Efficient E-Mail Spam Detection Strategy Using Genetic Decision Tree Processing with NLP Features

Table 1

Description of dataset attributes.

Attributes	Type	Description
1–48	char_freq_CHAR	The number of characters in an e-mail that are the same as CHAR.
49–54	capital_run_length_average	The average length of consecutive capital letter sequences
55	capital_run_length_longest	Longest consecutive capital letter sequence length
56	capital_run_length_longest	Longest consecutive capital letter sequence length
57	capital_run_length_total	Overall capital letters in e-mail
58	Class attribute	Indicating if an e-mail is classified as spam with class label (1) or not spam with class label (0)