As social media booms, abusive online practices such as hate speech have unfortunately increased as well. As letters are often repeated in words used to construct social media messages, these types of words should be eliminated or reduced in number to enhance the efficacy of hate speech detection. Although multiple models have attempted to normalize out-of-vocabulary (OOV) words with repeated letters, they often fail to determine whether the in-vocabulary (IV) replacement words are correct or incorrect. Therefore, this study developed an improved model for normalizing OOV words with repeated letters by replacing them with correct in-vocabulary (IV) replacement words. The improved normalization model is an unsupervised method that does not require the use of a special dictionary or annotated data. It combines rule-based patterns of words with repeated letters and the SymSpell spelling correction algorithm to remove repeated letters within the words by multiple rules regarding the position of repeated letters in a word, be it at the beginning, middle, or end of the word and the repetition pattern. Two hate speech datasets were then used to assess performance. The proposed normalization model was able to decrease the percentage of OOV words to 8%. Its F1 score was also 9% and 13% higher than the models proposed by two extant studies. Therefore, the proposed normalization model performed better than the benchmark studies in replacing OOV words with the correct IV replacement and improved the performance of the detection model. As such, suitable rule-based patterns can be combined with spelling correction to develop a text normalization model to correctly replace words with repeated letters, which would, in turn, improve hate speech detection in texts.
Compassionate feelings for people who are victimized because of their perceived sexual deviance (e.g., gay men) may be incompatible with support for heterosexual norms among heterosexual men. But, indifference (or passivity) toward such victims could raise concern over heterosexual men's gay-tolerance attitude. Two classic social psychological theories offer competing explanations on when heterosexual men might be passive or compassionate toward gay victims of hate crime. The bystander model proposes passivity toward victims in an emergency situation if other bystanders are similarly passive, but compassionate reactions if bystanders are responsive to the victims. Conversely, the social loafing model proposes compassionate reactions toward victims when bystanders are passive, but passivity when other bystanders are already responsive toward the victims' predicament. We tested and found supportive evidence for both models across two experiments (Ntotal = 501) in which passivity and compassionate reactions to gay victims of a purported hate crime were recorded after heterosexual men's concern for social evaluation was either accentuated or relaxed. We found that the bystander explanation was visible only when the potential for social evaluation was strong, while the social loafing account occurred only when the potential for social evaluation was relaxed. Hence, we unite both models by showing that the bystander explanation prevails in situations where cues to social evaluation are strong, whereas the social loafing effect operates when concern over social judgement is somewhat muted.