Usage of presuppositions in social media and news discourse can be a powerful way to influence the readers as they usually tend to not examine the truth value of the hidden or indirectly expressed information. Fairclough and Wodak (1997) discuss presupposition at a discourse level where some implicit claims are taken for granted in the explicit meaning of a text or utterance. From the Gricean perspective, the presuppositions of a sentence determine the class of contexts in which the sentence could be felicitously uttered. This paper aims to correlate the type of knowledge presupposed in a news article to the bias present in it. We propose a set of guidelines to identify various kinds of presuppositions in news articles and present a dataset consisting of 1050 articles which are annotated for bias (positive, negative or neutral) and the magnitude of presupposition. We introduce a supervised classification approach for detecting bias in political news which significantly outperforms the existing systems.

In the task of hate speech detection, there exists a high correlation between African American English (AAE) and annotators’ perceptions of toxicity in current datasets. This bias in annotated training data and the tendency of machine learning models to amplify it cause AAE text to often be mislabeled as abusive/offensive/hate speech (high false positive rate) by current hate speech classifiers. Here, we use adversarial training to mitigate this bias. Experimental results on one hate speech dataset and one AAE dataset suggest that our method is able to reduce the false positive rate for AAE text with only a minimal compromise on the performance of hate speech classification.

Although a lot of research has been done on utilising Online Social Media during disasters, there exists no system for a specific task that is critical in a post-disaster scenario – identifying resource-needs and resource-availabilities in the disaster-affected region, coupled with their subsequent matching. To this end, we present NARMADA, a semi-automated platform which leverages the crowd-sourced information from social media posts for assisting post-disaster relief coordination efforts. The system employs Natural Language Processing and Information Retrieval techniques for identifying resource-needs and resource-availabilities from microblogs, extracting resources from the posts, and also matching the needs to suitable availabilities. The system is thus capable of facilitating the judicious management of resources during post-disaster relief operations.

Toxic comments in online platforms are an unavoidable social issue under the cloak of anonymity. Hate speech detection has been actively done for languages such as English, German, or Italian, where manually labeled corpus has been released. In this work, we first present 9.4K manually labeled entertainment news comments for identifying Korean toxic speech, collected from a widely used online news platform in Korea. The comments are annotated regarding social bias and hate speech since both aspects are correlated. The inter-annotator agreement Krippendorff’s alpha score is 0.492 and 0.496, respectively. We provide benchmarks using CharCNN, BiLSTM, and BERT, where BERT achieves the highest score on all tasks. The models generally display better performance on bias identification, since the hate speech detection is a more subjective issue. Additionally, when BERT is trained with bias label for hate speech detection, the prediction score increases, implying that bias and hate are intertwined. We make our dataset publicly available and open competitions with the corpus and benchmarks.

We investigate whether pre-trained bidirectional transformers with sentiment and emotion information improve stance detection in long discussions of contemporary issues. As a part of this work, we create a novel stance detection dataset covering 419 different controversial issues and their related pros and cons collected by procon.org in nonpartisan format. Experimental results show that a shallow recurrent neural network with sentiment or emotion information can reach competitive results compared to fine-tuned BERT with 20x fewer parameters. We also use a simple approach that explains which input phrases contribute to stance detection.

We propose the task of emotion style transfer, which is particularly challenging, as emotions (here: anger, disgust, fear, joy, sadness, surprise) are on the fence between content and style. To understand the particular difficulties of this task, we design a transparent emotion style transfer pipeline based on three steps: (1) select the words that are promising to be substituted to change the emotion (with a brute-force approach and selection based on the attention mechanism of an emotion classifier), (2) find sets of words as candidates for substituting the words (based on lexical and distributional semantics), and (3) select the most promising combination of substitutions with an objective function which consists of components for content (based on BERT sentence embeddings), emotion (based on an emotion classifier), and fluency (based on a neural language model). This comparably straight-forward setup enables us to explore the task and understand in what cases lexical substitution can vary the emotional load of texts, how changes in content and style interact and if they are at odds. We further evaluate our pipeline quantitatively in an automated and an annotation study based on Tweets and find, indeed, that simultaneous adjustments of content and emotion are conflicting objectives: as we show in a qualitative analysis motivated by Scherer’s emotion component model, this is particularly the case for implicit emotion expressions based on cognitive appraisal or descriptions of bodily reactions.

Chinese word segmentation is necessary to provide word-level information for Chinese named entity recognition (NER) systems. However, segmentation error propagation is a challenge for Chinese NER while processing colloquial data like social media text. In this paper, we propose a model (UIcwsNN) that specializes in identifying entities from Chinese social media text, especially by leveraging uncertain information of word segmentation. Such ambiguous information contains all the potential segmentation states of a sentence that provides a channel for the model to infer deep word-level characteristics. We propose a trilogy (i.e., Candidate Position Embedding => Position Selective Attention => Adaptive Word Convolution) to encode uncertain word segmentation information and acquire appropriate word-level representation. Experimental results on the social media corpus show that our model alleviates the segmentation error cascading trouble effectively, and achieves a significant performance improvement of 2% over previous state-of-the-art methods.

Two prevalent transfer learning approaches are used in recent works to improve neural networks performance for domains with small amounts of annotated data: Multi-task learning which involves training the task of interest with related auxiliary tasks to exploit their underlying similarities, and Mono-task fine-tuning, where the weights of the model are initialized with the pretrained weights of a large-scale labeled source domain and then fine-tuned with labeled data of the target domain (domain of interest). In this paper, we propose a new approach which takes advantage from both approaches by learning a hierarchical model trained across multiple tasks from a source domain, and is then fine-tuned on multiple tasks of the target domain. Our experiments on four tasks applied to the social media domain show that our proposed approach leads to significant improvements on all tasks compared to both approaches.