Assessing the spread of Keynesian ideas in the economic policy debate: a Text Mining approach on Twitter
[EN] This paper proposes a methodology for examining the presence of Keynesian ideas in the economic debate. To this aim we use Twitter as a source of data to monitor the debate in real time. We quantify the presence of Keynesian and anti-Keynesian thought in tweets about the economy and we qualify...
| Autores: | , , |
|---|---|
| Formato: | capítulo de livro |
| Fecha de publicación: | 2023 |
| País: | España |
| Recursos: | Universitat Politècnica de València (UPV) |
| Repositorio: | RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia |
| Idioma: | inglés |
| OAI Identifier: | oai:riunet.upv.es:10251/201778 |
| Acesso em linha: | https://riunet.upv.es/handle/10251/201778 |
| Access Level: | acceso abierto |
| Palavra-chave: | Text Mining Keynesian thought |
| Resumo: | [EN] This paper proposes a methodology for examining the presence of Keynesian ideas in the economic debate. To this aim we use Twitter as a source of data to monitor the debate in real time. We quantify the presence of Keynesian and anti-Keynesian thought in tweets about the economy and we qualify the emotional tone of these tweets. Our preliminary results show that the 20 per-cent of total English tweets about #economy contain words related to Keynes while about 8 per- cent contain words referring to anti-Keynesian policies. The monthly analysis of the tweets shows a certain heterogeneity. The distribution of Keynes-related tweets is much more uneven than the distribution of anti-keynesian tweets. Our evidence suggests that the methodology we applied to understand how much of the Keynesian thought is still around in the economic debate can be promising. The next step will be to focus on georeferenced tweets to detect heterogenity across countries and to understand how country-level trends reflect the economy cycle. This study still has some limitations that will be faced in future research such as the classification of topics and the focus on English texts for the moment. |
|---|