Social media users often express hate speech towards specific targets and may either support or refuse activist movements. The automated detection of hate speech, which involves identifying both targets and stances, plays a critical role in event identification to mitigate its negative effects. In this paper, we present our methods for three subtasks of the Climate Activism Stance and Hate Event Detection Shared Task at CASE 2024. For each subtask (i) hate speech identification (ii) targets of hate speech identification (iii) stance detection, we experiment with optimized Transformer-based architectures that focus on tweet-specific features such as hashtags, URLs, and emojis. Furthermore, we investigate generative large language models, such as Llama2, using specific prompts for the first two subtasks. Our experiments demonstrate better performance of our models compared to baseline models in each subtask. Our solutions also achieve third, fourth, and first places respectively in the subtasks.

Text-embedded images can serve as a means of spreading hate speech, propaganda, and extremist beliefs. Throughout the Russia-Ukraine war, both opposing factions heavily relied on text-embedded images as a vehicle for spreading propaganda and hate speech. Ensuring the effective detection of hate speech and propaganda is of utmost importance to mitigate the negative effect of hate speech dissemination. In this paper, we outline our methodologies for two subtasks of Multimodal Hate Speech Event Detection 2023. For the first subtask, hate speech detection, we utilize multimodal deep learning models boosted by ensemble learning and syntactical text attributes. For the second subtask, target detection, we employ multimodal deep learning models boosted by named entity features. Through experimentation, we demonstrate the superior performance of our models compared to all textual, visual, and text-visual baselines employed in multimodal hate speech detection. Furthermore, our models achieve the first place in both subtasks on the final leaderboard of the shared task.

Automated socio-political protest event detection is a challenging task when multiple languages are considered. In CASE 2022 Task 1, we propose ensemble learning methods for multilingual protest event detection in four subtasks with different granularity levels from document-level to entity-level. We develop an ensemble of fine-tuned Transformer-based language models, along with a post-processing step to regularize the predictions of our ensembles. Our approach places the first place in 6 out of 16 leaderboards organized in seven languages including English, Mandarin, and Turkish.

The performance of hate speech detection models relies on the datasets on which the models are trained. Existing datasets are mostly prepared with a limited number of instances or hate domains that define hate topics. This hinders large-scale analysis and transfer learning with respect to hate domains. In this study, we construct large-scale tweet datasets for hate speech detection in English and a low-resource language, Turkish, consisting of human-labeled 100k tweets per each. Our datasets are designed to have equal number of tweets distributed over five domains. The experimental results supported by statistical tests show that Transformer-based language models outperform conventional bag-of-words and neural models by at least 5% in English and 10% in Turkish for large-scale hate speech detection. The performance is also scalable to different training sizes, such that 98% of performance in English, and 97% in Turkish, are recovered when 20% of training instances are used. We further examine the generalization ability of cross-domain transfer among hate domains. We show that 96% of the performance of a target domain in average is recovered by other domains for English, and 92% for Turkish. Gender and religion are more successful to generalize to other domains, while sports fail most.

Supervised training with cross-entropy loss implicitly forces models to produce probability distributions that follow a discrete delta distribution. Model predictions in test time are expected to be similar to delta distributions if the classifier determines the class of an input correctly. However, the shape of the predicted probability distribution can become similar to the uniform distribution when the model cannot infer properly. We exploit this observation for detecting out-of-scope (OOS) utterances in conversational systems. Specifically, we propose a zero-shot post-processing step, called Distance-to-Uniform (D2U), exploiting not only the classification confidence score, but the shape of the entire output distribution. We later combine it with a learning procedure that uses D2U for loss calculation in the supervised setup. We conduct experiments using six publicly available datasets. Experimental results show that the performance of OOS detection is improved with our post-processing when there is no OOS training data, as well as with D2U learning procedure when OOS training data is available.