Banque de France RPS Submitter, M. Ranvier, Mathilde Gerardin
{"title":"丰富法兰西银行月度商业调查:来自商业领袖评论文本分析的教训","authors":"Banque de France RPS Submitter, M. Ranvier, Mathilde Gerardin","doi":"10.2139/ssrn.3885553","DOIUrl":null,"url":null,"abstract":"In the context of the Banque de France’s monthly business survey, this document presents<br>the main findings of the textual analysis of business leaders’ comments. First, the richness<br>of these data is illustrated via an elementary sentiment index and the identification of the<br>main social movements since 2009 by means of keywords. Then, the article presents two<br>statistical applications whose reproducibility is discussed. The first one, applied to the 2018<br>yellow vests and the 2019 strikes, aims to estimate the impact on GDP of an event whose<br>effect is unequivocal. The second, backed by the study of Brexit, aims to characterize,<br>using a supervised learning model and word vectors, the effects of a complex event with<br>multiple impacts.","PeriodicalId":101534,"journal":{"name":"Banque de France Research Paper Series","volume":"417 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Enrichment of the Banque de France’s monthly business survey: lessons from textual analysis of business leaders’ comments\",\"authors\":\"Banque de France RPS Submitter, M. Ranvier, Mathilde Gerardin\",\"doi\":\"10.2139/ssrn.3885553\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In the context of the Banque de France’s monthly business survey, this document presents<br>the main findings of the textual analysis of business leaders’ comments. First, the richness<br>of these data is illustrated via an elementary sentiment index and the identification of the<br>main social movements since 2009 by means of keywords. Then, the article presents two<br>statistical applications whose reproducibility is discussed. The first one, applied to the 2018<br>yellow vests and the 2019 strikes, aims to estimate the impact on GDP of an event whose<br>effect is unequivocal. The second, backed by the study of Brexit, aims to characterize,<br>using a supervised learning model and word vectors, the effects of a complex event with<br>multiple impacts.\",\"PeriodicalId\":101534,\"journal\":{\"name\":\"Banque de France Research Paper Series\",\"volume\":\"417 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Banque de France Research Paper Series\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.2139/ssrn.3885553\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Banque de France Research Paper Series","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2139/ssrn.3885553","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Enrichment of the Banque de France’s monthly business survey: lessons from textual analysis of business leaders’ comments
In the context of the Banque de France’s monthly business survey, this document presents the main findings of the textual analysis of business leaders’ comments. First, the richness of these data is illustrated via an elementary sentiment index and the identification of the main social movements since 2009 by means of keywords. Then, the article presents two statistical applications whose reproducibility is discussed. The first one, applied to the 2018 yellow vests and the 2019 strikes, aims to estimate the impact on GDP of an event whose effect is unequivocal. The second, backed by the study of Brexit, aims to characterize, using a supervised learning model and word vectors, the effects of a complex event with multiple impacts.