Research Article
Natural Language Processing of Messages from a Social Network for Inflation Analysis
@INPROCEEDINGS{10.1007/978-3-031-22324-2_17, author={Leonardo Silva Vianna and Lizyane Rosa Antunes and Rafael Maia Pinto and Alexandre Leopoldo Gon\`{e}alves}, title={Natural Language Processing of Messages from a Social Network for Inflation Analysis}, proceedings={Data and Information in Online Environments. Third EAI International Conference, DIONE 2022, Virtual Event, July 28-29, 2022, Proceedings}, proceedings_a={DIONE}, year={2022}, month={12}, keywords={Inflation Natural language processing Network analysis}, doi={10.1007/978-3-031-22324-2_17} }- Leonardo Silva Vianna
Lizyane Rosa Antunes
Rafael Maia Pinto
Alexandre Leopoldo Gonçalves
Year: 2022
Natural Language Processing of Messages from a Social Network for Inflation Analysis
DIONE
Springer
DOI: 10.1007/978-3-031-22324-2_17
Abstract
Inflation is a progressive increase in the average price of goods and services. It can be measured using different inflation rates, which can vary according to the time, but also according to the region or country. Depending on the variation of product and service prices, users of social networks could discuss and express their private opinions about inflation. We questioned if there is a correlation between the messages transmitted by Twitter©users and the monthly variation of a specific inflation rate. Consequently, this research aims to examine Twitter©messages with content about inflation in Brazil through natural language processing and network analysis. The Twitter©messages from users in Brazil, obtained through the Application Programming Interface of this social network platform, were analyzed. The steps performed included querying the API for data acquisition, processing the messages using Natural Language Processing techniques, and executing a network analysis. We concluded that inflation influences the behavior of social network users and, additionally, natural language processing of Twitter©messages can reveal relevant knowledge for inflation analysis and have potential for prediction purposes.
