Figure 1

Direct comparison of the words in each of the dictionaries tested. For the comparison of two dictionaries, we plot words that are matched by the independent variable ‘x’ in the dependent variable ‘y’. Because of this, and cross stem matching, the plots are not symmetric across the diagonal of the entire figure. Where the scores are continuous in both dictionaries, we compute the RMA linear fit. When a sentiment dictionary contains both fixed and stem words, we plot the matches by fixed words in blue and by stem words in green. The axes in the bar plots are not of the same height, due to large mismatches in the number of words in the dictionaries, and we note the maximum height of the bar in the upper left of such plots. Detailed analysis of Panel C can be found in [39]. We provide a table for each off-diagonal panel in the S2 Appendix with the words whose scores exhibit the greatest mismatch, and a subset of these tables in Figure 2.