000006126 001__ 6126 000006126 005__ 20240523054002.0 000006126 0247_ $$2doi$$a10.6082/uchicago.6126 000006126 037__ $$aTHESIS$$bThesis 000006126 041__ $$aeng 000006126 245__ $$aEstimating Daily US Inflation Expectations Using Twitter 000006126 260__ $$bUniversity of Chicago 000006126 269__ $$a2023-06-03 000006126 336__ $$aThesis 000006126 502__ $$bM.A. 000006126 520__ $$aUsing natural language processing methods with Twitter data, I estimate a daily series of short-run US inflation expectations for the 2020-2022 period. Treating survey-based sources as a benchmark, I show that Twitter series reveals a similar pattern with a correlation of 89% with the survey data. Using tweet geolocation, I document state-level heterogeneity in inflation expectations that may be explained via differences in regional cost of living. Finally, as an application for macroeconomic forecasting, I show that the daily Twitter series is predictive of movements in future inflation, making it a relevant input in (now)forecasting exercises. More generally, this paper illustrates a textual analysis pipeline that can be used to extract inflation expectations almost concurrently and cost-effectively and highlights the potential of using unstructured text to obtain critical information about the perceived current state of the economy. 000006126 542__ $$fCC BY-NC 000006126 591__ $$aI would like to thank the University of Chicago’s Social Sciences Computing Services for supporting this work. 000006126 6531_ $$aUS Inflation Expectations 000006126 6531_ $$aNatural Language Processing 000006126 6531_ $$aLatent Dirichlet Allocation 000006126 6531_ $$aTwitter 000006126 690__ $$aSocial Sciences Division 000006126 691__ $$aComputational Social Sciences (MACSS) 000006126 7001_ $$aYasin, Awaid$$uUniversity of Chicago 000006126 72012 $$aMichael Weber 000006126 72014 $$aRui Zhao 000006126 8564_ $$95d9e1bd3-c88e-420d-ae6a-01fcebf9a577$$s3416409$$uhttps://knowledge.uchicago.edu/record/6126/files/Yasin_Awaid_MA_Thesis.pdf$$erestricted 000006126 908__ $$aI agree 000006126 909CO $$ooai:uchicago.tind.io:6126$$pGLOBAL_SET$$pTheses 000006126 983__ $$aThesis