Sentiment

Our measures of sentiment count positive and negative tone words, as defined by Loughran and McDonald (2011). Frequently used positive and negative tone include "good," "strong," "great," and "loss," "decline," and "difficult," respectively.

Overall Sentiment

Our measure of overall firm-level sentiment simply counts the frequency of mentions of positive words, deducts the frequency of mentions of negative words, and then divides by the length of the transcript. For our analysis we multiply the resulting measure by 100,000.

Reference & details

Political Sentiment

Following the same procedure as in the construction of PRisk_it (eq. 1), we measure the firm's political sentiment by counting the use of political but not non-political bigrams, but now conditioning on proximity to positive and negative words, rather than synonyms of risk or uncertainty:

where S(c ) is a function that assigns a value of +1 if bigram c is associated with positive sentiment (using Loughran & McDonald (2011)'s sentiment dictionary), a value of -1 if bigram c is associated with negative sentiment, and 0 otherwise. For our analysis we multiply the resulting measure by 100,000.

Reference & details

Non-political Sentiment

We measure the firm's non-political Sentiment in the same way as PSentiment_i,t(eq. 5), but count and weight non-political bigrams rather than political bigrams, that is, ℕ \ ℙ rather than ℙ \ ℕ. For our analysis we multiply the resulting measure by 100,000.

Reference & details