Compared with models in previous studies including SVM, Tree-CRF, BiRNN, LSTM, and BiLSTM, our method improved the accuracy value of sentiment analysis by 24%, 24%, 19%, 17%, and 9% respectively.

Table 8. DDIE precisions of ablation experiments. From Table 8, it is found that BiGGT is superior to its variants in terms of precision, where BiGRU is better than BiRNN and BiLIST, validating that ...

Binny Mathew, Punyajoy Saha, Seid Muhie Yimam, Chris Biemann, Pawan Goyal, and Animesh Mukherjee "HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection". Accepted at AAAI 2021. Hate ...