investigate the research question. The findings of this research indicated that users' intention to comply with health recommendations could be predicted. based on the five emotions of fear, trust, sadness, happiness, and anticipation. The results also showed that happiness emotion has a negative relationship and the feelings of fear, trust, sadness, and anticipation have a positive relationship with the compliance intention (P<0.05). In general, the findings of this study indicated the importance of emotions in individuals' health recommendations compliance.