############################################################ ## README file for the paper "The color of finance words," ## by Garcia, Hu and Rohrer (2021). ## Dated 20211201. ############################################################ ############################################################ ## Color.Part1.20211201.RData ############################################################ ## The above object has all the dictionaries used in the ## paper, as well as the MNIR loadings from the main ## specification (trained using earning calls 2006-2014). ## ## The associated code for this file is color.code.Part1.R ## ## The RData object, together with the metadata file and the ## R code allows the reader to adapt the choices we make ## when constructing the dictionaries (default settings ## yield the output in the csv files discussed above). ############################################################ ############################################################ ## Color.Part2.20211201.RData ############################################################ ## The above object has public metadata associated with the ## earnings calls we study, as well as the document-term-matrices ## (uni/bigrams) that we use in the paper. ## ## We matched our database to public sources (from Kaggle, ## see https://www.kaggle.com/borismarjanovic/price-volume-data-for-all-us-stocks-etfs). ## The metadata is the full sample that we use in the paper, ## missing values for returns simply means we could not merge ## with the Kaggle public data source. ## ## The associated code for this file is color.code.Part2.R ## ## It also contains the dtms with 65K terms we used for the ## bulk of the paper. These dtms allows us to construct ## sentiment scores for given a dictionary, as well ## as estimating the MNIR model from scratch. ############################################################ ############################################################ ## Color.Dictionaries.zip ############################################################ ## If you are interested in just getting dictionaries, ## the file Color.Dictionaries.zip has the final dictionaries ## from the paper (included in the appendix). ############################################################