dictNN: A Dictionary-Enhanced CNN Approach for Classifying Hate Speech on Twitter

Abstract

Hate speech on social media is a growing concern, and automated methods have so far been sub-par at reliably detecting it. A major challenge lies in the potentially evasive nature of hate speech due to the ambiguity and fast evolution of natural language. To tackle this, we introduce a vectorisation based on a crowdsourced and continuously updated dictionary of hate words and propose fusing this approach with standard word embedding in order to improve the classification performance of a CNN model. To train and test our model we use a merge of two established datasets (110,748 tweets in total). By adding the dictionaryenhanced input, we are able to increase the CNN model's predictive power and increase the F1 macro score by seven percentage points.

Prompt engineering for zero‐shot and few‐shot defect detection and classification using a visual‐language pretrained model

“…Expanding the information of input data quantitatively and qualitatively by referring to a dictionary can boost the performance of a deep learning model (Kupi et al, 2021;Peng et al, 2020;Qiu et al, 2020). Motivated by this technique, this study tailored prompts by looking up dictionaries.…”