Review Article

Survey on Astroturfing Detection and Analysis from an Information Technology Perspective

Table 2

Parameters and notation.

NotationMeaning

Account
pThe percentage of replies, and astroturfing has a relatively low value.
P is the probability of word appears, and is the joint probability.
sThe consecutive sentence
Semantic vector representation
kThe piece of a certain sentence, and K is the total number of pieces
lThe total quantity of the sentences in the piece
Following similarity, and denotes the following similarity of the accounts and
FOriginal tweets set, denotes the original tweets set for the account u
Low followers, and astroturfing has a relatively high value.
Retweet similarity, and denotes the retweet similarity between the accounts and
, is the retweeting time, and is the retweet ID
The most dominant application’s percentage
The posting frequency, and the astroturfing has a relatively high value
The number of received clicks, and astroturfing has a relatively low value
The transition probability from the word to
Sentence transition, and astroturfing has a relatively high value
Word cooccurrence
The average score of two consecutive sentences and
The best score of two consecutive sentences and
Pairwise sentence similarity
SDSemantic dispersion, and the astroturfing has a relatively high value