2021/10/05 by Fatemeh Salmani, Salmani, Fatemeh, Hamed Vahdat‐Nejad +3
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Sentiment Analysis and Opinion Mining #Social and Information Networks (cs.SI)
paper · pdf · doi:10.48550/arxiv.2110.02198
openalex publication_date 2021/10/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
One of the most important incidents in the world in 2020 is the outbreak of\nthe Coronavirus. Users on social networks publish a large number of comments\nabout this event. These comments contain important hidden information of public\nopinion regarding this pandemic. In this research, a large number of\nCoronavirus-related tweets are considered and analyzed using natural language\nprocessing and information retrieval science. Initially, the location of the\ntweets is determined using a dictionary prepared through the Geo-Names\ngeographic database, which contains detailed and complete information of places\nsuch as city names, streets, and postal codes. Then, using a large dictionary\nprepared from the terms of economics, related tweets are extracted and\nsentiments corresponded to tweets are analyzed with the help of the RoBERTa\nlanguage-based model, which has high accuracy and good performance. Finally,\nthe frequency chart of tweets related to the economy and their sentiment scores\n(positive and negative tweets) is plotted over time for the entire world and\nthe top 10 economies. From the analysis of the charts, we learn that the reason\nfor publishing economic tweets is not only the increase in the number of people\ninfected with the Coronavirus but also imposed restrictions and lockdowns in\ncountries. The consequences of these restrictions include the loss of millions\nof jobs and the economic downturn.\n