... compare two corpora: (1) the full set of blogposts, referred to as the standard corpus, and (2) acorpus associated with the peaking interval, re-ferred to as the sample corpus.To compare ... of a term, Niits total frequency, and Ei= (Ni·iOi)/iNiits expected frequencyin corpus i (where i takes values 1 and 2 for thestandard and sample corpus, respectively). Then,the ... entry, the text of the post along with the date and time are indexed. Posts without an explicitmood indication (10M) are discarded. We appliedstandard preprocessing steps (stopword removal,stemming)...