[WIP] Common Derogatory Words and Linguistic Structures

[malteserteresa]

Objective
Identifying derogatory terms and linguistic structures in the data sets

Description

Skills

Tools

Time Estimation

Tasks

• Step 1
• Step 2
• Step 3

[mgeyrdnlr]

In the gold data set, out of 318.765 word tokens, the most frequent terms and word groups, which can be considered as misogynistic as well as discriminating (without knowing the context), are:

1. bitch (freq. 1779)
2. feminazi (freq. 773)
3. whore (freq.615)
4. cunt (freq. 543)
5. hysterical ( freq. 413)
6. skank (freq. 350)
7. hoe (freq. 326)
8. pussy (freq. 291)
9. slut (freq. 214)
10. ugly (freq. 176)
11. bitches (freq. 131)
12. womensuck (freq. 123)
13. dyke (freq. 105)
14. nigga (freq. 63)
15. kunt (freq. 55)
16. whores (freq. 37)
17. cunts (freq. 24)
18. feminismisawful (freq. 16)
19. skanks(freq. 16)
20. bitchy (freq. 14)

[mgeyrdnlr]

In the gold data set, out of 318.765 word tokens, the most frequent words and word groups, around which potentially a misogynistic statement can be built, are:

1. women (freq. 1748)
2. sexist (freq. 1036)
3. she (freq. 909)
4. her (freq. 882)
5. woman (freq. 832)
6. fucking (freq. 682)
7. fuck (freq. 677)
8. rape (freq. 651)
9. stupid (freq. 365)
10. girl (freq. 363)
11. hate (freq. 273)
12. female (freq. 265)
13. notsexist (freq. 208)
14. male )freq. 143)
15. feminism (freq. 139).
16. feminist (freq. 139)
17. feminists (freq. 138)
18. womensuck (freq. 123)
19. abuse (freq. 88)
20. realdonaldtrump (freq. 88)
21. sexual (freq. 88)
22. ladies (freq. 77)
23. crazy (76)
24. cooking (freq. 73)
25. females (freq. 69)
26. gender (freq. 69)
27. camel (freq. 65)
28. toe (freq. 64)
29. equality (freq. 63)
30. raped ( freq. 63)
31. equal (freq. 62)
32. fuckin (freq. 60)
33. fucked (freq. 57)
34. trans (freq. 55)
35. mother (freq. 54)
36. sexism (freq. 54)
37. womenagainstfeminism (freq. 49)
38. disgusting (freq. 48)
39. abortion (freq. 46)
40. notallmen (freq. 37)
41. lady (freq. 36)
42. vagina (freq. 28)
43. rapists (freq. 27)
44. weinstein (freq. 27)
45. penis (freq. 22)
46. lesbian (freq. 19)
47. maledominance (freq. 19)
48. sexually (freq. 18)
49. boobs (freq. 11)
50. feminine (freq. 9)